ciago-labs-skills
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/ciago-labs--skills)HTML
<a href="/listings/ciago-labs--skills"><img src="/api/listings/ciago-labs--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.
Replace `<skill>` with a skill name from the [catalog](#available-skills), for example `pg-query-surgeon` or `docker-forensics`. `linux-perf-doctor` is a standalone repository: follow its own README.
Hermes Agent
hermes skills inspect ciago-labs/skills/<skill> # preview only; the scan runs at install hermes skills install ciago-labs/skills/<skill>
Hermes scans community skills before installing them and blocks CAUTION and DANGEROUS verdicts. Do not override the scanner. Each skill documents its controls in its own `SECURITY.md` (`skills/<skill>/SECURITY.md`).
Cursor, Codex, Gemini CLI, OpenCode and other agents
npx skills add ciago-labs/skills --skill <skill>
This route does not run a local security scan. Review the skill's source and `SECURITY.md` before use.
Claude Code
/plugin marketplace add ciago-labs/skills
Manual installation
git clone https://github.com/ciago-labs/skills.git SKILL=<skill> cp -r "skills/skills/$SKILL" ~/.hermes/skills/ # Hermes # or: ~/.claude/skills/ (Claude Code), ~/.agents/skills/ (Codex and others)
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 · 16 lines
- {
- "name": "ciago-labs-skills",
- "owner": { "name": "Ciago Labs" },
- "plugins": [
- {
- "name": "ciago-labs-skills",
- "description": "Collection of open-source agent skills",
- "source": "./",
- "strict": false,
- "skills": [
- "./skills/pg-query-surgeon",
- "./skills/docker-forensics"
- ]
- }
- ]
- }
README.md · README · 99 lines
- # Ciago Labs — Agent Skills
- **Production-focused skills for AI coding agents.**
- Ciago Labs Skills is an open-source collection of modular, tested, and security-conscious engineering skills that help AI coding agents perform real-world development and infrastructure tasks more reliably.
- Each skill is independently organized within this monorepo, with its own instructions, deterministic scripts, tests, references, examples, and documentation.
- [Available Skills](#available-skills) · [Installation](#installation) · [Contributing](#contributing) · [Security](#security)
- ## Available Skills
- | Skill | Description | Status |
- |---|---|---|
- | [pg-query-surgeon](skills/pg-query-surgeon) | Reviews PostgreSQL migrations for lock hazards, analyzes SQL and EXPLAIN ANALYZE plans, recommends indexes, and designs zero-downtime schema changes. | Available |
- | [docker-forensics](skills/docker-forensics) | Read-only audit of Docker images, layer history, container security posture, bridge/DNS networking, and container crash loops (OOM, SIGSEGV, CrashLoopBackOff) for Go, Rust, Node.js, and Python workloads. | Available |
- | [linux-perf-doctor](https://github.com/AnujTiwari-Student/linux-perf-doctor) | Read-only Linux performance diagnostics using /proc, /sys, PSI, and cgroup telemetry. Maintained in its own repository. | Standalone |
- More engineering skills are in development and will be added to this collection.
- ## Installation
- Replace `<skill>` with a skill name from the [catalog](#available-skills), for example `pg-query-surgeon` or `docker-forensics`. `linux-perf-doctor` is a standalone repository: follow its own README.
- ### Hermes Agent
- ```bash
- hermes skills inspect ciago-labs/skills/<skill> # preview only; the scan runs at install
- hermes skills install ciago-labs/skills/<skill>
- ```
- Hermes scans community skills before installing them and blocks CAUTION and DANGEROUS verdicts. Do not override the scanner. Each skill documents its controls in its own `SECURITY.md` (`skills/<skill>/SECURITY.md`).
- ### Cursor, Codex, Gemini CLI, OpenCode and other agents
- ```bash
- npx skills add ciago-labs/skills --skill <skill>
- ```
- This route does not run a local security scan. Review the skill's source and `SECURITY.md` before use.
- ### Claude Code
- ```
- /plugin marketplace add ciago-labs/skills
- ```
- ### Manual installation
- ```bash
- git clone https://github.com/ciago-labs/skills.git
- SKILL=<skill>
- cp -r "skills/skills/$SKILL" ~/.hermes/skills/ # Hermes
- # or: ~/.claude/skills/ (Claude Code), ~/.agents/skills/ (Codex and others)
- ```
- ## Example prompts
- - *"Use pg-query-surgeon to review this migration for lock hazards before I deploy."*
- - *"Here is an EXPLAIN ANALYZE output. Why is this query slow, and what index would fix it?"*
- - *"Use docker-forensics to find out why this container keeps exiting with code 137."*
- ## Design Principles
- - **Modular:** each skill is self-contained and independently organized.
- - **Verifiable:** skills include tests and deterministic supporting scripts where applicable.
- - **Security-conscious:** scripts minimize permissions, avoid unnecessary network access, and protect sensitive information.
- - **Transparent:** limitations, assumptions, and operational risks are documented.
- - **Agent-compatible:** designed for tools that support the Agent Skills format.
- ## Repository Layout
- ```
- .
- ├── .github/workflows/validate.yml centralized CI for all skills
- ├── .claude-plugin/marketplace.json Claude Code marketplace manifest
- ├── plugins/ plugins (coming soon)
- ├── skills/
- │ ├── pg-query-surgeon/ SKILL.md, scripts, tests, references, docs
- │ └── docker-forensics/ SKILL.md, scripts, tests, references, docs
- ├── CONTRIBUTING.md
- ├── SECURITY.md
- ├── LICENSE
- └── README.md
- ```
- Centralized CI validates and tests every skill in this repository. Standalone projects stay independently maintained and are linked from the catalog.
- ## Contributing
- Contributions are welcome. Please read [CONTRIBUTING.md](CONTRIBUTING.md) before opening a pull request. All changes must pass the repository's required validation checks.
- ## Security
- Review a skill's source code and permissions before installing it. Report vulnerabilities privately as described in [SECURITY.md](SECURITY.md).
- ## License
- Distributed under the MIT License. See [LICENSE](LICENSE). Check individual skill directories for any additional licensing terms.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.