🤖 A collection of AI agent skills that automate recurring engineering workflows that can be installed across multiple AI coding assistants.
This repository also configures its own agents. See what ai-assist-skills tells them →
Skill Claude Code
Run the encrypted, password-protected repository sync workflow for this project. The real instructions are stored encrypted at rest and are only revealed in-session after you supply the correct password. Invoke explicitly with /sync-repo.
Skill Claude CodeCodex
Validate and fix the CHANGELOG.md version number before opening a PR, commiting, or pushing changes, and keep package.json's version aligned with it. Reads main branch to determine the current latest version, classifies changes on the current branch, and proposes the correct next semver. Use this skill when the user…
Skill Claude Code
Reverse-engineer a website's visual design system from a URL and produce a fully spec-compliant DESIGN.md file (https://github.com/google-labs-code/design.md). The output includes both machine-readable YAML design tokens (colors, typography, spacing, rounded corners, components) and human-readable markdown rationale…
Skill Claude Code
Deep research and analysis workflow for codebases, technologies, domains, ideas, or data. Produces structured documentation with analytical frameworks, confidence-graded findings, and cited sources. Use when evaluating technologies, investigating domains, assessing feasibility, or analyzing codebases in depth.
Skill Claude Code
Guide the user through containerizing and serving a simple website or documentation folder with Docker — inspects the project to detect what to serve (ready-to-serve static HTML, a buildable site that emits static output, or a raw markdown/docs folder that needs rendering), generates a Dockerfile, .dockerignore…
Skill Claude Code
Stage and commit changes using the team's standard commit message format. Only invoke when the user explicitly types /ai-assist-git-commit. Never auto-trigger from general conversation about commits or git.
Skill Claude Code
Perform a standards-based code review on a GitHub Pull Request, then post the findings as inline review comments and mark the PR as 'Requested changes'. Reads all of the agents files that exist in the repository under review (AGENTS.md, .agents-docs/, CLAUDE.md on the PR's base branch) — the repo's full documented…
Skill Claude Code
Adaptive GitHub PR lifecycle skill — create PRs, write/update descriptions, investigate review comments (Copilot + human) with research and batch approval, and check merge readiness. Triggers on: create PR, open PR, describe PR, update description, PR body, check comments, copilot feedback, review comments, address…
Skill Claude CodeCodex
Publish a GitHub Release when CHANGELOG.md's top version is ahead of the latest published release. Only invoke when the user explicitly types /ai-assist-git-publish. Never auto-trigger from general conversation about releases, tags, or versions.
Skill Claude Code
Bulk-update outdated npm dependencies across one or more package.json files. Finds every package.json in the current working directory (recursively, skipping nodemodules), runs npm outdated, bumps each outdated dependency to its 'wanted' version prefixed with ^, then runs npm install. Use whenever the user wants to…
Skill Claude Code
17-dimension observability audit with tier activation, health scoring, and cost analysis. Covers logging, metrics, tracing, alerting, SLOs, profiling, security observability, and developer experience. Use when assessing observability posture, identifying telemetry gaps, or optimizing observability costs.
Skill Claude Code
Generate a plain-language project overview, comprehensive engineer status update, and surgical documentation enhancement. Reads project docs, specs, dependencies, and git history. Use when onboarding, returning from time off, refreshing stale docs, or preparing project overviews.
Skill Claude Code
Build self-contained, double-click-to-open HTML prototypes so the user can vet an interface before it gets built. One file holds several structurally different variants of a page, app screen, component, flow, or terminal/TUI layout (rendered in-browser), plus a draggable Design Deck for flipping between variants…
Skill Claude Code
16-dimension security posture assessment with adaptive activation, health scoring, and remediation plan. Covers application security, infrastructure, auth, crypto, privacy, supply chain, and more. Use when assessing security posture, auditing code for vulnerabilities, reviewing compliance, or preparing for security…
Skill Claude Code
22-dimension, 5-tier technical debt audit covering code quality, architecture, infrastructure, quality processes, and operational readiness. Produces severity-ranked findings with weighted health score. Use when assessing codebase health, prioritizing tech debt remediation, or auditing code quality across all layers.
Skill Claude Code
16-dimension test suite audit with depth control (quick/standard/deep), gap matrix, and health scoring. Covers coverage, quality, mocking, data management, CI/CD, performance, mutation testing, and modern patterns. Use when evaluating test suite quality, identifying testing gaps, or assessing test infrastructure…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: