New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Wf Spec Review Breakdown

by changkun in changkun/wallfacer

Audit a breakdown before anyone builds it: dependency ordering, task sizing, coverage gaps, overlapping boundaries, missing tests.

MITAuto-check passedAgent Workflows

Install Wf Spec Review Breakdown

skills CLI
$ npx skills add changkun/wallfacer --skill wf-spec-review-breakdown -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install changkun/wallfacer wf-spec-review-breakdown --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ 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-breakdown .claude/skills/wf-spec-review-breakdown && rm -rf skills-src

Use ~/.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/

Facts

Skill name
wf-spec-review-breakdown
GitHub stars
112
Token cost
~1.3k tokens
SKILL.md length
645 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Audit a breakdown before anyone builds it: dependency ordering, task sizing, coverage gaps, overlapping boundaries, missing tests.

  • Works in 9 steps: Parse arguments → Load the breakdown → Check dependency correctness → …
  • Tasks that involve Test coverage
  • SKILL.md covers Step 0: Parse arguments, Step 1: Load the breakdown, Step 2: Check dependency… and Step 3: Check task sizing, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Wf Spec Review Breakdown is an agent skill from changkun/wallfacer. Audit a breakdown before anyone builds it: dependency ordering, task sizing, coverage gaps, overlapping boundaries, missing tests. Read-only; returns PASS or NEEDS REVISION. Use immediately after breakdown.

Its SKILL.md is about 1.3k 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 Agent Workflows, covering Test coverage. 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

  • Tasks that involve Test coverage

Example prompts

  • “/wf-spec-review-breakdown”

Requirements

  • Pre-approved tools (allowed-tools): Read, Grep, Glob, Agent, Bash(ls *)

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. Parse arguments
  2. Load the breakdown
  3. Check dependency correctness
  4. Check task sizing
  5. Check spec coverage
  6. Check boundary conflicts
  7. Check test completeness
  8. Verify the critical path
  9. Summary

What it can do on your machine

Read from SKILL.md and the folder at commit 9fc9f06. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Glob
    • Agent
    • Bash(ls *)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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 Breakdown loads about 1.3k tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 645 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 9fc9f06, republished under its MIT licence (© changkun). 645 words, ~1,276 tokens.

Download SKILL.mdSave it as .claude/skills/wf-spec-review-breakdown/SKILL.md (or your agent's skills folder).
name
wf-spec-review-breakdown
description
Audit a breakdown before anyone builds it: dependency ordering, task sizing, coverage gaps, overlapping boundaries, missing tests. Read-only; returns PASS or NEEDS REVISION. Use immediately after breakdown.
allowed-tools
Read, Grep, Glob, Agent, Bash(ls *)
argument-hint
<spec-file.md or task-folder/>

Review Task Breakdown

Validate a task breakdown produced by /wf-spec-breakdown before starting implementation. Catch structural issues that would cause failures mid-execution.

Step 0: Parse arguments

Extract the spec file path or task folder from the first token. If given a spec file, locate its child spec directory (sibling directory with matching name, e.g., specs/shared/visual-identity/ for visual-identity.md). If given a directory, locate the parent spec (the .md file in the containing directory whose name matches the directory).

Step 1: Load the breakdown

  1. Read the parent spec in full. Parse its YAML frontmatter to extract title, status, depends_on, affects, effort.
  2. Read every child spec file in the subdirectory. Parse each child's YAML frontmatter — extract title, status, depends_on, affects, effort, dispatched_task_id.
  3. Read specs/README.md for track context and cross-spec dependencies.

Step 2: Check dependency correctness

For each child spec's depends_on list in its YAML frontmatter:

  • Verify every path in depends_on resolves to an existing spec file.
  • Verify no self-dependency (a spec cannot list itself in depends_on).
  • Verify no circular dependencies in the DAG (topological sort must succeed).
  • Verify dependency direction: if spec B modifies a function that spec A creates, B must depend on A. Cross-reference affects lists to catch this.
  • Flag missing dependencies: if two child specs have overlapping affects paths, check whether they need ordering.
  • Verify depends_on edges that cross subtrees or tracks are intentional and the target spec exists.

Report: list of dependency issues, or "Dependencies: OK".

Step 3: Check task sizing

For each child spec, estimate scope by examining the affects list from frontmatter and the "What to do" section in the body:

  • Read each file in affects to check its size and complexity.
  • Cross-check effort (small/medium/large/xlarge) against actual scope:
    • small with 6+ files in affects is suspicious.
    • xlarge with only 1-2 files may be over-estimated.
  • Flag specs whose "What to do" has fewer than 3 steps as potentially too small (might be foldable into a sibling spec).
  • Flag specs that create new packages AND refactor existing code (should usually be split).
  • Verify leaf specs are small enough for one agent task (2-5 files, one clear goal) per the spec document model.

Report: list of sizing concerns, or "Sizing: OK".

Show full SKILL.md (282 more words)Show less

Step 4: Check spec coverage

Compare the spec's implementation plan against the task breakdown:

  • For each item in the spec (sections, bullet points, requirements), check that at least one task covers it.
  • Flag spec items with no corresponding task.
  • Flag tasks that don't trace back to any spec item (scope creep).

Report: uncovered spec items and untraceable tasks, or "Coverage: OK".

Step 5: Check boundary conflicts

For each pair of child specs that have overlapping affects paths in their frontmatter:

  • Check that their "Boundaries" sections don't overlap (both claiming to modify the same function or type).
  • Check that the later spec's "What to do" accounts for changes made by the earlier spec (follow the depends_on ordering).
  • Flag cases where two independent specs (no depends_on edge between them) share affects entries — they may conflict during parallel execution.

Report: list of boundary conflicts, or "Boundaries: OK".

Step 6: Check test completeness

For each task:

  • Verify the "Tests" section exists and is non-empty.
  • Check that test cases cover the "Goal" (not just the mechanics of "What to do").
  • Flag tasks that modify existing behavior but only test new behavior.

Report: list of test gaps, or "Tests: OK".

Step 7: Verify the critical path

Compute the critical path through the dependency graph:

  • Identify the longest chain of sequential tasks.
  • Flag if the critical path has more than 6 tasks (may indicate missing parallelism opportunities).
  • Identify tasks with no dependents that could be reordered earlier.

Report: critical path length, parallelism opportunities.

Step 8: Summary

Present a structured report:

## Breakdown Review: <spec-name>

Tasks: N total, N phases
Critical path: N tasks deep
Parallelism: up to N tasks can run concurrently

### Issues Found
- [ ] <issue description with task references>
- [ ] <issue description>

### Recommendations
- <suggestion for improvement>

### Verdict: PASS / NEEDS REVISION

If issues are found, list specific remediation steps. Do NOT modify any files — this skill is read-only. The user decides whether to revise manually or re-run /wf-spec-breakdown with feedback.

© 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-breakdown of changkun/wallfacer.

Open the folder on GitHubat commit 9fc9f06

Compare with similar skills

Wf Spec Review Breakdown 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.

Wf Spec Review Breakdown compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wf Spec Review Breakdown this skillchangkun/wallfacer112—~1.3kAutomated safety check: PassMIT
Improvefossasia/eventyay-interpretation1.6k10 repos~3.7kAutomated safety check: WarnMIT
AlignmentOvid/paad131—~4.8kAutomated safety check: PassMIT
Review Workpeterkrueck/Claude-Code-Development-Kit1.4k—~3.3kAutomated safety check: PassMIT
Review SwarmDimillian/Skills4k—~1.6kAutomated safety check: PassMIT
Review Swarmsickn33/agentic-awesome-skills47k1 repos~1.9kAutomated safety check: PassMIT

Similar skills

  • Improve

    fossasia/eventyay-interpretation

    Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute.

    1.6k GitHub starsUsed in 10 repos~3.7k tokens
    Agent WorkflowsAuto-check: warnings

  • Alignment

    Ovid/paad

    A skill your agent uses when verifying that requirements/specs/PRDs and their implementation plans match — before starting work, after a spec or plan update, or when suspecting coverage gaps, scope…

    131 GitHub stars~4.8k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Review Work

    peterkrueck/Claude-Code-Development-Kit

    Review uncommitted code changes using parallel Claude sub-agents (Bug Hunter, Rules Auditor, optional Architect).

    1.4k GitHub stars~3.3k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • Review Swarm

    Dimillian/Skills

    Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test…

    4k GitHub stars~1.6k tokensUpdated 6 mo ago
    Agent WorkflowsAuto-check passed

  • Review Swarm

    sickn33/agentic-awesome-skills

    Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test…

    47k GitHub starsUsed in 1 repo~1.9k tokens
    Agent WorkflowsAuto-check passed

  • Write Plan

    jackfranklin/dotfiles

    Write a right-sized, reviewable implementation plan as a series of focused tasks, with exact file paths, interface contracts, behavioral test specifications, and verification commands.

    255 GitHub stars~3.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from changkun/wallfacer

All 14 skills in this repo

  • Wf 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.

    112 GitHub stars~2.6k tokensUpdated 2 days ago
    Auto-check passed

  • Wf Spec Create

    changkun/wallfacer

    Write a new spec from scratch when none exists for the idea yet.

    112 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed

  • 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.

    112 GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check passed

  • 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…

    112 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed

  • Wf Spec Report

    changkun/wallfacer

    Survey the whole spec tree: what is complete, in progress, blocked, and actionable next.

    112 GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check passed

  • Wf Spec Review Impl

    changkun/wallfacer

    Read-only verdict on whether an implementation meets its spec: each acceptance criterion classified, unintended changes flagged, test coverage checked.

    112 GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Wf Spec Review Breakdown

What does Wf Spec Review Breakdown do?

Audit a breakdown before anyone builds it: dependency ordering, task sizing, coverage gaps, overlapping boundaries, missing tests. Wf Spec Review Breakdown is an agent skill from changkun/wallfacer. Audit a breakdown before anyone builds it: dependency ordering, task sizing, coverage gaps, overlapping boundaries, missing tests.

When should I use Wf Spec Review Breakdown?

Wf Spec Review Breakdown fits situations like: tasks that involve Test coverage.

How do I install Wf Spec Review Breakdown in Claude Code?

Run `npx skills add changkun/wallfacer --skill wf-spec-review-breakdown -a claude-code`. Or copy the skill folder (.claude/skills/wf-spec-review-breakdown in changkun/wallfacer) into .claude/skills/wf-spec-review-breakdown in your project. Claude Code loads it when a task matches its description.

How do I install Wf Spec Review Breakdown in Codex?

Run `npx skills add changkun/wallfacer --skill wf-spec-review-breakdown -a codex`. Or copy the skill folder (.claude/skills/wf-spec-review-breakdown in changkun/wallfacer) into .agents/skills/wf-spec-review-breakdown in your project. Codex loads it when a task matches its description.

Can I use Wf Spec Review Breakdown 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-breakdown -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-breakdown, .gemini/skills/wf-spec-review-breakdown, .github/skills/wf-spec-review-breakdown and .opencode/skills/wf-spec-review-breakdown in your project.

What does Wf Spec Review Breakdown need to run?

SKILL.md names no scripts, command-line tools or credentials: Wf Spec Review Breakdown is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep, Glob, Agent, Bash(ls *).

Does Wf Spec Review Breakdown access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Wf Spec Review Breakdown 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 Breakdown use?

Wf Spec Review Breakdown 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 Breakdown use?

About 1.3k tokens (SKILL.md is roughly 5.1k 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 Breakdown?

Skills that share tags, products or a category with Wf Spec Review Breakdown: Improve (fossasia/eventyay-interpretation, 1.6k stars), Alignment (Ovid/paad, 131 stars), Review Work (peterkrueck/Claude-Code-Development-Kit, 1.4k stars) and Review Swarm (Dimillian/Skills, 4k 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 Breakdown?

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 9, 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.