- Skills
- 94
- 仓库
- 1
- 职业覆盖
- 0
- 场景覆盖
- 0
- Stars
- ★ 1
Joshua Hayes 的 Skills 94
no-key
A skill its skills.json lists as hidden that a model may still call by itself, kept broken so the lint is seen to catch it.
fake-skill
A FAKE skill in a FAKE tree, named for its folder until the test renames the folder.
extra-key
A skill its skills.json does not list as hidden that a model still cannot call, kept broken so the lint is seen to catch it.
unslop
Cut AI tells from writing. Use when the user says text reads like AI, asks to unslop it, or before prose ships to people.
technical-writing
Write or review docs, READMEs, RFCs, PR descriptions and commit messages to a layered standard: Diataxis structure, Google developer style, STE rules and Global English.
why
Find why code is the way it is, from its history and every evidence source this session can query, with citations. Use for 'why does X work this way', 'why did we pick Y', regressions and postmortems. Use how for runtime behavior.
verify-jstack
Drive jstack's commands (jbus, jmerge, jgauge, install.sh) the way a user does, inside a throwaway sandbox with stand-ins for T3 Code and GitHub, and keep the evidence. Use to prove a change to jstack works in the real commands and not only in its tests, before a pull request claims it does.
typescript-best-practices
TypeScript best practices. Use before reading or editing .ts or .tsx files.
teach
Explain a body of work plainly until the user understands it, using how and why. Use for 'teach me this', 'help me really understand X', or explaining a change or subsystem.
tdd
Fix a bug test-first, with a focused regression test that fails before the fix and passes after. Use for a bug with a clear, cheap test path; skip it when the test would be slow or integration-heavy.
statechart
Draw what an app's user sees as a Mermaid statechart from a TLA+ model, each bug TLC finds a numbered path. Use for 'show the PM the bug', or to turn an agreed chart into a TLA+ skeleton.
retro
Audit what happened over a past window from the raw records: build a dataset you can rerun, freeze a codebook before reading any outcome, sharpen the prompt, and send scouts, with a second labeller, a red team, and rates that show their row mix. Use for /retro, 'audit what happened over <window>', 'take a census of', 'what went wrong last week'.
poteto-help
Answer a help question about jstack: setup, which role takes a piece of work, and which playbook and skills fit a brief. Use for 'how do I do X in jstack', 'which playbook fits', or 'what do I type'.
make-bot-ui
Build a page whose buttons wake this T3 Code thread through a schedule_task webhook, served on the tailnet by a local server that keeps the webhook's URL and key off the browser. Use for /make-bot-ui, 'make a bot UI', 'buttons that wake this thread'.
maintain-verification-skill
Keep a repo's verify skill, `.claude/skills/verify-<app>/` or a `verify-<app>` project skill, and its feature map honest as the app changes: typed in the repo's home, it sends one scout per feature file to read the feature from source, then writes one crewmate brief for the live pass over every feature and at most one pull request of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".
maintain-formal-verification-skill
Bring a project's formal verification back in line after the code changed: update the model, rerun, and say whether each failure is drift or a bug. Use for 'is the model still true to the code', or after merges touched verified code.
interrogate
Adversarially review a change with two reviewers that do not see each other, then filter what they found. Use for 'challenge this', 'stress test this code', 'find blind spots' or 'tear this apart'.
figure-it-out
Frame a task no playbook fits (a large migration, an ambitious multi-part change, work reviewed after stepping away) and, in a home, plan it as entries. Use for 'figure it out'.