Evaluate PR Tests
dotnet/maui
Reviews the tests added in a pull request for fix coverage, quality, edge cases and test type, and recommends lighter test types where they would do.
Read-only verdict on whether an implementation meets its spec: each acceptance criterion classified, unintended changes flagged, test coverage checked.
Install Wf Spec Review Impl
$ npx skills add changkun/wallfacer --skill wf-spec-review-impl -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install changkun/wallfacer wf-spec-review-impl --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/changkun/wallfacer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/wf-spec-review-impl .claude/skills/wf-spec-review-impl && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "wf-spec-review-impl" agent skill from https://github.com/changkun/wallfacer/tree/main/.claude/skills/wf-spec-review-impl into .claude/skills/wf-spec-review-impl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wf-spec-review-impl", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/changkun/wallfacer/tree/main/.claude/skills/wf-spec-review-implType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add changkun/wallfacer --skill wf-spec-review-impl -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install changkun/wallfacer wf-spec-review-impl --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/changkun/wallfacer.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/wf-spec-review-impl .agents/skills/wf-spec-review-impl && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "wf-spec-review-impl" agent skill from https://github.com/changkun/wallfacer/tree/main/.claude/skills/wf-spec-review-impl into .agents/skills/wf-spec-review-impl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wf-spec-review-impl", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add changkun/wallfacer --skill wf-spec-review-impl -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install changkun/wallfacer wf-spec-review-impl --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/changkun/wallfacer.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/wf-spec-review-impl .cursor/skills/wf-spec-review-impl && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "wf-spec-review-impl" agent skill from https://github.com/changkun/wallfacer/tree/main/.claude/skills/wf-spec-review-impl into .cursor/skills/wf-spec-review-impl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wf-spec-review-impl", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/changkun/wallfacer.git --path .claude/skills/wf-spec-review-impl--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add changkun/wallfacer --skill wf-spec-review-impl -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install changkun/wallfacer wf-spec-review-impl --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/changkun/wallfacer.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/wf-spec-review-impl .gemini/skills/wf-spec-review-impl && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "wf-spec-review-impl" agent skill from https://github.com/changkun/wallfacer/tree/main/.claude/skills/wf-spec-review-impl into .gemini/skills/wf-spec-review-impl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wf-spec-review-impl", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install changkun/wallfacer wf-spec-review-implInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add changkun/wallfacer --skill wf-spec-review-impl -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/changkun/wallfacer.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/wf-spec-review-impl .github/skills/wf-spec-review-impl && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "wf-spec-review-impl" agent skill from https://github.com/changkun/wallfacer/tree/main/.claude/skills/wf-spec-review-impl into .github/skills/wf-spec-review-impl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wf-spec-review-impl", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add changkun/wallfacer --skill wf-spec-review-impl -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install changkun/wallfacer wf-spec-review-impl --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/changkun/wallfacer.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/wf-spec-review-impl .opencode/skills/wf-spec-review-impl && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "wf-spec-review-impl" agent skill from https://github.com/changkun/wallfacer/tree/main/.claude/skills/wf-spec-review-impl into .opencode/skills/wf-spec-review-impl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wf-spec-review-impl", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
wf-spec-review-impl- GitHub stars
- 112
- Token cost
- ~1.1k tokens
- SKILL.md length
- 518 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
Read-only verdict on whether an implementation meets its spec: each acceptance criterion classified, unintended changes flagged, test coverage checked.
- Works in 9 steps: Parse arguments → Load the requirements → Load the implementation → …
- Judge finished work
- SKILL.md covers Step 0: Parse arguments, Step 1: Load the requirements, Step 2: Load the implementation and Step 3: Check acceptance…, plus 5 more sections
- Calls git
What it does
Wf Spec Review Impl is an agent skill from changkun/wallfacer. Read-only verdict on whether an implementation meets its spec: each acceptance criterion classified, unintended changes flagged, test coverage checked. Writes nothing; returns COMPLETE, INCOMPLETE, or NEEDS FIXES. Use to judge finished work; use drift to record that judgment on the spec, wrapup to close the spec out.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Testing & QA, covering Test coverage. It works with Git. The repository describes itself as: Chat, specs, tasks, and code. An autonomous engineering platform. Full autonomy when you trust it. Full control when you don't. The licence is MIT.
When your agent uses it
- Judge finished work
- Use drift to record that judgment on the spec
- Wrapup to close the spec out
Example prompts
- “/wf-spec-review-impl”
Workflow steps
9 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 5b3cea1. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Wf Spec Review Impl loads about 1.1k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 518 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from changkun/wallfacer at commit 5b3cea1, republished under its MIT licence (© changkun). 518 words, ~1,107 tokens.
Download SKILL.mdSave it as
.claude/skills/wf-spec-review-impl/SKILL.md (or your agent's skills folder).- name
- wf-spec-review-impl
- description
- Read-only verdict on whether an implementation meets its spec: each acceptance criterion classified, unintended changes flagged, test coverage checked. Writes nothing; returns COMPLETE, INCOMPLETE, or NEEDS FIXES. Use to judge finished work; use drift to record that judgment on the spec, wrapup to close the spec out.
- argument-hint
- <spec-file.md or task-file.md> [commit-range]
Review Implementation Against Spec
Compare what was actually implemented against what the spec or task asked for. Catch deviations, missed requirements, and unintended side effects.
Step 0: Parse arguments
Extract the spec or task file path from the first token. Optionally accept a
commit range (e.g., abc123..HEAD) as the second token.
If no commit range is given, infer it: find the commit that added/modified the spec's task breakdown or the commit tagged in the task's status change to "Done".
Step 1: Load the requirements
- Read the spec or task file in full. Parse YAML frontmatter to extract
title,status,depends_on,affects,effort. - Extract acceptance criteria, "What to do" steps, "Tests" requirements, and "Boundaries" constraints from the body.
- Use the
affectslist from frontmatter as the expected set of files that should be modified by this implementation. - If reviewing a full spec (non-leaf), read all child spec files in the subdirectory and aggregate requirements recursively.
Step 2: Load the implementation
- Get the diff for the commit range:
git diff <range> --statfor file list, thengit diff <range>for full changes. - Get the commit messages:
git log <range> --onelinefor the narrative. - Group changes by file to understand what was touched.
Step 3: Check acceptance criteria
For each acceptance criterion or "What to do" step:
- Search the diff for evidence that it was implemented.
- Classify as: Implemented, Partially implemented, Not implemented, or Cannot determine.
- For "Partially implemented", explain what's missing.
Report: checklist of criteria with status.
Step 4: Check for unintended changes
Compare files touched in the diff against the affects list from frontmatter
and files listed in the spec body's "What to do" section:
- Flag files modified that aren't in
affectsor mentioned in "What to do". - For each unexpected file, read the diff hunk and assess whether the change is:
- Necessary (e.g., import added by a refactor)
- Cleanup (formatting, dead code removal)
- Scope creep (new behavior not in the spec)
- Regression risk (modifying unrelated logic)
Report: list of unexpected changes with assessment.
Show full SKILL.md (178 more words)Show less
Step 5: Check test coverage
For each "Tests" requirement in the spec/task:
- Search for a matching test function in the diff or codebase.
- Verify the test actually tests what the requirement asks for (not just that a test with a similar name exists).
- Flag requirements with no corresponding test.
- Discover and run the affected repository's documented test command.
Report: test coverage against requirements.
Step 6: Check boundary compliance
For each "Boundaries" constraint ("do NOT change X"):
- Search the diff for changes to the forbidden area.
- Flag violations with the specific diff hunk.
Report: boundary violations, or "Boundaries: respected".
Step 7: Check documentation
If the spec or task mentions documentation updates:
- Verify the relevant doc files were modified in the diff.
- Check that new API routes, env vars, or CLI flags appear in the docs.
- Cross-reference repository instructions and public documentation for consistency.
Report: documentation gaps, or "Docs: OK".
Step 8: Summary
Present a structured report:
## Implementation Review: <spec/task name>
Commits: N commits, M files changed, +A/-D lines
Commit range: <range>
### Acceptance Criteria
- [x] <criterion> — implemented in <file>
- [ ] <criterion> — NOT implemented
- [~] <criterion> — partial: <what's missing>
### Unintended Changes
- <file>: <assessment>
### Test Coverage
- [x] <requirement> — covered by TestFoo
- [ ] <requirement> — NO TEST
### Boundary Compliance
- OK / <violations>
### Documentation
- OK / <gaps>
### Verdict: COMPLETE / INCOMPLETE / NEEDS FIXESDo NOT modify any files. This skill is read-only. If issues are found, list specific remediation steps for the user to act on.
© changkun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/wf-spec-review-impl of changkun/wallfacer.
Open the folder on GitHubat commit 5b3cea1
Compare with similar skills
Wf Spec Review Impl next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Wf Spec Review Impl this skillchangkun/wallfacer | 112 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Evaluate PR Testsdotnet/maui | 23k | — | ~2.9k | Automated safety check: Pass | MIT | |
| Test RoadmapOvid/paad | 131 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Test Writer for Changed Codeposhan0126/dotclaude | 871 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Write TestsNeoLabHQ/context-engineering-kit | 1.7k | — | ~2k | Automated safety check: Pass | GPL-3.0 | |
| Reviewatelier-fashion/adlc-toolkit | 171 | — | ~1.9k | Automated safety check: Pass | MIT |
Similar skills
- Official
Test Roadmap
Ovid/paad
EXPERIMENTAL. An agent skill from Ovid/paad.
Test Writer for Changed Code
poshan0126/dotclaude
Writes tests for newly added or changed code by reading the git diff, mapping every code path and writing one-assertion tests that match the project's conventions.
Write Tests
NeoLabHQ/context-engineering-kit
Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked changes, or the latest commit if everything is committed).
Review
atelier-fashion/adlc-toolkit
Multi-agent code review covering correctness, quality, architecture, test coverage, and security
Stryker JS
mizchi/skills
Introduce StrykerJS mutation testing or assess JavaScript/TypeScript test quality.
More from changkun/wallfacer
All 14 skills in this repoWf Spec Breakdown
changkun/wallfacer
Split one spec into children — sub-design specs when questions are still open, or implementation-ready leaves when the plan is clear.
Wf Spec Create
changkun/wallfacer
Write a new spec from scratch when none exists for the idea yet.
Wf Spec Dispatch
changkun/wallfacer
Mark a validated spec ready to build and resolve its dependency wiring; where a task board with a transition API is present, create the linked task atomically.
Wf Spec Drive
changkun/wallfacer
Run the whole lifecycle for one spec, calling the other skills in order and advancing one legal transition at a time until it reaches a target state (default complete), stopping to ask at…
Wf Spec Report
changkun/wallfacer
Survey the whole spec tree: what is complete, in progress, blocked, and actionable next.
Wf Spec Validate
changkun/wallfacer
Structural lint over the spec tree — required frontmatter fields, valid status and effort values, track location, DAG acyclicity, dispatch consistency, orphans, status consistency.
Related
Works with
Categories
Questions about Wf Spec Review Impl
What does Wf Spec Review Impl do?
Read-only verdict on whether an implementation meets its spec: each acceptance criterion classified, unintended changes flagged, test coverage checked. Wf Spec Review Impl is an agent skill from changkun/wallfacer. Read-only verdict on whether an implementation meets its spec: each acceptance criterion classified, unintended changes flagged, test coverage checked.
When should I use Wf Spec Review Impl?
Wf Spec Review Impl fits situations like: judge finished work; use drift to record that judgment on the spec; wrapup to close the spec out.
How do I install Wf Spec Review Impl in Claude Code?
Run `npx skills add changkun/wallfacer --skill wf-spec-review-impl -a claude-code`. Or copy the skill folder (.claude/skills/wf-spec-review-impl in changkun/wallfacer) into .claude/skills/wf-spec-review-impl in your project. Claude Code loads it when a task matches its description.
How do I install Wf Spec Review Impl in Codex?
Run `npx skills add changkun/wallfacer --skill wf-spec-review-impl -a codex`. Or copy the skill folder (.claude/skills/wf-spec-review-impl in changkun/wallfacer) into .agents/skills/wf-spec-review-impl in your project. Codex loads it when a task matches its description.
Can I use Wf Spec Review Impl in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add changkun/wallfacer --skill wf-spec-review-impl -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wf-spec-review-impl, .gemini/skills/wf-spec-review-impl, .github/skills/wf-spec-review-impl and .opencode/skills/wf-spec-review-impl in your project.
What does Wf Spec Review Impl need to run?
Going by SKILL.md and its folder, Wf Spec Review Impl needs the command-line tools its instructions call (git).
Does Wf Spec Review Impl access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Wf Spec Review Impl safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Wf Spec Review Impl use?
Wf Spec Review Impl is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Wf Spec Review Impl use?
About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Wf Spec Review Impl?
Skills that share tags, products or a category with Wf Spec Review Impl: Evaluate PR Tests (dotnet/maui, 23k stars), Test Roadmap (Ovid/paad, 131 stars), Test Writer for Changed Code (poshan0126/dotclaude, 871 stars) and Write Tests (NeoLabHQ/context-engineering-kit, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Wf Spec Review Impl?
changkun (a GitHub user) maintains it in changkun/wallfacer, which has 112 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 4, 2026.
Source: changkun/wallfacer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.