nearform/unwind/uw-verify

Claude Code and agent skill by nearform/unwind

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use after layer analysis to detect gaps in documentation. Runs a deterministic coverage diff and outputs a work list for uw-complete.

Install

npx vskill@latest install nearform/unwind/uw-verify

SKILL.md

Verifying Layer Documentation

Purpose: Detect gaps between documentation and source code. Output is a work list for the next skill to fix.

This is now a deterministic check. Completeness is verified by set arithmetic (manifest − docs), not a subjective LLM comparison. The scanner already knows the ground-truth set of items per layer; this skill diffs that against what the docs actually contain (matched by anchor id, then by name).

Output:

  • docs/unwind/.cache/coverage/{layer}.json - per-layer coverage report
  • docs/unwind/layers/{layer}/gaps.md - missing items work list (only when gaps exist)

Process

Step 1: Run the Coverage Verifier
bash
# Locate the installed Unwind plugin, then load the core helper.
# $0/BASH_SOURCE are unreliable under `bash -c`, so glob the install cache.
UNWIND_PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-${UNWIND_PLUGIN_ROOT:-}}"
[ -f "$UNWIND_PLUGIN_ROOT/skills/scripts/_resolve-plugin-root.sh" ] || \
UNWIND_PLUGIN_ROOT="$(ls -dt "$HOME"/.claude/plugins/cache/*/unwind/*/ 2>/dev/null | head -1)"
source "${UNWIND_PLUGIN_ROOT%/}/skills/scripts/_resolve-plugin-root.sh"
ensure_unwind_core || echo "core unavailable — using legacy LLM gap detection"
node "$UNWIND_PLUGIN_ROOT/skills/scripts/verify-coverage.mjs" "$(pwd)"

The script:

  1. Loads docs/unwind/.cache/scan-manifest.json (the ground-truth candidate set).
  2. Reads every section .md under each docs/unwind/layers/{layer}/ folder and

extracts documented item ids (from <!-- id: ... --> anchors, then fuzzy by name).

  1. Diffs them: missing = in source, not in docs; extra = documented but

not in scan (flagged for review — may be dynamic or stale).

  1. Writes coverage/{layer}.json and a gaps.md work list for any layer with

missing items.

Step 2: Summarize

Report the per-layer coverage table the script prints (covered/total = pct%), and point the user/orchestrator at the generated gaps.md files. Then hand off to uw-complete to fill them.

Output Format (generated gaps.md)

markdown
# {layer} Documentation Gaps
> Generated by verify-coverage. Coverage: 36/37 (97.3%).
## Missing Items
### users
-**Type:** table
-**Location:** src/db/schema.ts:12-34
-**Id:** `table:src/db/schema.ts:users`

uw-complete reads this verbatim, documents each item under the correct section using the anchor-id heading format, and deletes gaps.md.

Legacy Fallback (no @unwind/core)

When the deterministic core is unavailable (no Node/pnpm, or build failed), fall back to the subjective comparison: for each layer, read the docs and the source entry points from architecture.md, build the two item lists by hand, and write the gaps the LLM finds to docs/unwind/layers/{layer}/gaps.md in the same format. This is slower and not reproducible — it exists only so the plugin still functions without the deterministic engine.

Next Step — continue or pause?

The branch depends on the coverage table just printed:

  • Any layer < 100% (gaps.md written) → next is unwind:uw-complete to fill them.
  • Every layer 100% → analysis is done → next is unwind:uw-plan.

Use AskUserQuestion to confirm:

  • Continue (recommended) — invoke unwind:uw-complete (gaps remain) or

unwind:uw-plan (100%).

  • Pause here — stop and resume later.

Act in the same turn; if they pause, tell them how to resume: "Run `unwind:uw-complete` (type `/uw-complete`) to fill gaps, or `unwind:uw-plan` if coverage is already 100%."

Pipeline: scan → analyze → verify ✓ → complete → grill → plan → dashboard.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
11
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. 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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/nearform/unwind/uw-verify/badge)](https://verified-skill.com/skills/nearform/unwind/uw-verify)

Something wrong with this skill or its page? Tell us.