By contextosai
Production-readiness audit for AI agent harnesses. Runs against your agent's real repo and traces, scores 44 runtime controls with file:line evidence, assigns a maturity band, and emits a prioritized fix queue. No artifact, no pass.
Write a clear, conventional git commit message from staged changes. Use when the user asks to commit, write a commit message, or describe what changed.
Audit an AI agent's harness for production readiness by reading its ACTUAL code, configs, and run traces — not a questionnaire. Scores 44 runtime controls (grouped into the eight ContextOS harness properties) Pass/Partial/ Fail with file:line evidence, assigns a maturity band, and emits a prioritized fix queue. Use when someone asks to audit / assess / production-readiness-check an AI agent, agent harness, LangGraph / OpenAI Agents SDK / ADK / CrewAI / custom agent, or asks "is my agent safe to ship / production-ready / governed".
Draft a pull request title and description from the commits and diff on the current branch. Use when the user asks to open a PR, write a PR description, or summarize a branch's changes for review.
Improve a project's README for clarity, structure, and completeness without changing its meaning. Use when the user asks to clean up, polish, or improve a README or project documentation.
Skills are folders of instructions, scripts, and resources that an agent loads dynamically to improve performance on specialized tasks. A skill teaches the agent how to complete a specific task in a repeatable way — writing a commit message in your team's style, drafting a PR description, polishing docs, and so on.
Each skill is self-contained in its own folder with a SKILL.md file holding
the instructions and metadata. Browse the skills directory for
working examples, or use the template as a starting point.
./skills — example skills you can use or learn from./spec — the Agent Skills specification./template — a minimal skill templateRegister this repository as a plugin marketplace:
/plugin marketplace add contextosai/skills
Then install a plugin. The production harness audit:
/plugin install harness-audit@contextosai-skills
Or the example skills (commit messages, PR descriptions, README polish):
/plugin install example-skills@contextosai-skills
Once installed, invoke a skill just by mentioning the task — for example,
"audit my agent harness for production readiness" triggers harness-audit, and
"write a commit message for my staged changes" triggers commit-message. You
can also run harness-audit explicitly as /harness-audit.
A skill is just a folder with a SKILL.md file containing YAML frontmatter and
Markdown instructions:
---
name: my-skill-name
description: A clear description of what this skill does and when to use it.
---
# My Skill Name
Instructions the agent will follow when this skill is active.
## Guidelines
- Guideline 1
- Guideline 2
The frontmatter requires two fields:
name — a unique identifier (lowercase, hyphens for spaces)description — what the skill does and when to use it; this is how the
agent decides the skill is relevant, so cover both the what and the whenSee spec/agent-skills-spec.md for the full
specification, and template/SKILL.md for a starting
point.
| Skill | Description |
|---|---|
harness-audit | Production-readiness audit for an AI agent harness: scores 44 runtime controls against your agent's real code with file:line evidence and emits a fix queue. |
commit-message | Write a conventional git commit message from staged changes. |
pr-description | Draft a PR title and description from a branch's commits and diff. |
readme-polish | Improve a README's clarity and structure without changing its meaning. |
Every SKILL.md and the marketplace manifest are checked in CI on each push and
pull request. Run the same check locally:
node scripts/validate-skills.mjs
Contributions are welcome — see CONTRIBUTING.md for the
skill format and the bar for inclusion, and please follow the
Code of Conduct.
Released under the MIT License.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub contextosai/skills --plugin example-skillsUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.