Menu
Skills in this repository
SkillsMP has collected 2,943 skills from tools-only/X-Skills. Open a skill to review its source and details.
tools-only/X-SkillsShowing 40 of 2,943 collected skills.
Runs the description-drift experiment — spawns all Claude Code agents simultaneously to collect self-reported capabilities, then compares them against static frontmatter descriptions to reveal how reliable orchestrator routing based on descriptions actually…
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,…
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,…
Converts user-facing documentation (how-to guides, tutorials, API references, examples) 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…
Orchestrates specialized agents to create high-quality Claude Code plugins. Delegates to plugin-assessor agent for domain research and code discovery, general-purpose agents for official docs verification, validation scripts for schema checks, and review…
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…
Use when working with ty — running Python type checks, configuring ty.toml or pyproject.toml, suppressing diagnostics, interpreting error codes, targeting Python versions, or integrating ty with editors and CI. Covers CLI flags, configuration schema, rule…
Review a GitHub Pull Request and submit a single review with inline code comments. Identifies bugs, security vulnerabilities, performance issues, logic errors, missing edge cases, and suggests improvements. Use when the user wants to review a PR, do a code…
Capture screenshots or GIF recordings of a new UI feature, upload them losslessly to a GitHub orphan branch (pr-assets), and add a Screenshots section to the current PR description. Images are served via github.com blob URLs which work for both public and…
Fetch PR review comments in sequential order, perform deep analysis with code context and impact assessment, suggest concrete solutions with alternatives, enter Plan mode for complex changes, and auto-resolve threads on GitHub.
Skill-aware orchestration with context routing. Decomposes complex tasks into skill-typed subtasks, extracts targeted context subsets, executes subagents in parallel, and synthesizes results. Self-answers trivial lookups inline. No SDK dependency — uses raw…
Unified paper audit skill supporting Chinese & English academic papers. Supports LaTeX (.tex), Typst (.typ), and PDF (.pdf) input formats. Three modes: self-check (pre-submission), review (peer review simulation), gate (quality gate pass/fail). Use when user…
LaTeX academic paper assistant for English papers (IEEE, ACM, Springer, NeurIPS, ICML). Use when writing, reviewing, compiling, or improving English LaTeX academic papers. Use when user mentions compile, grammar, bibliography, deai, translate, title, logic,…
Competitive analysis agent that identifies alternatives, compares features, and assesses market positioning. Skipped in quick mode.
Goal alignment agent that evaluates whether a project's implementation matches its stated objectives. Compares claimed features vs actual implementation, identifies gaps and over-engineering.
UX/DX audit agent that evaluates user experience and developer experience quality. Assesses first-use experience, README quality, API/CLI design, documentation coverage, and identifies experience pain points.
Product discovery agent that analyzes a project snapshot to identify what the product is, who it's for, and what problem it solves. Produces user personas, value propositions, and stage assessment.
Roadmap planner agent that synthesizes all analysis outputs into a final product review report with scores, prioritized improvements, milestones, and key metrics.
Build type-safe React apps with TanStack Query (data fetching, caching, mutations), Router (file-based routing, search params, loaders), and Start (SSR, server functions, middleware). Use when working with react-query, data fetching, server state, routing,…
Running `prek --all-files` produces pages of plugin-validator output — every file in the repo gets validated, and pre-existing warnings/errors (broken links, SK006 complexity, missing trigger phrases) for files unrelated to the current change drown out…
Define explicit triggers for escalating to human at each stage (not just Discovery). When should agents block and ask vs attempt repair vs fail?
Use when assigning backlog items to a GitHub milestone. Args: {milestone-number} [P0|P1|P2|title-filter]. Uses backlog list to load items, shows items with GitHub Issue status, lets user select which to assign. Creates missing GitHub Issues for selected P0/P1…
When per-item files have plan: N/A (set on completed items), work-backlog-item Step 2 treats it as a valid plan path and stops with 'This item already has a plan at N/A'. Currently all 22 items with plan: N/A are status: done so they're filtered out, but this…
Audit agent lifecycle — validates agent execution capability against configuration. Accepts plugin path, runs 8 semantic audits (capability vs config alignment, skill loading correctness, inter-agent contracts, prompt contradictions, tool sufficiency, dead…
Comprehensive linting and formatting verification workflows. Provides automatic format-lint-resolve pipelines for orchestrators and sub-agents. Use when running linters, fixing ruff/mypy/bandit errors, ensuring code quality before completion, or resolving…
Install and configure the GitHub CLI (gh) for AI agent environments where gh may not be pre-installed and git remotes use local proxies instead of github.com. Provides auto-install script with SHA256 verification and GITHUB_TOKEN auth with anonymous fallback.…
Integrate patterns from external sources (URLs or files) into local skills, agents, and plugins. Triggers on comparing external agent definitions against local equivalents, extracting best practices from frameworks like GSD or BMAD-METHOD, enhancing local…
Creates Claude Code agent files from requirements — handles discovery, template selection, frontmatter generation, scope determination (project/user/plugin), and plugin.json updates. Use when the user asks to create an agent, generate an agent, add an agent…
`validate_glfm.py` lines 152-153 hardcode `https://sourcery.assaabloy.net` as the default GitLab instance URL. `gitlab-ci-local-guide.md` line 51 also references this URL. This leaks a corporate internal URL into a public repository. Replace with a generic…
`plugin_validator.py` token complexity thresholds (4400 warn, 8800 error) are hardcoded constants. Allow per-project or per-plugin configuration via a config file (e.g., `.claude-plugin/validator.json` or a `[tool.plugin-validator]` section in…
Define explicit guidance for measuring and managing context size per agent. What's the target token budget? How to detect context pressure?
Test agent-browser (Playwright-based) on host with unrestricted network and Playwright browsers installed. **Validation steps**: - Install browsers: `npx playwright install` - Test: `npx agent-browser open https://code.claude.com/docs/en/skills` - Test: `npx…
Resolve linting/type errors by investigating root causes, not silencing symptoms. Use when ruff, mypy, pyright, or basedpyright report issues. Researches rules, reads code context, loads python3-development skill, and elegantly rewrites code to fix underlying…
Verify claims in backlog items, skill documentation, or plugin content against primary sources using web lookups. Spawns parallel verification agents that MUST use WebFetch/WebSearch/gh — training data recall is explicitly rejected as evidence. Produces…
The skill-research-process skill has sound research orchestration but lacks output specification for producing complete CLI tool skills. Three gaps identified via assessment against the uv skill: (1) No local directory input — passing a path like…
"Extract and enhance `validate_frontmatter.py` into a standalone open-source project. First dedicated linter for Claude Code plugin frontmatter (SKILL.md, agents/*.md, commands/*.md). Official `claude plugin validate` only checks plugin.json…
Use when working, planning, or closing a backlog item. Bridges backlog items to the SAM planning pipeline with optional GitHub Issue/Project/Milestone tracking. No args: interactive browser. With '#N': load item directly from GitHub Issue #N (labels and…
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic…
Groom backlog items — trigger /groom-backlog-item <title|section|all> — fact-checks item claims against primary sources, runs RT-ICA per item, then spawns @backlog-item-groomer agents. Writes groomed content into per-item files in .claude/backlog/. Use when…
Document the multi-agent expert panel methodology as a reusable system for building datasets that inform skills and systems. The process — assign framework experts to repositories, ask structured questions, cross-examine, synthesize, map to requirements,…