Menu
SkillsMP a collecté 30 skills depuis Marshall-Hallenbeck/dot_files. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 30 skills collectés sur 30.
Use when asked to work on, implement, or complete a GitHub issue — before writing any code, checks issue state, existing PRs, git history, and codebase to determine what work remains or if the issue is already resolved
Langue du texte source : anglais
Use when starting, checking, or finishing work on a GitHub issue in any repo where multiple agents may work in parallel — posts a session-info claim comment and manages the in-progress label so other agents skip claimed issues
Langue du texte source : anglais
Use when asked to create, open, publish, or submit a pull request from the current branch
Langue du texte source : anglais
Use when asked to create, open, file, or draft a GitHub issue
Langue du texte source : anglais
Commit session changes only, or all changes if no session edits.
Langue du texte source : anglais
Autonomous test-fix pipeline. Runs full suite, diagnoses each failure, fixes source code, and iterates until all tests pass. Asks the user when uncertain about intended behavior.
Langue du texte source : anglais
Group ALL working-tree changes into logical commits.
Langue du texte source : anglais
Set up or repair a persistent Claude Remote Control environment for a project using a systemd user service, including blocker checks, project symlink, linger, verification, and URL capture.
Langue du texte source : anglais
Guide for using the Sentry CLI to interact with Sentry from the command line. Use when the user asks about viewing issues, events, projects, organizations, making API calls, or authenticating with Sentry via CLI.
Langue du texte source : anglais
Holistic review pipeline: simplification, correctness, security, overcautious check, lint/fix, all tests, fix failures, audits, and final review. Fixes EVERYTHING — every severity and every warning — so nothing is left open.
Langue du texte source : anglais
Run full quality gate: linting, type checks, unit tests, and integration tests — all in parallel.
Langue du texte source : anglais
Review uncommitted changes for missing test coverage, then create the missing tests. Use after implementation and before commit.
Langue du texte source : anglais
Get straight to the point in every response. Use whenever responding to ANY user message — coding, debugging, explanations, planning, casual chat. Lead with the answer or next concrete action, number multi-step work, restate state across turns, suppress…
Langue du texte source : anglais
Write comprehensive unit tests for a module or function. Handles test runner detection, mock conventions, and iterates until all tests pass.
Langue du texte source : anglais
Summarize git changes for PRs or commits. Does not commit unless explicitly asked.
Langue du texte source : anglais
Run formatting, linting, and type checking. Auto-detects project languages (Python, JS/TS, Bash). Fixes auto-fixable issues and stages changes.
Langue du texte source : anglais
Use when reviewing changes before commit to catch patterns that silence failures, fail open, add unauthorized fallbacks, or hide errors behind graceful degradation.
Langue du texte source : anglais
Security audit of uncommitted changes. Scans for OWASP top 10, injection, exposed secrets, auth bypasses, and unsafe patterns.
Langue du texte source : anglais
End-to-end Claude Code setup optimization: update CLAUDE.md with session learnings, recommend new automations, audit config quality, clean stale memory, and check for new capabilities.
Langue du texte source : anglais
Spawn an agent team in tmux split panes for parallel exploration. Best for investigation, debugging, ambiguous tasks, and multi-angle review where you want to steer work in real-time.
Langue du texte source : anglais
Review uncommitted code changes for bugs, security issues, and correctness. Finds AND fixes all issues.
Langue du texte source : anglais
Run integration-level suites. Auto-detects runner (pytest markers, Jest, E2E).
Langue du texte source : anglais
Decompose a plan into parallel work tracks and execute with subagents. Reads PLAN.md, splits into non-overlapping tracks, spawns agents, and runs integration tests.
Langue du texte source : anglais
Dispatcher skill for unit, integration, or full quality-gate workflows. Auto-detects language and scope.
Langue du texte source : anglais
Run unit-test suites. Auto-detects runner (pytest, Jest, Vitest, cargo, go test).
Langue du texte source : anglais
Run Codex and Claude code reviews iteratively until both find no issues. Use after making changes and before committing.
Langue du texte source : anglais
Look up documentation for any library using Context7. Resolves library IDs and queries versioned docs.
Langue du texte source : anglais
Normalize agents/skills/hooks so responsibilities are separated and workflows are coherent.
Langue du texte source : anglais
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Langue du texte source : anglais
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Langue du texte source : anglais