clean-docs

Solid

Clean up the repository's docs, comments, rules, and tests as a CAFleet team of disjoint-slice scanner members gated by a reviewer — exactly one workflow per run. Use the residue workflow when the user asks to clean up historical narration or historical residue, remove deprecation notes / "this replaces X" / "renamed from Y" / "previously … now …" prose, drop design-number provenance citations, or delete removal-sentinel tests. Use the affirmative workflow when the user asks to run an affirmative-writing sweep, fix prohibition-only rule sections, pair prohibitions with affirmatives, remove meaningless fallbacks, or make code fail fast. Use the simplification workflow when the user asks to simplify the docs or comments, tighten verbose prose, de-duplicate documentation, or remove redundant comments. Nothing is applied before the reviewer approves the merged run artifact. Members load this skill by its name clean-docs via their backend's skill-loader.

AI & Automation 51 stars 4 forks Updated today MIT

Install

View on GitHub

Quality Score: 84/100

Stars 20%
57
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Clean-Docs Skill (CAFleet-orchestrated) One skill, three workflows — **residue**, **affirmative**, **simplification** — run as the same CAFleet team shape over the same per-run process. This page is the dispatcher and the single home of the **shared orchestration spine**; each workflow body (`<workflow>/<workflow>.md`) carries only its own trigger scenario, scan mechanics, artifact spec, and guarantees, citing the spine here rather than restating it. ## Required reading Identify your coding agent first — a member's spawn prompt names it on the `CODING AGENT:` line; the Director (main session) uses its own identity — then Read your overlay and **resolve** it before your first action. **Load-bearing — Read in order before acting:** | # | Read | What you lose if you skip it | |---|------|------------------------------| | 1 | your overlay section [`../../../skills/cafleet/reference/coding-agent-overlays.md#<name>`](../../../skills/cafleet/reference/coding-agent-overlays.md) — read **and resolve** it (see *Resolve your overlay* in the cafleet `SKILL.md`) | you emit a literal `{bg_run}` / `{reviewer_model}` / `{skill_loader}` / `{decision_surface}`, guess a wrong value, or ignore a backend note | | 2 | the `cafleet` skill's [`reference/base-dir.md`](../../../skills/cafleet/reference/base-dir.md) | the task-scope BASE resolution, the no-bypass write protocol, and the `<unset>` contract — you mis-root run artifacts or fall back to `/tmp` | | 3 | the `cafleet-design-doc` skill'...

Details

Author
himkt
Repository
himkt/cafleet
Created
5 months ago
Last Updated
today
Language
Rust
License
MIT

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category