Menu
SkillsMP a collecté 99 skills depuis cajias/claude-skills. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 99.
Research (as an internal step) a GitHub/GitLab milestone's open issues in order to PRINT a copy-paste autonomous-loop prompt that drives the milestone to completion — behavior-driven (BDD) scenarios, adversarial gap-checking, a per-iteration…
Langue du texte source : anglais
Eight APM-marketplace-authoring gotchas discovered during real migrations from hand-authored .claude-plugin/marketplace.json to APM-managed and from CC-native plugin authoring. Use when: (1) running APM's packaging step (with or without `--dry-run`) or its…
Langue du texte source : anglais
Canonical authoring layout for an APM (microsoft/apm) package, plus the decision matrix for whether you need a `marketplace:` block. Use when: (1) you've run `apm init` and are unsure where SKILL.md / agent .md / command .md files belong (answer: under…
Langue du texte source : anglais
Fix for Claude Code startup error `Plugin directory not found at path: <marketplace_root>/<plugin_name>. Check that the marketplace entry has the correct path.` when the marketplace is a `source: "directory"` marketplace that uses `metadata.pluginRoot` to…
Langue du texte source : anglais
Analyze Claude Code sessions to extract configuration improvements. Use when: (1) Want to optimize Claude Code setup (skills, permissions, CLAUDE.md), (2) Need to find what tools should be pre-granted (repeated permission requests), (3) Looking for skills to…
Langue du texte source : anglais
This skill should be used when the user asks to "migrate quip to obsidian", "download quip images", "fix quip diagrams", "export quip folder", or mentions migrating Quip documents with images/diagrams to Obsidian. Handles complete Quip folder migration…
Langue du texte source : anglais
Generate comprehensive software effort estimation reports that analyze codebase complexity, calculate traditional development effort across five estimation models, and quantify productivity gains from LLM-assisted development. Use when estimating project…
Langue du texte source : anglais
Standalone AIDE-style autoresearch agent: tree-search over candidate solutions (draft/debug/improve operators) for any task directory with a task.md and score.py — ML engineering, heuristic optimization, or harness engineering. Runs the current best…
Langue du texte source : anglais
Use when: (1) User asks to "review for AI writing" or "check for LLM signs" (2) User wants to "detect AI-generated text" or "humanize this document" (3) User wants to identify and fix signs of AI/LLM-generated writing (4) User mentions Wikipedia AI writing…
Langue du texte source : anglais
Humanize a document by removing AI-writing patterns via a multi-agent workflow (analyze → revise → adversarial review → loop-until-clean). Use when the user asks to "humanize", "de-AI", "remove AI tells", or "review for AI writing" on a file.
Langue du texte source : anglais
Extract reusable skills from Claude Code sessions. Triggers: /claudeception command, "save this as a skill", "what did we learn?". Creates SKILL.md files for non-obvious discoveries, workarounds, and debugging insights.
Langue du texte source : anglais
Use Obsidian as Claude's primary workspace and persistent memory. Activates for ALL file operations during sessions - working notes, scratchpads, analysis, task tracking - not just permanent knowledge. Prefer Obsidian MCP tools over local disk writes. Use…
Langue du texte source : anglais
Use this skill for efficient Obsidian vault navigation and search. Covers which MCP tools to use, search strategies, batch operations, and how to leverage frontmatter summaries for quick triage.
Langue du texte source : anglais
Monitor GitHub pull requests and automatically resume when new commits are detected
Langue du texte source : anglais
Semantic search over Obsidian Zettelkasten notes. Use when the user asks "What do I know about X?", "Find notes about...", or wants to search their knowledge base by meaning rather than exact keywords.
Langue du texte source : anglais
Fix for Task tool subagents with subagent_type=Bash being unable to write files when PreToolUse hooks block write operations. Use when: (1) dispatching parallel Bash agents to implement code in worktrees, (2) agents report "Permission to use Bash has been…
Langue du texte source : anglais
Fix AWS CDK bundling failures caused by multiple package lock files in the same project. Use when: (1) CDK synth/deploy fails with "ValidationError: Multiple package lock files found: pnpm-lock.yaml, package-lock.json", (2) NodejsFunction or other bundled…
Langue du texte source : anglais
Fix disk space exhaustion caused by AWS CDK temp folder accumulation on macOS. Use when: (1) Disk is full or nearly full with no obvious cause, (2) Running CDK synth, deploy, or tests (especially in TDD loops), (3) /private/var/folders is consuming tens of…
Langue du texte source : anglais
Fix extremely slow AWS CDK tests (30+ minutes for a single test file). Use when: (1) CDK tests take 30+ minutes to run, (2) Each test creates `new cdk.App()` in beforeEach, (3) Tests trigger Docker image builds repeatedly, (4) Jest shows tests running but no…
Langue du texte source : anglais
How to discover and add Claude Code plugin marketplaces. Use when: (1) user asks about claudemarketplaces.com or similar discovery sites, (2) user wants to add a plugin marketplace, (3) confusion between marketplace directories and actual marketplaces, (4)…
Langue du texte source : anglais
Fix CloudFormation deployment failures caused by KMS alias collisions. Use when: (1) CDK deploy fails with "AWS::EarlyValidation::ResourceExistenceCheck" error, (2) Multiple CDK stacks create KMS keys with similar aliases, (3) Deployment fails before…
Langue du texte source : anglais
Fix Docker Desktop stuck in partial running state on macOS. Use when: (1) `docker ps` fails with "dial unix ... docker.sock: connect: no such file or directory", (2) `docker desktop status` says "Could not retrieve status. Is Docker Desktop running?", (3)…
Langue du texte source : anglais
Squash multiple git commits into one using soft reset - a non-interactive alternative to rebase. Use when: (1) you need to squash commits without an editor, (2) interactive rebase hangs or requires manual intervention, (3) CI/CD or automated contexts where…
Langue du texte source : anglais
Organize GitHub repository issues with proper milestones, native relationships, and clean labeling structure. Use when grooming issues, setting up milestones, establishing dependencies, or cleaning up issue tracking in a GitHub repository.
Langue du texte source : anglais
Debug common GitLab CI/CD pipeline failures. Use when: (1) Pipeline fails with unclear error messages, (2) Jobs fail with AWS credential or permission errors, (3) Node/npm jobs fail in CI but work locally, (4) Format/lint checks fail in pipeline, (5) MR…
Langue du texte source : anglais
Explore GitLab groups, subgroups, and projects using glab CLI API commands. Use when: (1) Need to list all projects in a GitLab group/namespace, (2) WebFetch fails for private/internal GitLab instances like code.aws.dev, (3) Want to get project details…
Langue du texte source : anglais
Reply to GitLab MR code review discussion threads using glab CLI. Use when: (1) need to respond to specific code review comments, (2) want threaded replies not top-level MR comments, (3) `glab mr note` only adds top-level comments. Covers: getting discussion…
Langue du texte source : anglais
Use when GitLab MR comments have position null, appear as DiscussionNote instead of DiffNote, or inline code review comments show as general MR comments. Also use when glab api nested object parameters are ignored.
Langue du texte source : anglais
Fix yamllint failures on GitLab CI `!reference` tags. Use when: (1) yamllint fails with "unknown tag" on `.gitlab-ci.yml`, (2) Pre-commit hooks reject valid GitLab CI syntax, (3) CI lint job fails but GitLab accepts the YAML, (4) Error mentions `!reference`…
Langue du texte source : anglais
This skill should be used when the user asks to "execute an HLD", "implement a high-level design", "run phased migration", "execute architecture phases", "implement HLD with TDD", or has a multi-phase project document (HLD, architecture doc, migration plan)…
Langue du texte source : anglais
Phase 0.5: Infrastructure State Analysis for CDK/CloudFormation work. MANDATORY before TDD RED phase when working with infrastructure code. Prevents architectural errors by analyzing deployed state, cross-stack dependencies, and synth behavior.
Langue du texte source : anglais
Fix mypy "Name iterm2.Session is not defined" or "Name iterm2.Window is not defined" errors in iterm-c4 project. Use when: (1) mypy fails with name-defined errors on iterm2 types despite ignore_missing_imports=true in pyproject.toml, (2) working with the…
Langue du texte source : anglais
This skill should be used when the user asks to "convert markdown to LaTeX", "create a PDF book from markdown", "turn markdown files into a professional book", "generate LaTeX from markdown", or mentions creating professional PDF documentation from markdown…
Langue du texte source : anglais
Requirements for implementing an MCP (Model Context Protocol) server that works with the official @modelcontextprotocol/sdk client. Use when: (1) implementing an MCP server from scratch, (2) getting "Expected initialize response" errors, (3) MCP client fails…
Langue du texte source : anglais
Structure Obsidian documentation to reduce cognitive load using index files that link to detail files. Use when: (1) a single note is getting too long (>100 lines), (2) documentation covers multiple aspects (overview, architecture, implementation), (3)…
Langue du texte source : anglais
Enable Claude Code to delegate specific tasks to Amazon Q CLI agents running in the background with full tool permissions. Use when bridging to Q's specialized integrations such as Quip, ticketing systems, or diagram generation that Claude doesn't have direct…
Langue du texte source : anglais
Transfer markdown documents to Quip with proper formatting validation, handling common issues with lists, tables, and diagrams that occur during bulk uploads. Use when writing or syncing markdown content to Quip documents with section-by-section transfer for…
Langue du texte source : anglais
Fix TDD workflow state loss during Claude Code context compaction. Use when: (1) Agent forgets which TDD phase (RED/GREEN/REFACTOR) it's in after long sessions, (2) Agent repeats exploration/investigation work it already did, (3) Ralph-loop iterations lose…
Langue du texte source : anglais
Use when user says "create a tdd plan", "tdd loop", "iterative plan", "ralph-loop plan", "create plan for ralph". Generates a TDD-based plan formatted for ralph-loop execution with concurrent tasks, pr-review validation, and optional deploy/integration test…
Langue du texte source : anglais
Intelligently route tasks to the most appropriate Amazon Q CLI agent based on task type, with support for explicit agent selection and special workflow patterns. Use when delegating tasks to Q agents or triggering the quip-upload workflow for file uploads to…
Langue du texte source : anglais