setup-working-genius

Solid

Optional per-repo configuration — pin the work-file directory and verify commands so every stage runs them the same way.

AI & Automation 5 stars 0 forks Updated 4 days ago MIT

Install

View on GitHub

Quality Score: 80/100

Stars 20%
26
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Setup Working Genius The workflow runs fine on defaults (`.genius/` for work files, verify commands discovered per run). This skill pins those choices per repo so no session has to rediscover them. Run it once, or never. Run it as a conversation, not a script: look first, propose what you found, and let the user correct each choice before anything gets written. ## Process ### 1. Explore - `CLAUDE.md` / `AGENTS.md` at the repo root — which exists? Is there already a `## Working Genius` section? - `.genius/` — any work files already in flight? - The project's task runner (`package.json` scripts, `Makefile`, `justfile`, `pyproject.toml`, …) — find the likely typecheck, test, and lint commands. ### 2. Ask, one decision at a time **A — Work-file directory.** Default `.genius/` at the repo root. Also ask: commit work files or gitignore them? Recommend committing — done files are decision history, and gates only bind what's visible to every session. **B — Verify commands.** Propose the discovered typecheck / test / lint commands; let the user correct them. These are what Enablement runs each cycle and Tenacity runs fresh at close-out. **C — Gate enforcement.** How hard should the Stop hook hold the gate rule when a stage ran past an unchecked, unskipped gate? `warn` (default): blocks ending the session once per distinct bypass state — the repair message lands, then the user can still stop. `block`: every stop attempt re-blocks until the bypass is repaired or recorded as s...

Details

Author
donald-ada
Repository
donald-ada/workinggenius
Created
3 weeks ago
Last Updated
4 days ago
Language
Shell
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category