catch-me
Automated domain onboarding to help you adopt the mindset and vocabulary of a specific profession.
Install
mkdir -p .claude/skills/catch-me && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11084" && unzip -o skill.zip -d .claude/skills/catch-me && rm skill.zipInstalls to .claude/skills/catch-me
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Start or refresh domain onboarding for the current project. Generates persona, lexicon, signaling, anti-patterns, first-week plan, and a project-specific playbook for a chosen profession.Key capabilities
- →Generate persona
- →Create lexicon
- →Define anti-patterns
- →Develop first-week plan
How it works
It spawns a role-onboarder agent that generates domain-specific artifacts and a playbook tailored to the current project.
Inputs & outputs
When to use catch-me
- →Learning a new domain
- →Adopting a specific professional role
- →Project context onboarding
About this skill
catch-me
Entry point for the catch-me-if-you-can onboarding flow. The user wants to rapidly pass as — and think like — a practitioner in some domain, so they can direct Claude better on this specific project.
What happens when this skill fires
- The
role-onboardersubagent (bundled at${CLAUDE_PLUGIN_ROOT}/agents/role-onboarder.md) takes over in a forked context. - It asks up to three short questions (role + flavor, depth, project context) — skipping any already supplied in the invocation args.
- It generates 6 role artifacts +
meta.jsoninline, following${CLAUDE_PLUGIN_ROOT}/skills/catch-me/templates/role-generation-prompt.md. - It pipes the output through
${CLAUDE_PLUGIN_ROOT}/skills/catch-me/scripts/write_role_files.sh <slug>, which writes atomically to the user's project at$(pwd)/.claude/catch-me/roles/<slug>/and updates$(pwd)/.claude/catch-me/active-role.json. - It returns a compact cover-story summary (≈15 lines) to the user.
Invocation patterns
/catch-me— ask everything from scratch./catch-me <role>— role given, ask depth + project context./catch-me "<free-text description>"— parse what you can from the description, ask the rest.
Notes
- User input may be in any language, but generated artifacts are always English (v1 scope).
- All role state lives inside the user's current project at
.claude/catch-me/— nothing is written outside the project. Different projects get independent role state. - If the requested role already exists under
.claude/catch-me/roles/, the subagent offers resume / regenerate / replace instead of blindly overwriting. - After activation, the passive
active-roleskill auto-attaches the persona on role-relevant prompts — no further action needed from the user.
When not to use it
- →Non-project-specific onboarding
- →Projects without domain context
Limitations
- →Limited to English artifacts
- →State lives only within the project
How it compares
It creates project-specific onboarding artifacts rather than generic role descriptions.
Compared to similar skills
catch-me side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| catch-me (this skill) | 0 | 3mo | Review | Beginner |
| product-manager-toolkit | 32 | 7mo | Review | Beginner |
| gathering-requirements | 3 | 8mo | No flags | Intermediate |
| ideate | 1 | 6mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
product-manager-toolkit
davila7
Comprehensive toolkit for product managers including RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market strategies. Use for feature prioritization, user research synthesis, requirement documentation, and product strategy development.
gathering-requirements
CaptainCrouton89
Systematically clarify user needs, preferences, and constraints before planning or implementation. Classifies work type, investigates existing systems, discovers edge cases and integration points, resolves assumptions, and creates detailed specifications. Use when building features, enhancements, or integrations where requirements need clarification.
ideate
liveloveapp
Capture and document a new idea in this repo. Use when the user says things like "help me brainstorm", "I have an idea", or "let's capture this for the future" and wants it recorded in `design/ideas/` with a summary, supporting research (repo context + web if useful), and a sketch.
rfc
jiangzhe
Design and resolve RFC documents through evidence-gated multi-round workflow. Use when planning large architectural/program-level changes in docs/rfcs, enforcing goal/scope/direction clarity, explicit first-principles/long-term/original-fit proposal lenses with rationale, draft-to-formal progression
gsd-map-codebase
wikiepeidia
Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents
idea-extraction
RepairYourTech
Exhaustive idea extraction through recursive breadth-before-depth exploration with Deep Think protocol and fractal structure. Use during /ideate to transform raw ideas into comprehensive, structured ideation output. Writes to a fractal folder hierarchy — every node has an index, CX file, and childre