my-ai-tools
Marketplace for my-ai-tools plugins
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/jellydn/my-ai-tools with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/jellydn/my-ai-tools'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/jellydn--my-ai-tools)HTML
<a href="/listings/jellydn--my-ai-tools"><img src="/api/listings/jellydn--my-ai-tools/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
These steps run a script from the network that findsafeskills does not scan.
The installer can replace existing configuration files. Run a dry run first and use `--backup` or `-Backup` when you want a restorable copy.
macOS, Linux, and WSL
Review the installer, then run it:
curl -fsSL https://ai-tools.itman.fyi/install.sh -o install.sh less install.sh bash install.sh --dry-run bash install.sh --backup
For a direct one-line installation:
curl -fsSL https://ai-tools.itman.fyi/install.sh | bash
Windows 11
Open PowerShell and run the canonical installer:
Invoke-RestMethod https://ai-tools.itman.fyi/install.ps1 | Invoke-Expression
This downloads and executes a remote script. Review [install.ps1](install.ps1) before trusting it. It installs missing prerequisites through `winget`, reuses existing tools, refreshes PATH for the current process, and starts the shared installer in Git Bash. Windows may request administrator approval for Git or Node.js installation. Package installation uses `--source winget`, not the Microsoft Store. Node and npm are discovered again after installation and passed to Git Bash in the same process; no separate prerequisite command or terminal restart is needed after a successful install. The wrapper skips Git Bash login profiles so an older shell PATH cannot hide these tools. Approve only the package installer's elevation prompt; the wrapper does not relaunch the full configuration installer as administrator. If approval is denied, setup stops and can be rerun safely. Native Windows uses Node/npm, not Bun, for package installation; Linux, macOS, and WSL keep Bun-first behavior.
The installer can replace existing configuration. To inspect the script, preview changes, and request a backup, use the saved-script path instead:
Invoke-RestMethod https://ai-tools.itman.fyi/install.ps1 -OutFile install.ps1 Get-Content .\install.ps1 powershell -NoProfile -ExecutionPolicy Bypass -File .\install.ps1 -DryRun powershell -NoProfile -ExecutionPolicy Bypass -File .\install.ps1 -Backup
Execution-policy bypass applies only to that process. `-DryRun` does not install prerequisites; install them first if the preview reports they are missing. The one-line command is non-interactive and automatically uses `--yes`.
If setup fails, resolve the reported error and rerun the same command. If a newly installed prerequisite still cannot be found, close all terminal windows and reopen PowerShell. If `winget` is missing, install or update [App Installer](https://aka.ms/getwinget), or install [Git for Windows](https://git-scm.com/download/win), [`jq`](https://jqlang.org/download/), and [Node.js LTS with npm](https://nodejs.org/) manually. In Git setup, select **Git from the command line and also from 3rd-party software**. Do not bypass package lifecycle errors with `--ignore-scripts`: native binaries can remain uninstalled.
If the wrapper says all prerequisites are met but Bash then reports missing Node/npm, check that the downloaded `install.ps1` includes `Find-Node` and the `OpenJS.NodeJS.LTS` installation step. A stale web deployment can serve an older wrapper while cloning the latest Bash installer. Maintainers must check the **Dokku Deploy** workflow for `ai-tools.itman.fyi`; a successful **Deploy GitHub Pages** run does not update that domain. Until the domain is updated, use a reviewed repository checkout and run:
powershell -NoProfile -ExecutionPolicy Bypass -File .\install.ps1 -Yes
Repository checkout
git clone https://github.com/jellydn/my-ai-tools.git cd my-ai-tools ./cli.sh --dry-run ./cli.sh --backup
On Windows PowerShell, use the native wrapper from the checkout:
git clone https://github.com/jellydn/my-ai-tools.git Set-Location my-ai-tools .\install.ps1 -DryRun .\install.ps1 -Backup
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 267 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- {
- "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
- "name": "my-ai-tools",
- "description": "Marketplace for my-ai-tools plugins",
- "owner": {
- "name": "my-ai-tools",
- "email": "dung@productsway.com"
- },
- "plugins": [
- {
- "name": "accountable-engineering",
- "description": "Guides disciplined AI-assisted engineering that avoids cognitive surrender and keeps humans accountable. Use for non-trivial implementation, architecture, security, or operational tasks.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/accountable-engineering",
- "category": "productivity"
- },
- {
- "name": "babysit-pr",
- "description": "Monitors an open GitHub PR for CI failures, review feedback, mergeability, and safe retries or fixes.",
- "version": "1.0.0",
- "author": {
- "name": "my-ai-tools contributors"
- },
- "source": "./skills/babysit-pr",
- "category": "productivity"
- },
- {
- "name": "adr",
- "description": "Manages Architecture Decision Records (ADR) for tracking important architectural decisions. Initialize, create, list, search, and view ADRs.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/adr",
- "category": "productivity"
- },
- {
- "name": "codemap",
- "description": "Orchestrate parallel codebase analysis to produce 7 structured documents (STACK, INTEGRATIONS, ARCHITECTURE, STRUCTURE, CONVENTIONS, TESTING, CONCERNS) in .planning/codebase/.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/codemap",
- "category": "productivity",
- "homepage": "https://github.com/jellydn/my-ai-tools"
- },
- {
- "name": "commit-atomic",
- "description": "Creates atomic commits by logically grouping staged changes with commitizen convention",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/commit-atomic",
- "category": "productivity"
- },
- {
- "name": "docs-update",
- "description": "Update user-facing documentation when code changes. Use when asked to update docs, review docs, handle documentation changes, run scheduled documentation tasks, or analyze recent commits for documentation needs.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/docs-update",
- "category": "productivity"
- },
- {
- "name": "draft-pull-request",
- "description": "Creates or updates a draft pull request using gh CLI with a what/why/how description and optional change-outline views",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/draft-pull-request",
- "category": "productivity"
- },
- {
- "name": "handoffs",
- "description": "Creates detailed handoff plans of conversations for continuing work in new sessions. Capture context, technical decisions, and pending tasks for seamless session continuation.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/handoffs",
- "category": "productivity"
- },
- {
- "name": "llm-wiki",
- "description": "Build and maintain a persistent, compounding knowledge wiki from raw sources. Use when the user wants to create a knowledge base, ingest documents into a wiki, query a wiki, health-check a wiki, or set up Karpathy's LLM Wiki pattern.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/llm-wiki",
- "category": "productivity",
- "homepage": "https://github.com/jellydn/my-ai-tools"
- },
- {
- "name": "pickup",
- "description": "Resumes work from previous handoff sessions stored in .planning/handoffs/. Load and continue from where you left off in prior sessions.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/pickup",
- "category": "productivity"
- },
- {
- "name": "plannotator-setup-goal",
- "description": "Turn an idea into a structured goal package via Plannotator-gated discovery, fact sheet, and plan.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/plannotator-setup-goal",
- "category": "productivity"
- },
- {
- "name": "portless-local",
- "description": "Named .localhost URLs for local development - replaces port numbers with stable, readable URLs",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/portless-local",
- "category": "productivity"
- },
- {
- "name": "pr-review",
- "description": "Fix PR review comments by implementing requested changes. Fetch review comments, implement fixes, run tests, and commit changes.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/pr-review",
- "category": "productivity"
- },
- {
- "name": "prd",
- "description": "Generate Product Requirements Documents (PRD) for new features. Use when planning features, starting projects, or creating specifications.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/prd",
- "category": "productivity"
- },
- {
- "name": "qmd-knowledge",
- "description": "Project-specific knowledge management system using qmd MCP server. Captures learnings, issue notes, and conventions in a searchable knowledge base.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/qmd-knowledge",
- "category": "productivity",
- "homepage": "https://github.com/jellydn/my-ai-tools"
- },
- {
- "name": "ralph",
- "description": "Convert PRDs to prd.json format for the Ralph autonomous agent system. Converts markdown PRDs to Ralph's JSON format.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/ralph",
- "category": "productivity"
- },
- {
- "name": "security-audit",
- "description": "Perform structured security audits using OWASP Top 10, ASVS, cheat sheets, framework checks, and DevSecOps controls.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/security-audit",
- "category": "code-quality"
- },
- {
- "name": "slop",
- "description": "Removes AI-generated code slop from git diffs to maintain code quality. Clean up extra comments, defensive checks, type casts, and inconsistent style.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/slop",
- "category": "productivity"
- },
- {
- "name": "tdd",
- "description": "Guides through the complete TDD workflow with Red-Green-Refactor cycle. Start features, write failing tests, implement minimal code, and refactor with confidence.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/tdd",
- "category": "productivity"
- },
- {
- "name": "code-quality-review",
- "description": "Run an extremely strict maintainability and structural code quality review — flags abstraction issues, spaghetti growth, and boundary leaks",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/code-quality-review",
- "category": "code-quality"
- },
- {
- "name": "code-review",
- "description": "Review the diff since a fixed point along two axes — Conventions (does the code follow this repo's coding standards and Tidy First practices?) and Intent (does the change do what it claims to do?). Runs both reviews in parallel sub-agents and reports them side by side.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/code-review",
- "category": "code-quality"
- },
- {
- "name": "tmux",
- "description": "Remote control tmux sessions for interactive CLIs (python, node, gdb, etc.) by sending keystrokes and capturing pane output. Integrates with LogPilot for AI-assisted log analysis.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/tmux",
- "category": "terminal-automation",
- "homepage": "https://github.com/jellydn/logpilot"
- },
- {
- "name": "visual-pr",
- "description": "Posts a concise visual outline as a GitHub pull request comment without replacing the pull request description.",
- "version": "1.0.0",
- "author": {
- "name": "Dung Huynh Duc",
- "email": "dung@productsway.com"
- },
- "source": "./skills/visual-pr",
- "category": "productivity"
- }
- ]
- }
README.md · README · 509 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # Welcome to my-ai-tools 👋
- [](https://github.com/jellydn/my-ai-tools/actions/workflows/test.yml)
- [](https://github.com/jellydn/my-ai-tools/stargazers)
- [](LICENSE)
- [](CONTRIBUTING.md)
- > Portable, source-controlled configuration for AI coding assistants.
- `my-ai-tools` installs one consistent set of agent guidelines, skills, commands, hooks, MCP servers, and tool
- settings across supported AI coding assistants. It can also export local configuration changes back into this
- repository.
- 📖 [Documentation website](https://ai-tools.itman.fyi) · 🎬 [Setup video](https://www.youtube.com/watch?v=ESudSFAyuuw)
- ## ✨ Features
- - Configures Claude Code, OpenCode, Amp, Codex, Cursor, Pi, Antigravity, and many other assistants.
- - Shares reusable skills, agent guidance, commands, hooks, and MCP server definitions.
- - Supports macOS, Linux, Windows 11 with PowerShell and Git Bash, and WSL.
- - Provides side-effect-free dry runs and optional backups before installation.
- - Exports installed configurations back to the repository for bidirectional sync.
- - Validates JSON and other supported configuration files before installation.
- ## 📋 Requirements
- ### macOS, Linux, and WSL
- - Bash 3.0 or later
- - Git
- - `curl` for the one-line installer
- - Bun or Node.js LTS for JavaScript-based tools
- ### Windows 11
- - Windows PowerShell 5.1 or PowerShell 7
- - [`winget`](https://learn.microsoft.com/windows/package-manager/winget/) (App Installer) for automatic prerequisite setup
- The installer handles Git for Windows (including Git Bash), `jq`, and Node.js LTS with npm. You do not need to
- install them separately or open Git Bash first. WSL users can use the Linux instructions.
- ## 🚀 Installation
- The installer can replace existing configuration files. Run a dry run first and use `--backup` or `-Backup` when
- you want a restorable copy.
- ### macOS, Linux, and WSL
- Review the installer, then run it:
- ```bash
- curl -fsSL https://ai-tools.itman.fyi/install.sh -o install.sh
- less install.sh
- bash install.sh --dry-run
- bash install.sh --backup
- ```
- For a direct one-line installation:
- ```bash
- curl -fsSL https://ai-tools.itman.fyi/install.sh | bash
- ```
- ### Windows 11
- Open PowerShell and run the canonical installer:
- ```powershell
- Invoke-RestMethod https://ai-tools.itman.fyi/install.ps1 | Invoke-Expression
- ```
- This downloads and executes a remote script. Review [install.ps1](install.ps1) before trusting it. It installs
- missing prerequisites through `winget`, reuses existing tools, refreshes PATH for the current process, and starts
- the shared installer in Git Bash. Windows may request administrator approval for Git or Node.js installation.
- Package installation uses `--source winget`, not the Microsoft Store. Node and npm are discovered again after
- installation and passed to Git Bash in the same process; no separate prerequisite command or terminal restart
- is needed after a successful install. The wrapper skips Git Bash login profiles so an older shell PATH cannot
- hide these tools. Approve only the package installer's elevation prompt; the wrapper does not relaunch the full
- configuration installer as administrator. If approval is denied, setup stops and can be rerun safely.
- Native Windows uses Node/npm, not Bun, for npm package installation; Linux, macOS, and WSL keep Bun-first behavior.
- Amp is not installed through npm. Setup uses the [official Amp installers](https://ampcode.com/docs/cli):
- `install.ps1` on native Windows (including Git Bash), and `install.sh` on macOS, Linux, and WSL.
- Setup checks `amp version` and only reuses the binary in `AMP_HOME/bin` (default: `~/.amp/bin`);
- finding another command on PATH is not enough, including an npm shim under a custom prefix.
- Symlinks to the official binary are recognised and do not trigger an npm warning.
- An exported Bash `amp()` function produces a warning; setup verifies the official binary directly without removing or unsetting the function.
- `AMP_HOME` may be a Windows path or a Git Bash path; setup converts it for each side, so the
- official installer and the verification always use the same directory.
- Our wrapper promotes the official bin directory in the current Bash and PowerShell processes only.
- The official Windows `install.ps1` adds `AMP_HOME\bin` (default: `.amp\bin`) to the saved User PATH when absent;
- it does not reorder an existing entry. The official Unix `install.sh` can add `~/.local/bin` to a shell profile
- when needed. These official-installer changes persist across sessions; the wrapper's promotion does not.
- The PowerShell wrapper checks Amp only if it was accepted in setup; declining Amp leaves other tool installs unaffected.
- The one-line command and `-y` / `--yes` use these default categories:
- - **Default tools:** Amp, Pi, Codex, OpenCode, Claude Code, Grok, qmd, rtk, ctx, open-cursor, ai-switcher, open_code_review, and Plannotator.
- - **Shared skills:** bundled local skills, installed for the selected agents.
- - **Applicable MCP/plugin configuration:** bundled configuration for the selected agents. The three memory
- MCP choices (qmd, codebase-memory-mcp, agentmemory) remain available; `user-memory` stays opt-in.
- - **Optional standalone catalog:** remaining CLIs, formatters, and tools need selection. Interactive runs
- prompt for them; automation can use `--with-tools`.
- qmd, ctx, and Plannotator are also logged as integration dependencies of the core agent templates.
- ctx installation in `-y` mode does not import history, start its daemon, install upstream skills, or change
- persistent Windows PATH. Other MCP commands keep their existing external prerequisites. No unrelated agent's
- plugin or skill directory is configured in yes mode.
- From a reviewed checkout, select extra tools without enabling integrations:
- ```bash
- ./cli.sh --yes --without-integrations --with-tools=fx,cursor --dry-run
- ./cli.sh --yes --without-integrations --with-tools=fx,cursor
- # Default configuration, plugins, shared skills and MCPs (can replace existing config):
- ./cli.sh --yes --backup
- ```
- Windows equivalents are `-WithoutIntegrations -WithTools 'fx,cursor'` and `-Yes -Backup` on a saved
- `install.ps1`. Tool names are comma-separated; `./cli.sh --help` lists the catalog. `--without-integrations`
- (`-WithoutIntegrations`) installs standalone CLIs only and leaves existing configuration unchanged.
- `--with-integrations` remains accepted but is now the default. Selecting an extra tool does not select
- another agent's configuration. Noninteractive/CI runs use the same default categories as `--yes`.
- The installer can replace existing configuration. To inspect the script, preview changes, and request a backup,
- use the saved-script path instead:
- ```powershell
- Invoke-RestMethod https://ai-tools.itman.fyi/install.ps1 -OutFile install.ps1
- Get-Content .\install.ps1
- powershell -NoProfile -ExecutionPolicy Bypass -File .\install.ps1 -DryRun
- powershell -NoProfile -ExecutionPolicy Bypass -File .\install.ps1 -Backup
- ```
- Execution-policy bypass applies only to that process. `-DryRun` does not install prerequisites; install them first
- if the preview reports they are missing. The one-line command is non-interactive and automatically uses `--yes`.
- If setup fails, resolve the reported error and rerun the same command. If a newly installed prerequisite still
- cannot be found, close all terminal windows and reopen PowerShell. If `winget` is missing, install or update
- [App Installer](https://aka.ms/getwinget), or install [Git for Windows](https://git-scm.com/download/win),
- [`jq`](https://jqlang.org/download/), and [Node.js LTS with npm](https://nodejs.org/) manually. In Git setup,
- select **Git from the command line and also from 3rd-party software**. Do not bypass package lifecycle errors
- with `--ignore-scripts`: native binaries can remain uninstalled.
- #### Windows recovery: Amp command priority
- If `amp` reports an incompatible npm build, or PowerShell blocks `AppData\Roaming\npm\amp.ps1`,
- check command selection before changing anything. The wrapper verifies the official binary, puts its directory
- first in the current PowerShell process PATH, and checks command selection again. A shadowing alias, function,
- or a PATH entry that a new terminal would pick first is reported as a warning and does not fail the rest of
- the setup; only a missing or broken official binary fails the run.
- ```powershell
- Get-Command amp -All
- $ampHome = if ($env:AMP_HOME) { $env:AMP_HOME } else { Join-Path $env:USERPROFILE '.amp' }
- $ampBin = Join-Path $ampHome 'bin'
- & (Join-Path $ampBin 'amp.exe') version
- # Current session only: prefer the official binary, without removing npm or other tools.
- $env:Path = "$ampBin;$env:Path"
- Get-Command amp -All
- amp version
- ```
- For future sessions, open Windows **Environment Variables** and place the official Amp bin directory before
- `AppData\Roaming\npm` in PATH, then close and reopen PowerShell. Do not replace the full PATH or remove npm's
- directory: other tools can need it. Review any `amp` alias or function separately; PATH does not override those.
- If the official binary is missing, install it with
- `Invoke-RestMethod https://ampcode.com/install.ps1 | Invoke-Expression`, then repeat the checks above.
- Do not reinstall `@ampcode/cli` through npm or lower execution policy to run its stale shim. Setup does not
- uninstall existing copies, delete shims, or change execution policy. A direct binary version failure needs
- investigation; changing PATH alone cannot repair an incompatible binary.
- In Bash or Git Bash, run `type amp` in your own shell to check for a function. Unexported functions from
- shell profiles are not visible to the child Bash process running setup.
- Claude is skipped only when `claude --version` succeeds with nonempty output. A broken shim (including a
- missing native binary) is repaired even with `--yes`, then checked again. npm installs for Claude and OpenCode
- explicitly include optional platform packages and enable lifecycle scripts for that command only; Claude
- repair also uses `--force`. When npm supports script approval, Claude installation adds
- `--allow-scripts=@anthropic-ai/claude-code` to permit only that package's lifecycle scripts for that invocation.
- Older npm versions without this setting omit the flag. These options do not change user/global npm settings
- or approve scripts for other packages. Installation still fails if the final `claude --version` check fails.
- If OpenCode postinstall reports `ECONNRESET`, its platform download failed; the log alone does not identify
- the network cause. Check registry connectivity and your network/proxy policy, then retry
- `npm install -g @opencode/cli --include=optional --ignore-scripts=false`, verify `opencode --version`, and rerun
- setup. Optional catalog tools, including OpenCode 2, AI Launcher (`ai-switcher`), and Pi, warn and continue
- after installation or verification fails. Setup lists failed/skipped optional components at the end and
- skips their configurations for that run. Rerun setup to retry them. Claude, Amp, Codex, prerequisite checks,
- and required integration dependencies (including qmd, ctx, and Plannotator) still fail setup with a nonzero
- exit code. Optional failure does not mean that tool was installed successfully.
- AI Launcher reports success only after its installer succeeds and `ai --version` returns nonempty output
- successfully. On native Windows, setup downloads the official release directly instead of executing the
- upstream installer, which has no download retries and writes directly to the installed binary. The new
- release is staged beside the destination, checked against the release's SHA-256 checksum, and run with
- `--version` before it replaces `ai.exe`. Failed downloads, checksum checks, or staged health checks preserve
- the existing binary. A missing Windows architecture asset is reported, not substituted with another build.
- Shared installer downloads make at most three GET attempts for curl connection/partial-transfer/timeout/
- empty-response/receive errors (7, 18, 28, 52, 56), with 1-second then 2-second waits. Curl 35 retries only
- when that attempt's stderr matches `connection (was )?reset`, ignoring case. Generic TLS handshake errors,
- HTTP errors, and TLS certificate failures do not retry. Earlier attempts and stdout cannot enable a retry.
- Each attempt has a 15-second connection limit and 120-second transfer limit. Persistent TLS resets stop
- after three attempts; retries do not identify the cause or repair certificate, protocol, or proxy problems.
- TLS verification remains enabled on every attempt.
- Partial files are restarted, not appended; checksum verification still applies. Downloaded scripts
- and npm installs are never automatically replayed. This can recover a transient interruption, not repair
- a persistent network problem. Unix/WSL AI Launcher installation still uses the upstream installer.
- #### Windows recovery: Pi and persistent download resets
- npm already retries eligible registry reads (default `fetch-retries=2`, delays of 10 to 60 seconds, and a
- 5-minute per-request timeout). Local settings can differ. Setup does not add an outer Pi install retry or
- change user/global npm settings. Check the configured registry and effective retry count first:
- ```powershell copy Copy Registry Checks
- node --version
- npm --version
- npm config get registry
- npm config get fetch-retries
- npm ping
- ```
- `npm ping` tests registry metadata access only, not every package tarball or GitHub release download.
- Pi's `EPERM` cleanup warnings do not establish why Windows refused a removal. Save the npm debug log,
- close any Pi process you started, and use Resource Monitor or Process Explorer to check the exact failing
- path for an open handle. Check that directory's permissions if no handle is found. Do not stop all Node
- processes, run blanket deletion/cache cleanup, disable TLS checks, or use administrator mode as a workaround.
- After network access and any confirmed file-access problem are resolved, retry once from PowerShell:
- ```powershell copy Copy Pi Recovery
- npm install -g @earendil-works/pi-coding-agent --loglevel=http --timing
- pi --version
- ```
- Run the health check even if npm reports success. If failures persist, share the **redacted npm debug log**
- with failed URL host/path, HTTP status or socket error, attempt counts, timestamps, and Node/npm versions.
- For AI Launcher, include Git Bash's `curl --version` and a redacted verbose trace of the failing release
- asset GET, including redirects and response headers. Say whether a proxy/VPN is in use and whether another
- approved network reproduces it. Remove tokens, cookies, proxy credentials, and signed URL query strings.
- For `EPERM`, include the exact affected path, the confirmed handle/permission findings, and whether the error
- also occurs during the isolated Pi retry. These are needed to separate local file access from network resets.
- Optional qmd requires Node.js >=22 on native Windows. Its installer prioritizes the real `node.exe` directory
- and npm's global prefix in the same Git Bash session, ahead of stale Bun launchers or extensionless Node copies
- in `~/.local/bin`. Those old files are not deleted. In npm 11.19.1, unreviewed `allowScripts` entries warn but
- still run unless strict policy is enabled. The installer does not change npm script policy. Review actual
- build errors and approve only required packages if your policy requires it; do not enable all scripts globally.
- On Windows ARM64, qmd keyword indexing/search works, but sqlite-vec currently warns that vector search is unsupported.
- Optional Plannotator installs only the official v0.29.0 Windows release binary (x64 or ARM64), with a pinned
- SHA-256 hash. It uses `%LOCALAPPDATA%\plannotator` and updates only the current Git Bash PATH. No remote
- PowerShell script, policy bypass, persistent PATH change, sidecar, skill, or agent-settings edit is used.
- The direct method avoids an upstream PowerShell `$Minimal`/`$minimal` variable collision. Failure output gives
- the release URL, expected hash, and destination for manual recovery. In a separate terminal, add that directory
- and npm's global prefix to your user PATH, or use full executable paths. Unix/WSL installation paths are unchanged.
- #### Plannotator installation and Inbox CLI
- On macOS, Linux, and WSL, install Plannotator with the official installer:
- ```bash
- curl -fsSL https://plannotator.ai/install.sh | bash
- ```
- The default my-ai-tools installation runs this same installer on Unix-like systems. On native Windows,
- it uses the pinned official v0.29.0 binary fallback documented above instead of executing a remote PowerShell script.
- After installation, use the `plannotator inbox` command to open and manage the local Inbox:
- ```bash
- # Start the Inbox and open it in your browser
- plannotator inbox
- # Open the running Inbox and print its URL without blocking
- plannotator inbox --open
- # Start it in the background and print the URL without opening a browser
- plannotator inbox --background
- # Check whether it is running, including its URL and data directory
- plannotator inbox status
- # Run the stdio MCP server for an agent that has no native Inbox integration
- plannotator inbox mcp
- ```
- The installer configures `plannotator inbox mcp` for supported MCP clients. For agents with a native
- Inbox integration, use the agent's `plannotator_inbox` tool when available. The Inbox tool is enabled for
- new sessions after the Inbox has been started once; restart the agent to load it in an existing session.
- Use `plannotator inbox stop` only when you want to stop the shared Inbox, because other agent sessions use
- the same process. Run `plannotator inbox --help` for the complete CLI reference.
- If the wrapper says all prerequisites are met but Bash then reports missing Node/npm, check that the downloaded
- `install.ps1` includes `Find-Node` and the `OpenJS.NodeJS.LTS` installation step. A stale web deployment can serve
- an older wrapper while cloning the latest Bash installer. Maintainers must check the **Dokku Deploy** workflow
- for `ai-tools.itman.fyi`; a successful **Deploy GitHub Pages** run does not update that domain. Until the domain
- is updated, use a reviewed repository checkout and run:
- ```powershell
- powershell -NoProfile -ExecutionPolicy Bypass -File .\install.ps1 -Yes
- ```
- ### Repository checkout
- ```bash
- git clone https://github.com/jellydn/my-ai-tools.git
- cd my-ai-tools
- ./cli.sh --dry-run
- ./cli.sh --backup
- ```
- On Windows PowerShell, use the native wrapper from the checkout:
- ```powershell
- git clone https://github.com/jellydn/my-ai-tools.git
- Set-Location my-ai-tools
- .\install.ps1 -DryRun
- .\install.ps1 -Backup
- ```
- ## ⚙️ Installer options
- | Bash option | PowerShell option | Purpose |
- | --- | --- | --- |
- | `--dry-run` | `-DryRun` | Show planned changes without applying them. |
- | `--backup` | `-Backup` | Back up existing files before installation. |
- | `--no-backup` | `-NoBackup` | Skip the interactive backup prompt. |
- | `--yes` / `-y` | `-Yes` | Install the default tool set, shared skills, applicable MCP/plugin config and declared dependencies. |
- | `--with-tools=fx,cursor` | `-WithTools 'fx,cursor'` | Add optional standalone catalog CLIs. |
- | `--with-integrations` | `-WithIntegrations` | Install bundled config, plugins, skills and MCP dependencies (default). |
- | `--without-integrations` | `-WithoutIntegrations` | Install standalone CLIs only; leave configuration unchanged. |
- | `--rollback` | `-Rollback` | Restore the most recent backup. |
- | `--verbose` / `-v` | `-Verbose` | Show detailed installer output. |
- | `--migrate-gemini` | — | Migrate Gemini CLI configuration to Antigravity CLI. |
- Non-interactive Bash and PowerShell pipelines automatically add `--yes`. This mode uses the same default
- categories above; it is not a configuration-free install. Review
- [`cli.sh`](cli.sh) before using it in automation.
- ## 🤖 Supported tools
- The repository currently contains configuration or integration support for:
- | Category | Tools |
- | --- | --- |
- | Primary assistants | Claude Code, OpenCode, Amp, Codex, Cursor, Pi, Oh My Pi, Antigravity, Kilo, Kimi Code, Muse Code |
- | Additional CLIs | CommandCode, GitHub Copilot CLI, Gemini CLI, Grok CLI, MiMo-Code, Qoder CLI, DeepSeek Harness, Kiro CLI, Devin CLI, Factory Droid, Cline, Reasonix |
- | Workflow and desktop tools | Conductor, Delta, Codiff, OpenMausBot, Hunk, ctx, herdr, Orca, AI Launcher, CCS, fx, Open Code Review, ghui |
- Some installers are platform-specific, and optional tools are skipped when they are not detected. Gemini CLI is
- deprecated for Google One and unpaid tiers; use the `--migrate-gemini` option to move its configuration to
- Antigravity CLI.
- See [`configs/`](configs/) for the source configuration of each tool and [`skills/`](skills/) for shared skills.
- For an opt-in VPS terminal accessed from a Mac over Tailscale, see the
- [Pi Durable setup](configs/pi/durable/README.md). It uses a pinned experimental
- TUI, private persistent storage, and a user service; the general installer does not enable it.
- ## 🔌 Shared configuration
- The installer manages these common resources where the target tool supports them:
- - Agent guidance and software-development practices
- - Reusable skills and commands
- - Lifecycle and safety hooks
- - Tool-specific settings, themes, and provider configuration
- - MCP servers from [`configs/mcp-registry.json`](configs/mcp-registry.json)
- The MCP registry includes integrations such as Context7, sequential thinking, qmd, codebase memory, agent memory,
- fff, React Grab, logpilot, sem, and ctx. Installation depends on each server's runtime and credentials.
- For explicit cross-project user preferences, [user-memory MCP](packages/user-memory-mcp/README.md) provides
- five preference tools backed by local files. It is **optional**: the installer does not install or configure it.
- The existing qmd, codebase-memory-mcp, and agentmemory integrations remain unchanged. Follow the package guide
- to build, link, and register user-memory only if you need a separate explicit-preference store.
- See [the memory guide](MEMORY.md) for the distinction between preferences, project knowledge, and session handoffs.
- ctx's initial history indexing is optional. If provider paths cannot be inspected safely, the installer retains
- the verified binary and continues with a warning. Retry with `ctx setup`; see [ctx troubleshooting](TOOL_REFERENCE.md#-ctx-optional)
- for exact-path imports without bypassing its safety checks.
- Do not commit secrets. Keep API keys in environment variables or the target tool's credential store. Review
- `.env.example` for server-side environment variable names used by this repository.
- ## 🔄 Export local changes
- `generate.sh` copies supported configuration from your home directory back into the repository. Preview the
- operation first:
- ```bash
- ./generate.sh --dry-run
- ./generate.sh
- git diff
- ```
- Review the diff before committing. Generated configuration can contain machine-specific values or credentials that
- must not enter version control.
- ## 🧭 Common workflows
- ### Restore a backup
- ```bash
- ./cli.sh --rollback
- ```
- ```powershell
- .\install.ps1 -Rollback
- ```
- Backups are stored in `~/ai-tools-backup-<timestamp>`, and the installer keeps the five most recent backups.
- ### Migrate Gemini CLI to Antigravity CLI
- ```bash
- ./cli.sh --migrate-gemini
- ```
- ### Validate a contribution
- ```bash
- bash -n cli.sh generate.sh install.sh lib/*.sh scripts/*.sh
- ./cli.sh --dry-run
- ./scripts/sync-token-efficiency.sh --check
- bats tests/
- biome check .
- ```
- See [`TESTING.md`](TESTING.md) for focused test commands and [`CONTRIBUTING.md`](CONTRIBUTING.md) for repository
- conventions.
- ### Update shared agent guidelines
- Edit [`configs/token-efficiency.md`](configs/token-efficiency.md) or
- [`configs/experiment-workspaces.md`](configs/experiment-workspaces.md), then run:
- ```bash
- ./scripts/sync-token-efficiency.sh
- ./scripts/sync-token-efficiency.sh --check
- ```
- The script syncs both sections across the managed profiles. Experiment Workspaces also covers the Claude Code
- profile and the root `AGENTS.md` and `GEMINI.md`. Do not edit these generated sections in individual profiles;
- the CI check rejects drift from the canonical files. The workspace guideline uses `try` when available, but
- the installer does not install it. It requires shell integration; fresh experiments use an interactive selector,
- with fallbacks for agent shells without a terminal. `generate.sh` restores the canonical sections after export,
- so an older home-directory profile cannot remove them.
- ## 🎨 GitHub Coding Taste Generator
- `code-taste` analyzes public GitHub repositories and generates an evidence-backed
- coding preference profile. This command requires Bun and an OpenAI-compatible API
- key. Tree-sitter extracts TypeScript/TSX declarations; Markdown chunks retain headings
- and fenced code. See [setup and model configuration](docs/code-taste-openrouter.md).
- ```bash
- bun install
- bun run code-taste analyze jellydn/my-ai-tools
- bun run code-taste analyze jellydn --repos 3 --language TypeScript
- bun run code-taste export --format markdown
- ```
- Analysis state is stored in ignored `.code-taste/`. `CODING_TASTE.md` is intentionally
- not ignored so you can review and commit the resulting guidance. Markdown omits evidence;
- review the evidence in `.code-taste/profile.json` or the JSON export before treating
- inferred preferences as project rules.
- ## 📚 Documentation
- HTML pages in [`docs/`](docs/index.html) are generated from the Markdown sources. Regenerate them with `bun scripts/render-docs.ts`.
- - [Documentation website](https://ai-tools.itman.fyi)
- - [Detailed tool and skill reference](TOOL_REFERENCE.md)
- - [Fusion orchestration](docs/fusion-orchestration.md)
- - [Claude Code agent teams](docs/claude-code-teams.md)
- - [30-day applied AI learning sprint](docs/30-day-applied-ai-learnings.md)
- - [qmd knowledge management](docs/qmd-knowledge-management.md)
- - [My AI Bot](docs/my-ai-bot.md)
- - [Public repository knowledge base](docs/rag-architecture.md)
- - [Retrieval evaluation](docs/rag-retrieval-quality.md)
- - [Applied AI and GenAI cheat sheet](docs/ai-applied-genai-cheat-sheet.md)
- - [Testing guide](TESTING.md)
- ## 🤝 Contributing
- Contributions, issues, and feature requests are welcome. Read [`CONTRIBUTING.md`](CONTRIBUTING.md), run the relevant
- checks, and open an issue before a large behavior or configuration change.
- ## 📜 License
- This project is available under the [MIT License](LICENSE).
- ## 👤 Author
- **Dung Huynh**
- - Website: [productsway.com](https://productsway.com/)
- - YouTube: [IT Man Channel](https://www.youtube.com/@it-man)
- - X: [@jellydn](https://twitter.com/jellydn)
- - GitHub: [@jellydn](https://github.com/jellydn)
- ## ⭐ Show your support
- Give this project a ⭐️ if it helps you.
- [](https://ko-fi.com/dunghd)
- [](https://paypal.me/dunghd)
- [](https://www.buymeacoffee.com/dunghd)
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.