joetawil7/first-pass / skills/setup-first-pass
setup-first-pass
UnverifiedSet up first-pass for a main folder that holds many repos, or for one repo. In a main folder it writes one set of working rules at the root that every session loads, a workspace map, and a section in each repo with that repo's real commands, test limits and invariants, and it lists each repo's own hooks so first-pass can run them from the main folder. In one repo it writes the rules and the section into that repo. Use when asked to set up, install, add, update or re-run first-pass, to "add the shipping rules", or when the start-of-session check says something drifted. Re-run to update.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 33.0 KB |
| assets/INVARIANTS.md | markdown | 801 B |
| assets/breaker.md | markdown | 9.5 KB |
| assets/machine-block.md | markdown | 1.3 KB |
| assets/profile-block.md | markdown | 5.7 KB |
| assets/project-block.md | markdown | 1.2 KB |
| assets/rules-block.md | markdown | 22.6 KB |
| assets/words-block.md | markdown | 1.6 KB |
| assets/workspace-block.md | markdown | 626 B |
assets/words-block.md
View on GitHub<!-- first-pass:words:start v0.9.3 default (the default list; the habit-words skill replaces it with the words this user actually writes, read from their sessions) -->
### Habit words
Words the user may write, and the checks each one asks for. None of them ever means "sound
more certain", and the checks apply whether or not the words are written.
- "be 100% sure", "confident", "don't assume": every claim rests on a command, its output or
a file:line from this session, and the rest is listed as "Not verified" (Evidence).
- "cover all gaps and cases", "bug free", "doesn't break anything": the pre-mortem, with
every other reader and writer of the data (question 5) and the test that proves each case.
- "full", "deep", "comprehensive", "everything": say up front what will be read whole, what
sampled and what not covered, and repeat it in the report (Say the coverage).
- "carefully", "correctly", "perfect", "take your time": the definition of done (Done means
proven), not a slower pace.
- "all fine, right?", "is it done?", "anything left?": what is not done or not verified
comes first (No yes by default).
- "are you sure?": re-check the claim at its source, then say which part holds and which does
not; never flip, and never apologize instead of checking (Pushback gets checked).
- "fix it once and for all": reproduce it first, then fix the class (the `fix-the-class` skill).
- "do whatever you want", "take control": covers the task named; money, production deletes
and outward-facing actions still need a yes (Grants stay narrow).
<!-- first-pass:words:end -->
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |