ai-agent-skills

Generate git commit messages, PR titles/descriptions, and changelog entries. Analyzes staged changes, enforces Conventional Commits, scans for sensitive content, links tickets (GitHub Issues / Jira), and updates CHANGELOG.md. Triggers on: "commit", "create a PR", "push", "changelog", "release", or when the user is ready to commit or open a pull request.

Provides the audit checklists, severity criteria (blocking/warning/suggestion), and artifact patterns needed to properly review Agent OS profiles and standards. Always invoke this skill before auditing - without it you can only give generic feedback, not structured severity-tagged findings. Invoke when the user pastes a standard and asks if it is good or what is wrong with it; when the user asks to review, audit, validate, or critique an agent-os profile or standard; or when the user mentions "agent-os profile", "agent-os standard", or "my agent-os setup" in a review or validation context.

Scaffolds production-ready directory structures for agentic AI projects using Agent-OS v3 (Builder Methods). Use when the user asks to set up, scaffold, initialize, or restructure a project for agentic development — including mono-repos, single repos, multi-language repos, full-stack, backend, frontend, or middleware projects. Triggers on "scaffold directory", "project structure", "agentic scaffold", "project layout", "initialize AI project", "directory structure", "agent-os setup", "mono-repo layout", "IaC structure".

Converts transcripts, video summaries, meeting notes, brainstorming sessions, strategy documents, and rough notes into polished Obsidian-flavored Markdown. Activates when creating or editing notes in an Obsidian vault, generating front matter, applying callout blocks, structuring knowledge base articles, or producing developer-facing guides. Also triggers on mentions of Obsidian, front matter, callout blocks, vault organisation, or requests for GitHub-compatible Markdown documents.

Exports a single Obsidian vault note and all its linked images into a portable zip or tar.gz archive, preserving vault-root-relative paths so the archive unpacks correctly anywhere. Use only when the user explicitly invokes /export-vault-note.

Create new agent skills from scratch, modify and improve existing skills, and measure skill performance through evaluation and benchmarking. Use when users want to create a skill, write a skill, build a new skill, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance, or optimize a skill's description for better triggering accuracy. Also triggers when users say "turn this into a skill", "make a skill for X", "skill for doing Y", or ask about skill structure, skill format, or SKILL.md files.

Ships completed work in the ai-agent-skills repository. Two phases depending on context: WRAP UP (on a feature branch with committed work — updates CHANGELOG, README, marketplace.json, commits, pushes, creates a PR) and CUT RELEASE (on main after a merge — determines semver bump, updates CHANGELOG version section, tags, pushes, creates a GitHub draft release). Use when the user says "ship this", "I'm done", "create a PR", "cut a release", "tag a release", "wrap this up", or "release it". Always checks GitHub auth first. Load the `conventions` skill for commit and PR formatting rules.

Defines the commit message, branch naming, pull request, and release note conventions for the ai-agent-skills repository. Make sure to load this skill whenever writing a commit message, naming a branch, drafting a PR title or body, or writing CHANGELOG entries in this repo. Use when the user asks "how should I format this commit", "what's the branch naming convention", "how do I write the PR", "what commit type should I use", or before any git commit, PR creation, release note, or CHANGELOG task in this project.

Begins a new piece of work in the ai-agent-skills repository. Two modes: EXISTING ISSUE (user provides a GitHub issue number or URL — fetches it, cuts the correct branch) and NEW ISSUE (user describes what needs doing — classifies as feature or bug, drafts a structured requirement using the repo's issue template, confirms with the user, creates the GitHub issue, then cuts the branch). Always checks GitHub auth first and confirms user identity. Use when the user says "start work on #14", "begin issue", "start a new feature", "I need to build X", "create an issue for Y", or passes a GitHub issue URL. Load the `conventions` skill for branch naming rules.

Generate polished, well-structured README.md files for software projects. Use this skill whenever the user wants to write, create, draft, generate, update, improve, or rewrite a README — including phrasings like "write a readme", "document this project", "make a readme for my repo", "the readme is terrible, fix it", or "I need docs for this package". Also triggers when a user shares a repo or codebase and asks for documentation, a project description, a GitHub landing page, or a "getting started" doc. Do NOT use for general markdown writing unrelated to project READMEs (e.g. blog posts, changelogs, design docs).

Make sure to use this skill whenever the user types /handoff (with or without a filename argument), says "handoff", "save state", "context rot", "save session", "create a handoff", "I need a clean start", wants to snapshot progress before clearing context or switching sessions, is approaching the context limit (300–400k tokens), or wants to delegate the current session state to another agent. Also invoke for RESUME mode: when the user says "load handoff", "resume from [file]", "continue where we left off", "pick up where I left off", "load the handoff at [path]", references a .claude/handoffs/ file path, or says there is a handoff file from a prior session. Creates or loads a structured JSON snapshot capturing goals, decisions, completed steps, pending work, constraints, and modified files so work can continue cleanly in a new session.

Reviews REST API designs during the planning phase against security, resilience, design, and operational best practices. Use when vetting an API design, reviewing an OpenAPI spec, critiquing endpoint structure, or evaluating API contracts before implementation. Triggers on "review my API", "API design review", "REST review", or "vet this API". Activates naturally during plan mode when API endpoints, contracts, or service boundaries are being designed. Make sure to use this skill whenever an API design, endpoint list, or OpenAPI specification is presented for feedback.

Explores a codebase for architectural friction through the lens of Ousterhout's deep-module principle (small interface, large implementation). Seven-step interactive workflow: an Explore sub-agent navigates the codebase organically — the friction it experiences IS the signal. Surfaces candidate clusters with coupling reasons, call patterns, shared types, dependency categories, and existing tests that a boundary test would replace. User picks what to explore, frames the problem, then 3–4 parallel sub-agents design competing deep-module interfaces. Chosen design becomes a structured RFC action file readable by GitHub MCP or ROVO (Jira) MCP. Use when the user says "arch review", "find shallow modules", "module depth", "deep module", "Ousterhout", "testability audit", "surface coupling", "design interfaces", "RFC issues", or "architectural friction".

Structured design critique and plan stress-testing. Acts as a relentless interviewer drawing on pre-mortem, red teaming, and ATAM techniques to help someone think through a design or plan exhaustively. Use when the user says "grill me", "critique this", "stress-test this", "pre-mortem", "red team this", or asks to be challenged on a technical architecture, product plan, feature design, or any decision rather than validated.