Automated summary
Acts as a launcher that routes each audit request to the correct /nitpicker subcommand.
Strengths
- Explicit routing table mapping common user phrasings to a specific command.
- Keeps a single source of truth by deferring the command list to skills/nitpicker/SKILL.md instead of duplicating it.
- Enforces one command per request and leaves any command chaining to the nitpicker router.
- Covers a wide range of audits including security, tests, types, docs, CI and licenses.
Limitations
- Performs no audit itself; it only selects the command to run.
- Matching relies on expected phrasings, so ambiguous requests may need `make list` or clarification.
- Assumes the /nitpicker commands and the underlying router are installed.
Use when the user wants to run one of the repository's audit commands or asks which audit commands are available.
Do not use it to actually carry out a specific audit or for tasks unrelated to /nitpicker commands.
Security analysis
SafeThe skill only provides routing instructions to internal /nitpicker audit commands and a fallback command to list skills. It does not instruct destructive actions, data exfiltration, credential handling, or use of external network tools. The referenced commands are within the repository's own audit tooling and pose no meaningful execution risk.
No concerns found
How this analysis is madeExamples
Run a full pre-release audit of this repo and tell me what needs fixing before we ship.We're worried about SQL injection and leaked secrets — run the appropriate audit on this codebase.What audit commands are available in this repo?name: skills description: Routes audit requests to the right /nitpicker command. Use when the user wants to run one of the hostile audit commands in this repo, or asks what audit commands are available.
Skills Launcher
Everything public in this repository is one skill — nitpicker — invoked as
/nitpicker <command> [extra instructions]. The authoritative command table
lives in skills/nitpicker/SKILL.md (## Commands); do not duplicate it
here. /nitpicker help prints it.
Routing Guide
If the user says… → run:
- "review the whole repo / audit everything / pre-release check" →
/nitpicker(default audit) - "review this code / find bugs / tear this apart" →
/nitpicker review - "review this PR / give me a PR comment" →
/nitpicker pr - "implement cr comments / address pr feedback" →
/nitpicker cr - "security audit / find vulnerabilities / check for secrets" →
/nitpicker security - "audit the tests / do the tests actually test anything" →
/nitpicker tests - "audit the types / check type safety / find the anys / are the type ignores real" →
/nitpicker types - "check the docs / find stale documentation" →
/nitpicker docs - "audit CONTRIBUTING / is our contributor guide accurate / we have no CONTRIBUTING.md" →
/nitpicker contributing - "what architecture is this / detect patterns" →
/nitpicker arch-profile - "audit the architecture / find violations" →
/nitpicker arch - "perf audit / why is this slow / will this scale" →
/nitpicker perf - "audit dependencies / prune deps" →
/nitpicker deps - "audit the licenses / license compatibility / are we GPL-contaminated / check attribution" →
/nitpicker license - "find silent failures / what errors are we swallowing" →
/nitpicker errors - "audit the CI / GitHub Actions security" →
/nitpicker ci - "audit the commits / verify conventional commits" →
/nitpicker commits - "audit the migrations / is this migration safe" →
/nitpicker migrations - "audit observability / can we debug this at 3am" →
/nitpicker observability - "does the spec match the code / is this change breaking" →
/nitpicker contract - "a11y audit / check WCAG / keyboard accessible" →
/nitpicker a11y - "privacy audit / PII audit / GDPR check" →
/nitpicker privacy - "config audit / check env vars / config drift" →
/nitpicker config - "audit the infra / Dockerfile / Terraform / k8s security / IaC misconfig" →
/nitpicker iac - "audit prompt safety / check for prompt injection / is this agent safe / LLM integration" →
/nitpicker prompt-safety - "find leaks / unclosed connections / fd leak" →
/nitpicker leaks - "i18n audit / find hardcoded strings" →
/nitpicker i18n - "find race conditions / is this thread-safe" →
/nitpicker concurrency - "close loopholes / can our rules be bypassed" →
/nitpicker agent-loopholes - "enforce hooks / harden hook coverage" →
/nitpicker agent-hooks - "audit .claude/rules / rules placement" →
/nitpicker agent-rules - "be lazy / YAGNI / find bloat / over-engineering" →
/nitpicker complexity - "find unwired code / is everything hooked up / incomplete implementations" →
/nitpicker unwired - "plan this / how should we build X / design the implementation" →
/nitpicker plan - "execute the plan / implement the approved plan / build what we planned" →
/nitpicker execute-plan - "teach me X / help me learn X / explain X so it sticks / next lesson" →
/nitpicker teach - "can we ship / release gate" →
/nitpicker release-gate - "baseline the findings / accept existing debt / only fail on new findings" →
/nitpicker baseline - "what audit commands are there / list the commands" →
/nitpicker help
Rules
- Select exactly one command per request. Never chain commands yourself — the nitpicker router owns any command-to-command hand-off.
- If the request matches multiple commands, pick the most comprehensive
(
/nitpickerdefault audit covers code, architecture, and docs).
If Unclear
Run make list (or uv run scripts/list-skills.py) to print the skill and
its commands with descriptions, then ask the user which one fits.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/audit-request-router-mryiqfr9/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/audit-request-router-mryiqfr9' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/audit-request-router-mryiqfr9/download' --output '.skill-downloads/audit-request-router-mryiqfr9/SKILL.md.part' && mv '.skill-downloads/audit-request-router-mryiqfr9/SKILL.md.part' '.skill-downloads/audit-request-router-mryiqfr9/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/audit-request-router-mryiqfr9/SKILL.md' && test -s '.skill-downloads/audit-request-router-mryiqfr9/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/skills' && cp -R '.skill-downloads/audit-request-router-mryiqfr9' '.claude/skills/skills'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/audit-request-router-mryiqfr9'openskills read 'audit-request-router-mryiqfr9'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/audit-request-router-mryiqfr9/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.