coding-agent skills

2,449 tagged coding-agent, measured the same way as everything else here.

Browse within: pi 114acp 90ai-coding-agent 83deepseek 76agentic 74tui 70ai-coding-assistant 59pi-coding-agent 59autonomous-coding 58claude-agent-skills 57agent-orchestration 56eletron 55codex-cli 52game-ai 52

claude-md-improver

169

mrclrchtr/supi

Skill Claude CodeCodex

Audit and improve existing CLAUDE.md files across a repository. Use for a deliberate, repo-wide quality review—not to record learnings from the current session.

79 3d ago A 39 tokens original MIT

claude-md-revision

170

mrclrchtr/supi

Skill Claude CodeCodex

Record durable, project-specific learnings from the current session in CLAUDE.md, .claude.local.md, or AGENTS.md—not general documentation, session summaries, or repo-wide audits.

79 3d ago A 45 tokens original MIT

code-review

171

genai-io/san

Skill Claude CodeCodex

Review changed code for correctness bugs — logic errors, nil/error handling, concurrency, resource leaks, edge cases, broken invariants. Reports findings first, ordered by severity, then fixes on request. Scoped to correctness, not quality or style cleanups. Use when the user says "code review", "review my changes"…

75 6d ago A 83 tokens original Apache-2.0

qa

172

genai-io/san

Skill Claude CodeCodex

Regression test a San feature by name. Looks for a feature doc in docs/reference/ or docs/packages/2-feature/, runs automated Go tests and interactive tmux tests, then produces a pass/fail report. Use this skill when the user says "qa", "regression test", "test feature X", "verify feature", or references a feature…

75 6d ago A 85 tokens original Apache-2.0

release

173

genai-io/san

Skill Claude CodeCodex

Create a new versioned release with changelog. Bumps version in code, updates CHANGELOG.md, commits, tags, and pushes using the repository release flow. GitHub Actions creates the release and uses only the current changelog section as release notes. Use when the user says "release", "cut a release", "bump version"…

75 6d ago A 75 tokens original Apache-2.0

lanegrid/agtrace

Skill Claude CodeCodex

Investigate AI agent provider tool schemas (Claude Code, Codex, Gemini) and design unified domain abstractions in agtrace architecture.

59 1mo ago A 33 tokens original Apache-2.0

git-workflow

175

lanegrid/agtrace

Skill Claude CodeCodex

Git workflow standards - branch management, commit conventions, and PR creation process. Use when planning work that involves git operations or PR submissions.

59 1mo ago A 31 tokens original Apache-2.0

code-trace-tree

176

saidake/code-trace-tree-jetbrains

Skill Claude CodeCodex

Read, edit, and refresh Code Trace Tree plugin data (VS Code and JetBrains). Use when the user asks to add/update/remove trace points (line, file, or directory), inspect or modify Code Trace Tree profiles, sync agent-written traces into the IDE, ask the IDE to reload plugin data, or select/navigate to trace points in…

59 4d ago C 228 tokens original MIT

agentic-code-review

177

DominikTobureto/awesome-grok-build

Skill Claude CodeCodex

Use when reviewing a diff, pull request, branch, or AI-generated code for correctness, security, regression, test, performance, and maintainability risks before merge.

58 +1 10d ago A 38 tokens original MIT

hooksmith

178

DominikTobureto/awesome-grok-build

Skill Claude CodeCodex

Use when designing or reviewing safe Grok Build hooks for linting, tests, formatting, notifications, command guards, lifecycle automation, or project hook trust decisions.

58 +1 10d ago A 35 tokens original MIT

repo-health-check

179

DominikTobureto/awesome-grok-build

Skill Claude CodeCodex

Use when auditing a repo before changes to find the smallest safe PR, quality risks, stale docs, missing tests, ignored-file gaps, or agent setup issues. Best first skill for unfamiliar codebases.

58 +1 10d ago A 44 tokens original MIT

do

180

raphaeltm/simple-agent-manager

Skill Claude CodeCodex

End-to-end autonomous task executor. Takes a task description and handles the full lifecycle: research, plan, implement, review with specialist skills, and merge via PR. Use when given a task to execute end-to-end.

55 3d ago A 46 tokens AGPL-3.0

prototype

181

raphaeltm/simple-agent-manager

Skill Claude CodeCodex

Build a UI prototype for design exploration. Creates a self-contained, unauthed page in the real web app with mock data, exposes it for preview, and runs visual audits. Use when exploring layouts, information architecture, or interaction patterns before committing to production implementation.

55 3d ago A 55 tokens AGPL-3.0

workflow

182

raphaeltm/simple-agent-manager

Skill Claude CodeCodex

Orchestrate multi-step workflows by decomposing and dispatching subtasks, then waiting through SAM durable parent wake delivery. Use when coordinating multiple agents or multi-phase work.

55 3d ago A 36 tokens AGPL-3.0

issue-review

183

copperheadhq/copperhead

Skill Claude CodeCodex

Triage a copperhead GitHub issue, attempt reproduction, and check it against the spec. Use when the user asks to review an issue, e.g. /issue-review 42 or /issue-review .

54 3d ago A 47 tokens original Apache-2.0

copperheadhq/copperhead

Skill Claude CodeCodex

Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.

54 3d ago A 55 tokens copy · 70% Apache-2.0

pr-review

185

copperheadhq/copperhead

Skill Claude CodeCodex

Review a copperhead pull request against the repo's invariants and spec workflow. Use when the user asks to review a PR, e.g. /pr-review 28 or /pr-review .

54 3d ago A 44 tokens original Apache-2.0

pnpm

186

moeru-ai/alint

Skill Claude CodeCodex

Node.js package manager with strict dependency resolution. Use when running pnpm specific commands, configuring workspaces, or managing dependencies with catalogs, patches, or overrides.

53 4d ago A 35 tokens copy · 100% MIT

simple-english

187

moeru-ai/alint

Skill Claude CodeCodex

Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop. Use for documentation, READMEs, runbooks, procedures, error messages, release notes, incident reports, and API guides. Also use when the user says "STE", "Simplified Technical…

53 4d ago A 149 tokens copy · 81% MIT

xsai

188

moeru-ai/alint

Skill Claude CodeCodex

Use this skill when the user is building with xsai or any @xsai/ package, or is evaluating xsAI for a small OpenAI-compatible workflow with text generation, streaming, tool calling, structured output, embeddings, image generation, speech synthesis, or transcription.

53 4d ago A 61 tokens copy · 100% MIT

package-release

189

dannote/dot-pi

Skill Claude CodeCodex

Prepare, publish, repair, or verify package releases and changelogs. Always use for package/version release, publish, ship, tag, changelog, release notes, registry publication, documentation publication, or GitHub Release work. Distinguish package releases from application deployments before acting.

51 3d ago A 60 tokens original MIT

session-reflect

190

dannote/dot-pi

Skill Claude CodeCodex

Analyze a user's pi coding-agent session history for recurring behavior, prompting habits, workflow loops, friction, and preferences. Use when the user asks to inspect or reflect on pi sessions, common behavior patterns, agent/user interaction style, prompting habits, or personal pi workflow quality.

51 3d ago A 58 tokens original MIT

twitter-thread-style

191

dannote/dot-pi

Skill Claude CodeCodex

Write or revise X/Twitter developer announcement threads in the user's preferred style. Use for technical launch threads, project announcements, release threads, and threads with code screenshots/snippets.

51 3d ago A 39 tokens original MIT

grok-build-supervisor

192

Vanyangyang/cursor-bridge

Skill Claude CodeCodex

Part of grok-build-supervisor

Initialize the persistent local proxy, then immediately ensure a visible Grok Build TUI for the current workspace when /grokexecute on activates, and continuously supervise that coding-agent session through a user-level Supervisor daemon as the user sends work, waits for completion, reconnects from another host task…

51 3d ago A 103 tokens original MIT

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: