Claude Skill

upkeep-audit

Run the Upkeep repo audit locally against any repository path. Use when asked to audit a repo, check docs/spec/asset drift, or run upkeep without GitHub Actions.

LLM Mart · 0 points · 0 26 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download wei18-upkeep-skills_upkeep-audit-2642c2c.zip · 1 KB

wei18/upkeep 16 0 forks MIT Updated 7d ago

Install

skills CLI npx skills add https://github.com/wei18/Upkeep/tree/main/skills/upkeep-audit

Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install wei18-upkeep@llmmart

Git git clone https://github.com/wei18/Upkeep.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole wei18/upkeep collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Upkeep Local Audit

Run the full Upkeep audit pipeline (discovery → parallel reviewers → synthesis → HTML report) against a local repository. Output-only: the target repo is never modified.

Steps

Ensure the Upkeep checkout at ~/.cache/upkeep:
- Missing: git clone --depth 1 https://github.com/wei18/upkeep ~/.cache/upkeep
- Present: git -C ~/.cache/upkeep pull --ff-only (if the pull fails — diverged or dirty checkout — delete ~/.cache/upkeep and re-clone; it is disposable)
- Then (cd ~/.cache/upkeep && npm ci) after a fresh clone or whenever the pull changed package-lock.json (when unsure, run it — it is idempotent).
Run the audit (takes several minutes; reviewers run as parallel claude -p subprocesses — run it in the background and report progress):
```
~/.cache/upkeep/scripts/local-audit.sh <target-path> [--model M] [--rubric-lang L] [--max-turns N] [--out FILE]
```
Pass flags only when the user asked for them, with one exception: the report defaults to ./upkeep-report.html in the current working directory, so if the working directory is inside the target repo, pass --out pointing outside it (e.g. ~/upkeep-report.html) — the audit must never write into the target repo. Other defaults match the CI inputs (claude-opus-4-8, rubric en, 30 turns); --rubric-lang accepts en or zh-TW.
Summarize: the script prints the report markdown at the end. Present the findings grouped by severity (high → medium → low), each with its file path and a one-line problem statement, then give the absolute path of the generated report file (upkeep-report.html by default, or the --out path). If any reviewers failed, name them.

Requirements (tell the user what is missing instead of failing silently)

claude CLI installed and logged in (Claude Pro/Max subscription).
Node 20+, git.

Files (upkeep)

.claude-plugin

plugin.json 323 B

{
  "name": "upkeep",
  "description": "Run the Upkeep repo audit locally against any repository path — output-only drift report with evidence and severity.",
  "version": "2.1.1",
  "author": {
    "name": "Wei18"
  },
  "homepage": "https://github.com/wei18/upkeep",
  "repository": "https://github.com/wei18/upkeep"
}

SKILL.md 2.1 KB

---
name: upkeep-audit
description: Run the Upkeep repo audit locally against any repository path. Use when asked to audit a repo, check docs/spec/asset drift, or run upkeep without GitHub Actions.
---

# Upkeep Local Audit

Run the full Upkeep audit pipeline (discovery → parallel reviewers → synthesis → HTML report) against a local repository. Output-only: the target repo is never modified.

## Steps

1. **Ensure the Upkeep checkout** at `~/.cache/upkeep`:
   - Missing: `git clone --depth 1 https://github.com/wei18/upkeep ~/.cache/upkeep`
   - Present: `git -C ~/.cache/upkeep pull --ff-only` (if the pull fails — diverged or dirty checkout — delete `~/.cache/upkeep` and re-clone; it is disposable)
   - Then `(cd ~/.cache/upkeep && npm ci)` after a fresh clone or whenever the pull changed `package-lock.json` (when unsure, run it — it is idempotent).
2. **Run the audit** (takes several minutes; reviewers run as parallel `claude -p` subprocesses — run it in the background and report progress):
   ```bash
   ~/.cache/upkeep/scripts/local-audit.sh <target-path> [--model M] [--rubric-lang L] [--max-turns N] [--out FILE]
   ```
   Pass flags only when the user asked for them, with one exception: the report defaults to `./upkeep-report.html` in the current working directory, so if the working directory is inside the target repo, pass `--out` pointing outside it (e.g. `~/upkeep-report.html`) — the audit must never write into the target repo. Other defaults match the CI inputs (`claude-opus-4-8`, rubric `en`, `30` turns); `--rubric-lang` accepts `en` or `zh-TW`.
3. **Summarize**: the script prints the report markdown at the end. Present the findings grouped by severity (high → medium → low), each with its file path and a one-line problem statement, then give the absolute path of the generated report file (`upkeep-report.html` by default, or the `--out` path). If any reviewers failed, name them.

## Requirements (tell the user what is missing instead of failing silently)

- `claude` CLI installed and logged in (Claude Pro/Max subscription).
- Node 20+, git.