geronimo-iia/llm-wiki-skills/review
Claude Code and agent skill by geronimo-iia/llm-wiki-skills
- community
Checking that the SKILL.md file is still in the repository.
Build a prioritized review queue from lint findings, draft pages, and low-confidence knowledge; process items one at a time with guided decisions.
Install
npx vskill@latest install geronimo-iia/llm-wiki-skills/reviewSKILL.md
Review
Process wiki pages that need human attention: structural errors, unverified drafts, and low-confidence active pages. The queue is rebuilt from existing fields each session — no dedicated state required.
Step 1 — Discover the wiki root
Step 2 — Build the review queue
Assemble from three sources, then merge and deduplicate:
Source 1 — lint errors and warnings (highest priority):
Pages with Error findings (broken links, missing fields, unknown type) rank first — they are structurally broken, not just unreviewed.
Source 2 — draft pages:
Source 3 — low-confidence active pages:
Filter to pages where confidence < 0.4.
Priority order:
| Priority | Condition | |
|---|---|---|
| 1 — Error | wiki_lint Error finding | |
| 2 — Warning | wiki_lint Warning finding | |
| 3 — Draft | status: draft, no lint finding | |
| 4 — Low confidence | status: active, confidence < 0.4 |
Within each tier: sort by confidence ascending (least certain first), then last_updated ascending (oldest first).
If the user provided a max-items argument, cap the queue at that count.
Step 3 — Review loop
Process items one at a time. For each page:
3a. Read the page
3b. Show context
Present:
- What triggered the flag (lint finding type, draft status, or confidence value)
- Backlinks — who links to this page (load-bearing vs. orphaned)
- Last 3 commits — how recently and how often this page was touched
3c. Guide the review decision
| Decision | When | Action | |
|---|---|---|---|
| Promote | Content is correct and complete | Set status: active, raise confidence to 0.7–0.9, commit | |
| Update | Content is partially correct | Edit claims, update confidence, keep status: draft if still incomplete, commit | |
| Resolve contradiction | Page has open question from ingest | Verify conflicting claims, update claims[], remove open question, adjust confidence, commit | |
| Defer | Cannot verify now | Leave as-is, add a dated note in body; skip for this session | |
| Flag for deletion | Page is redundant or wrong | Set status: archived, lower confidence to 0.1, add superseded_by if applicable, commit |
3d. Resolve contradictions (when applicable)
When a page has an open question flagged during ingest:
- Read the source page cited in the open question (
wiki_content_read) - Compare the conflicting claims side by side
- Determine which is more authoritative (recency, source type, confidence)
- Update
claims[]— add an entry for the resolved claim with the winning source - Remove the open question from the body
- Set
confidenceto reflect the resolved state (raise if resolved, leave low if uncertain) - Write and commit
3e. Write and commit
3f. Move to the next item
Step 4 — Report
After the session ends (queue exhausted or user stops):
Key rules
- Never delete — use
status: archived+superseded_by; deletion
removes the page from backlinks and breaks graph edges
- Preserve claim history — add to
claims[], do not replace existing
entries; both the old and new versions should be visible
- Defer is valid — add a dated reason, move on; the queue rebuilds next
session from current field values
- One page at a time — finish each review decision before starting the
next; do not batch writes
- Confirm borderline promotions — if
confidencewould jump from < 0.4
to ≥ 0.7, confirm with the user before writing
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/review/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/geronimo-iia/llm-wiki-skills/review)