Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From t5ive-skills
Guide for choosing which Claude Code skill to use. Use when user asks "what skill should I use", "which skill for X", "where do I start", "skill workflow", or describes a situation (starting feature, hit a bug, doing review) and wants to know the right tool.
How this skill is triggered — by the user, by Claude, or both
Slash command
/t5ive-skills:skill-navigatorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read `references/situations.md` for full decision tree.
Read references/situations.md for full decision tree.
| Situation | Skill Chain |
|---|---|
| Don't know which skill to use | /ask-matt |
| New feature, no codebase | /grill-me → /tdd |
| New feature, existing codebase | /setup-matt-pocock-skills (1st) → /grill-with-docs → /tdd |
| Bug (reproducible) | /debug-mantra → /post-mortem |
| Bug (flaky / perf) | /diagnose → /post-mortem |
| Hard bug / perf regression (deep) | /diagnosing-bugs → /post-mortem |
| Review / before merge | /scrutinize |
| Review diff for over-engineering | /ponytail-review |
| Audit whole repo for bloat | /ponytail-audit |
| Context window full | /handoff |
| Report to management | /management-talk |
| Understand codebase | /zoom-out |
| Architecture review | /improve-codebase-architecture |
| Break spec into issues | /to-prd → /to-issues |
| Move issues through triage | /triage |
| Write minimal code (lazy mode) | /ponytail |
| Reduce token usage, respond in Thai | /pordee |
| Learn a new concept over sessions | /teach |
| Sharpen domain terminology / ADRs | /grill-with-docs or /domain-modeling |
| Design module with clean seam | /codebase-design |
| Write or edit a skill | /writing-great-skills |
| Configure repo for MP skills | /setup-matt-pocock-skills |
karpathy-guidelines — always-on plugin, no invoke needed. pordee — always-on once activated, no re-invoke needed per session.
User-invoked (you type them): ask-matt, grill-me, grill-with-docs, triage, improve-codebase-architecture, setup-matt-pocock-skills, to-issues, to-prd, prototype, handoff, teach, writing-great-skills
Model-invoked (agent reaches for automatically): diagnosing-bugs, tdd, domain-modeling, codebase-design, grilling
User-invoked may invoke model-invoked. Never the reverse.
npx claudepluginhub t5ive/t5ive-skills --plugin skill-navigatorGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.