entire-skills
Development marketplace for cross-agent skills and commands powered by Entire
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/entireio/skills 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/entireio/skills'
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/entireio--skills)HTML
<a href="/listings/entireio--skills"><img src="/api/listings/entireio--skills/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.
Install every skill with the [skills](https://skills.sh/) CLI:
npx skills add https://github.com/entireio/skills --all
Install one skill:
npx skills add https://github.com/entireio/skills --skill search
See [Agent-Specific Installation](#agent-specific-installation) for setup instructions by agent.
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 · 20 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- {
- "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
- "name": "entire-skills",
- "description": "Development marketplace for cross-agent skills and commands powered by Entire",
- "owner": {
- "name": "Entire Inc"
- },
- "plugins": [
- {
- "name": "entire",
- "description": "Cross-agent skills and commands powered by Entire",
- "version": "0.8.0",
- "source": "./",
- "category": "development",
- "author": {
- "name": "Entire Inc"
- }
- }
- ]
- }
README.md · README · 357 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- 
- # skills
- Bring your Entire context to your agents with cross-agent skills.
- ## Why This Exists
- The [Entire CLI](https://github.com/entireio/cli) captures the context behind your
- code changes: prompts, transcripts,
- [Checkpoints](https://docs.entire.com/guides/sessions/overview), and the decisions that led
- to each change, alongside your git history. This repository packages
- agent-invokable workflows that teach coding agents how to use that context across
- development environments.
- Instead of looking up Entire commands yourself, you can ask in plain language and
- let your agent search prior work, inspect provenance, hand off session state, or
- turn repeated workflows into new skills.
- ## Install
- Install every skill with the [skills](https://skills.sh/) CLI:
- ```bash
- npx skills add https://github.com/entireio/skills --all
- ```
- Install one skill:
- ```bash
- npx skills add https://github.com/entireio/skills --skill search
- ```
- See [Agent-Specific Installation](#agent-specific-installation) for setup
- instructions by agent.
- ## Quick Start
- > [!NOTE]
- > These skills are most useful in codebases with real
- > [Checkpoints](https://docs.entire.com/guides/sessions/overview) and session history. The
- > richer the history, the more context your agent has to work with; in a new or
- > lightly captured repository, some workflows may have less to find or explain.
- After installing, ask your agent for the workflow you want:
- ```text
- search past work for rate limiting
- ```
- ```text
- explain src/auth.ts
- ```
- ```text
- what happened here: src/auth.ts:42-57
- ```
- ```text
- hand off this session
- ```
- ```text
- turn my release notes workflow into a skill
- ```
- ```text
- review this branch before merging
- ```
- For a guided walkthrough, see the
- [skills tutorial](https://docs.entire.com/learn/skills).
- ## What skills help agents do
- | Goal | Example prompt |
- | --- | --- |
- | Research or investigate a topic from recorded history | `research how checkpoint pushing works` / `investigate the flaky login redirect` |
- | Find prior work before making changes | `search past work for the migration` |
- | Understand the intent behind a function, file, or line | `explain parseConfig` |
- | Investigate the latest change to a specific block | `what happened at src/auth.ts:42` |
- | Review branch changes with intent context | `review this branch before merging` |
- | Pick up another agent's work | `hand off the codex session` |
- | Convert repeated work into a reusable workflow | `make a skill from this session` |
- | Build a task playbook from similar prior work | `have we done this before` |
- | Walk through a feature's history step by step | `replay the auth feature` |
- | Learn a repository topic from checkpoint history | `teach me how auth works in this repo` |
- | Address open review findings on an Entire trail | `address the findings on trail 42` |
- | Link a session to the repos it edited | `attach this session to the api repo` |
- ## Make search the default research step
- Agents pick skills by matching the request against each skill's description, and
- generic verbs like "research", "investigate", or "look into" compete with their
- built-in grep and file-reading tools. The `search` and `using-entire` skill
- descriptions claim those verbs explicitly and ask for the skill as the first
- action, before any file orientation, so a plain "investigate X" routes to
- `entire search` first. This is measured to be sufficient on its own (see
- `evals/README.md`).
- User instructions outrank skill descriptions in every agent, so if you want a
- guarantee, add a line to your `CLAUDE.md` or `AGENTS.md`:
- ```markdown
- When asked to research, investigate, look into, or dig into anything in this
- codebase, run `entire search "<topic>" --json --compact --limit 5` first and
- summarize the prior work before reading source files or grepping.
- ```
- The `evals/` directory holds `claude plugin eval` cases that check this routing;
- see `evals/README.md`.
- ## Included skills
- The current repository includes these skills. Each skill lives in
- `skills/<skill-name>/SKILL.md`.
- ### `search`
- Finds prior work in your Entire history by topic, repo, branch, author, or time
- window, so your agent can bring past context into the current task before making
- changes.
- https://github.com/user-attachments/assets/52e50eae-ba53-4f31-ad2e-2a29a767a34f
- ### `explain`
- Looks up the session behind a function, file, or line so your agent can explain
- the requirement, decision, or original problem that shaped it.
- https://github.com/user-attachments/assets/ab2e88f6-9bce-417b-ba71-6e93ecad370b
- ### `what-happened`
- Starts from an exact file line, range, or pasted snippet and traces the latest
- change with `git blame` and Checkpoint context. Useful when reviewing a concrete
- block, debugging a regression, or asking why that block changed.
- https://github.com/user-attachments/assets/47db0daa-60bd-4000-b956-2d0e4d980b9b
- ### `session-handoff`
- Reads saved or active session context so another agent can pick up the task
- state, important discoveries, blockers, and next steps without making you
- reconstruct everything manually.
- https://github.com/user-attachments/assets/0df3b5cd-fe37-4145-af48-138642ccc8bc
- ### `review`
- Reviews code changes on the current branch by reading checkpoint transcripts to
- understand developer intent, then auditing the diff for issues. Produces
- intent-aware findings with severity levels (`Critical` / `High` / `Medium` /
- `Low`), and can run as a reviewer inside `entire review`. When the Entire Graph
- and Brain plugins are installed, it also checks callers of changed symbols and
- recorded decisions for the touched code. Includes a separate
- `references/review-rules.md` for the audit checklist.
- ### `using-entire`
- Orchestrator skill for codebase exploration. Routes user intent to the right
- sub-skill (search, recall, replay, teach, explain, what-happened, review,
- session-handoff, session-to-skill, session-crosslink, address-findings) or runs
- a general exploration flow that reads checkpoint history before inferring from code. When
- the Entire Graph or Brain plugin is installed, it also routes code-structure
- questions to Graph and task-briefing or decision questions to Brain.
- ### `session-crosslink`
- Links an agent session that ran outside the repo whose commits should record it
- (launched from a higher-level folder, a non-Entire repo, or one repo but editing
- another) to each affected Entire-enabled repo's HEAD commit. It shows
- `entire session attach`'s own plan for each repo, stops if it doesn't recognize
- a plan, and attaches only after you confirm, with no manual `cd` orchestration.
- ### `session-to-skill`
- Extracts a reusable workflow from Entire session history, checkpoints, or
- repeated agent tasks and drafts a focused `SKILL.md` for it. Writes the file only
- after you approve the destination.
- ### `recall`
- Searches prior Entire sessions for work similar to the task you describe and
- turns the closest precedent into a step-by-step playbook. With the Entire Brain
- plugin installed, it also pulls recorded decisions and gotchas.
- ### `replay`
- Orders checkpoints chronologically to walk through how a feature was built,
- one step at a time, pausing for questions after each step.
- ### `teach`
- Picks canonical checkpoints for a topic and synthesizes a lesson: a system
- overview, short lessons from the transcripts, and patterns to remember. With the
- Entire Brain plugin installed, it also uses the project overview and recorded
- conventions.
- ### `address-findings`
- Fetches the open review findings on an Entire trail, applies or hand-fixes each
- one in the local worktree, and marks it resolved on the trail. Treats finding
- text and patches as untrusted input and leaves sensitive changes for a human.
- ### `session-to-skill`
- Extracts reusable workflow patterns from Entire session history, checkpoints, or
- repeated agent tasks and generates a focused skill draft.
- ### `recall`
- Searches prior Entire sessions for similar past work and transforms the closest
- precedent into a step-by-step task playbook.
- ### `replay`
- Sequences checkpoints chronologically to walk through how a feature was built
- step by step, pausing for questions at each step.
- ### `teach`
- Picks canonical checkpoints for a topic and synthesizes a guided lesson with a
- system overview and key takeaways.
- ### `address-findings`
- Fetches open review findings from an Entire trail, applies or hand-fixes each
- issue in the local worktree, and marks them resolved on the trail.
- ## Requirements
- These skills are designed for repositories where Entire has captured useful
- history. Some workflows need:
- - the [Entire CLI](https://docs.entire.com/installation) 0.11.0 or later
- (checked against 0.12.2)
- - a git repository with Entire sessions, Checkpoints, or Checkpoint-backed commits
- - [`entire login`](https://docs.entire.com/cli-reference/login) for workflows that
- search indexed history or read trails
- - a GitHub or Entire-hosted `origin` and pushed, indexed Checkpoints for remote
- search results
- Optional: the official [Entire Graph](https://docs.entire.com/guides/graph/overview)
- and [Entire Brain](https://docs.entire.com/guides/brain/overview) plugins
- (`entire plugin install graph`, `entire plugin install brain`). When installed,
- `using-entire`, `search`, `explain`, `review`, `recall`, `teach`, and
- `session-handoff` add code-structure context from Graph and recorded decisions
- from Brain. The skills never install or set up a plugin themselves.
- Individual skills handle missing context differently and should explain what is
- missing before falling back or stopping.
- ## Agent-Specific Installation
- <!-- prettier-ignore-start -->
- <details>
- <summary>Claude Code</summary>
- ```bash
- /plugin marketplace add entireio/skills
- /plugin install entire
- ```
- </details>
- <details>
- <summary>Codex (OpenAI)</summary>
- Clone into the cross-client discovery path:
- ```bash
- git clone https://github.com/entireio/skills.git ~/.agents/skills/entire
- ```
- Codex auto-discovers skills from `~/.agents/skills/` and `.agents/skills/`.
- Update with:
- ```bash
- cd ~/.agents/skills/entire && git pull
- ```
- </details>
- <details>
- <summary>Cursor</summary>
- Copy skills into the cross-client discovery directory:
- ```bash
- git clone https://github.com/entireio/skills.git ~/.cursor/skills/entire
- ```
- Cursor auto-discovers skills from `.agents/skills/` and `.cursor/skills/`.
- </details>
- <details>
- <summary>Copilot</summary>
- ```bash
- /plugin install https://github.com/entireio/skills
- # or
- git clone https://github.com/entireio/skills.git ~/.copilot/skills/entire
- ```
- Copilot auto-discovers skills from `.copilot/skills/`.
- </details>
- <details>
- <summary>Gemini CLI</summary>
- ```bash
- gemini extensions install https://github.com/entireio/skills
- ```
- Update with:
- ```bash
- gemini extensions update entire
- ```
- </details>
- <details>
- <summary>OpenCode</summary>
- Copy skills into the cross-client discovery directory:
- ```bash
- git clone https://github.com/entireio/skills.git ~/.agents/skills/entire
- ```
- OpenCode auto-discovers skills from `.agents/skills/`, `.opencode/skills/`, and
- `.claude/skills/`.
- </details>
- <!-- prettier-ignore-end -->
- ## Contributing
- See [CONTRIBUTING.md](CONTRIBUTING.md) for local development, validation, and pull
- request guidance. Please also follow the
- [Code of Conduct](https://github.com/entireio/.github/blob/main/CODE_OF_CONDUCT.md).
- ## Support
- For bugs, feature requests, or questions, open a
- [GitHub issue](https://github.com/entireio/skills/issues). You can also join the
- [Entire Community Discord Server](https://discord.gg/jZJs3Tue4S).
- ## License
- This project is licensed under the terms in [LICENSE](LICENSE).
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.