Audit documentation against code for drift, sync docs after code changes, optimize CLAUDE.md and SKILL.md prompts, validate GLFM/Markdown formatting, and summarize files, URLs, or images with source-attributed citations.
Audit documentation against code for drift, sync docs after code changes, or track doc freshness. Delegates to the right specialist automatically.
Author user-facing docs, validate GLFM formatting, or summarize files/URLs/images. Pass the task description or file path.
Write source-attributed content from URLs or content blocks. Fetches sources, cross-references claims, and produces content with hyperlinked citations. Pass the source URL and content context.
Convert user-facing documentation into an AI-readable Claude skill. Pass a GitHub URL or local path to the docs directory.
Optimize AI-facing prompts, CLAUDE.md, SKILL.md, or agent definitions using Anthropic best practices. Pass the file path as argument.
Audits documentation accuracy against code, syncs docs after code changes, and tracks doc freshness. Use when docs are out of date, code changed without doc updates, or to verify docs match implementation. Delegates to specialist agents — does not implement changes directly.
Authors and validates user-facing documentation — READMEs, tutorials, API docs, GitLab Wiki pages, and GLFM-formatted content. Also routes summarization requests (files, URLs, images, multi-source). Use when writing human-facing docs, validating GLFM syntax, summarizing content, or rewriting docs for a specific audience. NOT for AI-facing docs — use rewrite-room-optimizer for those.
Primary source verification and citation-driven content writer. Analyzes websites and content blocks, cross-references claims against source material, and produces attributed content with hyperlinked citations. Use when creating blog posts, research summaries, or any content requiring rigorous source attribution and credit to original creators.
Converts user-facing documentation directories into Claude Code skill directories — SKILL.md with valid frontmatter plus thematically grouped references/*.md files. Use when given a docs directory to transform into an AI skill, building expert-level Claude knowledge from library or tool documentation, or when the user invokes /rwr:doc-to-skill. Reads the user-docs-to-ai-skill SKILL.md and follows it — delegates Phase 1.5 workflow identification to process-siren.
Optimizes AI-facing prompts, CLAUDE.md configurations, SKILL.md files, and agent definitions using Anthropic prompt engineering best practices. Use when CLAUDE.md feels ineffective, SKILL.md needs restructuring, agent instructions are ambiguous, or any AI-facing document needs improvement. NOT for user-facing docs — use rewrite-room-author for those.
Use when auditing docs vs code drift, syncing docs after changes, optimizing CLAUDE.md or SKILL.md for AI consumption, validating GLFM and Markdown, or summarizing files/URLs/images — routes each task to the correct specialist agent via /rwr:audit, /rwr:optimize, or /rwr:author
Converts user-facing documentation (how-to guides, tutorials, API references, examples) in any format — Markdown, PDF, DOCX, PPTX, XLSX, AsciiDoc, RST, HTML, Jupyter notebooks, man pages, TOML/YAML/JSON configs, and plain text — into Claude Code skill directories with SKILL.md plus thematically grouped references/*.md files. Use when given a docs directory or mixed-format documentation to transform into an AI skill. Uses MCP file-reader server for binary formats.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Professional workflow plugins for Claude Code — make Claude apply your project's actual linting rules, commit conventions, and testing standards, not generic defaults. Covers Python, shell, Perl, CI/CD, and AI tooling.
| Without plugins | With plugins |
|---|---|
| Claude gives generic Python advice | Claude applies Python 3.11+, Typer, Rich, httpx conventions specific to your stack |
| Claude says "done" before linters pass | holistic-linting enforces root-cause fixes before any task completes |
| Claude speculates and hallucinates | hallucination-detector blocks completion on ungrounded claims |
| Claude jumps to solutions without investigating | verification-gate forces evidence gathering before action |
| Session transcripts disappear with no learning | agentskill-kaizen mines transcripts for anti-patterns and generates skill patches |
| Commit messages are inconsistent | conventional-commits enforces feat/fix/chore format for semantic versioning |
| Claude reads source files when it should delegate | orchestrator-discipline hooks block investigation escalation at the tool level |
# Add the marketplace (one-time setup, ~10 seconds, no restart required)
/plugin marketplace add Jamie-BitFlight/claude_skills
# Install a plugin
/plugin install plugin-name@jamie-bitflight-skills
Start a new session and ask Claude to perform a task the plugin handles (for example, build a CLI with Typer after installing python3-development). Claude will apply the plugin's conventions rather than generic defaults.
Comprehensive frameworks with multiple skills, commands, and specialized agents.
npx claudepluginhub jamie-bitflight/claude_skills --plugin rwrRead The Fucking Prompt — finds the strongest user reaction to an AI instruction-following failure in a chosen session, reconstructs the triggering assistant output, and renders a shareable terminal-style PNG.
This skill should be used when the model needs to ensure code quality through comprehensive linting and formatting. It provides automatic linting workflows for orchestrators (format → lint → resolve via concurrent agents) and sub-agents (lint touched files before task completion). Prevents claiming "production ready" code without verification. Includes linting rules knowledge base for ruff, mypy, and bandit, plus the linting-root-cause-resolver agent for systematic issue resolution.
When setting up commit message validation for a project. When project has commitlint.config.js or .commitlintrc files. When configuring CI/CD to enforce commit format. When extracting commit rules for LLM prompt generation. When debugging commit message rejection errors.
Comprehensive Perl 5.30+ development plugin with modular skills for scripting, CPAN ecosystem, environment setup, testing, linting, and validation. Includes specialized agents for script development, code auditing, and CLI architecture.
Build FastMCP 3.x Python MCP servers — covers provider/transform architecture (including CodeMode, Tool Search, and server-level transforms), component versioning, session state, authorization (MultiAuth, PropelAuth, connection-pooled token verifiers), evaluation creation, Pydantic validation, async patterns, STDIO and HTTP transports, nginx reverse proxy deployment, background tasks, Prefab Apps UI, security patterns, client SDK usage, testing, deployment, and migration from FastMCP v2. TypeScript is a legacy reference only and is not updated for v3.
Auto-formatting hooks for Python, JavaScript, Markdown, and Bash with Google-style docstrings and code quality checks.
Faithful information summarization with fidelity preservation, structured output, and anti-hallucination methodology. Provides skills for file, URL, and image summarization; agents for autonomous summarization tasks; and hooks for validating agent output structure.
Audit and optimize Claude Code configurations with dynamic best-practice research
Documentation review, cleanup, and generation with AI slop detection, style learning, and human-quality writing enforcement
Documentation quality, generation, and improvement using Diataxis principles. Pairs with beagle-core for full workflow.
Codex CLIにセカンドオピニオンを求めるスキル。「codexと相談して」「codexに聞いて」で発動する。