cp-skill-revise-iterative

Solid

Explicit-invocation instruction for iteratively revising a note for flow and cohesion while retaining numbered candidates and checking semantic fidelity before each continuation.

AI & Automation 83 stars 10 forks Updated yesterday CC-BY-4.0

Install

View on GitHub

Quality Score: 88/100

Stars 20%
64
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

## EXECUTE NOW **Demoted.** No longer in `promoted_skills` (see `src/commonplace/scaffold_manifest.py`) — the per-pass cost wasn't earning back enough revision quality. `commonplace-init` no longer auto-installs this into `.claude/skills/` or `.agents/skills/` for new projects, and the harness doesn't auto-load it here. Invoke it explicitly when you want this revision path. **Target: $ARGUMENTS** (exactly one note path or filename — if empty, ask which note) ### Step 0: Resolve the file Resolve `$ARGUMENTS` to a full path. If it's a bare filename, search `kb/notes/` for a match. Read the file to confirm it exists and capture the original content. ### Step 1: Initialize ``` i=0 source_file=<resolved path> ``` Copy the original to `${source_file}.0` — this is the baseline for the first revision pass. The workflow makes substantive editorial changes. Remove `user-verified: true` from `${source_file}.0` if present, and keep it absent from every generated revision. Do not remove it from the original until the user accepts a revision; applying an accepted revision revokes the prior attestation automatically. ### Step 2: Revision loop Run the following loop. **Max iterations: 5** (hard cap to prevent runaway). #### 2a. Run non-interactive revision ```bash claude -p "Revise $(basename ${source_file}).$i for flow, readability, and cohesion. Preserve all semantic content, claims, and structure. You MAY improve the title (# heading) and description frontmatter field if you s...

Details

Author
zby
Repository
zby/commonplace
Created
5 months ago
Last Updated
yesterday
Language
Python
License
CC-BY-4.0

Similar Skills

Semantically similar based on skill content — not just same category