Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
Structural lint over the spec tree — required frontmatter fields, valid status and effort values, track location, DAG acyclicity, dispatch consistency, orphans, status consistency.
Install Wf Spec Validate
$ npx skills add changkun/wallfacer --skill wf-spec-validate -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install changkun/wallfacer wf-spec-validate --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-validate .claude/skills/wf-spec-validate && 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-validate" agent skill from https://github.com/changkun/wallfacer/tree/main/.claude/skills/wf-spec-validate into .claude/skills/wf-spec-validate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wf-spec-validate", 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-validateType 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-validate -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install changkun/wallfacer wf-spec-validate --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-validate .agents/skills/wf-spec-validate && 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-validate" agent skill from https://github.com/changkun/wallfacer/tree/main/.claude/skills/wf-spec-validate into .agents/skills/wf-spec-validate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wf-spec-validate", 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-validate -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install changkun/wallfacer wf-spec-validate --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-validate .cursor/skills/wf-spec-validate && 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-validate" agent skill from https://github.com/changkun/wallfacer/tree/main/.claude/skills/wf-spec-validate into .cursor/skills/wf-spec-validate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wf-spec-validate", 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-validate--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-validate -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install changkun/wallfacer wf-spec-validate --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-validate .gemini/skills/wf-spec-validate && 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-validate" agent skill from https://github.com/changkun/wallfacer/tree/main/.claude/skills/wf-spec-validate into .gemini/skills/wf-spec-validate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wf-spec-validate", 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-validateInstalls 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-validate -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-validate .github/skills/wf-spec-validate && 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-validate" agent skill from https://github.com/changkun/wallfacer/tree/main/.claude/skills/wf-spec-validate into .github/skills/wf-spec-validate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wf-spec-validate", 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-validate -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-validate --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-validate .opencode/skills/wf-spec-validate && 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-validate" agent skill from https://github.com/changkun/wallfacer/tree/main/.claude/skills/wf-spec-validate into .opencode/skills/wf-spec-validate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wf-spec-validate", 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-validate- GitHub stars
- 112
- Token cost
- ~2.2k tokens
- SKILL.md length
- 1,072 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
Structural lint over the spec tree — required frontmatter fields, valid status and effort values, track location, DAG acyclicity, dispatch consistency, orphans, status consistency.
- Works in 5 steps: Parse arguments → Discover all specs → Per-spec validation → …
- Check the tree is well-formed
- SKILL.md covers Step 0: Parse arguments, Step 1: Discover all specs, Step 2: Per-spec validation and Step 3: Cross-spec validation…, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Wf Spec Validate is an agent skill from 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. Read-only; reports problems and fixes nothing. Use to check the tree is well-formed; use report for what the specs say about progress.
Its SKILL.md is about 2.2k 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 Development. 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
- Check the tree is well-formed
- Use report for what the specs say about progress
Example prompts
- “/wf-spec-validate”
Requirements
- Pre-approved tools (allowed-tools): Read, Grep, Glob, Bash(ls *)
Workflow steps
5 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 these tools, so the agent can use them without asking each time:
ReadGrepGlobBash(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 Validate loads about 2.2k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 1,072 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). 1,072 words, ~2,158 tokens.
Download SKILL.mdSave it as
.claude/skills/wf-spec-validate/SKILL.md (or your agent's skills folder).- name
- wf-spec-validate
- description
- Structural lint over the spec tree — required frontmatter fields, valid status and effort values, track location, DAG acyclicity, dispatch consistency, orphans, status consistency. Read-only; reports problems and fixes nothing. Use to check the tree is well-formed; use report for what the specs say about progress.
- allowed-tools
- Read, Grep, Glob, Bash(ls *)
- argument-hint
- spec-file.md
Validate Specs
Run structural validation on spec documents against the repo's document model
— a document-model spec under specs/, an internals doc describing how specs
are parsed, or, failing both, the conventions below. If a specific spec file is given as
$ARGUMENTS, validate only that spec (and run cross-spec checks it
participates in). Otherwise, validate the entire spec tree.
Step 0: Parse arguments
If an argument is provided, treat it as a single spec file to validate.
Otherwise, validate all specs under specs/.
Step 1: Discover all specs
- Glob for all spec files recursively:
specs/**/*.md(excluding README.md and any non-spec markdown files like changelogs). - For each spec file, parse YAML frontmatter between
---fences. Extract:title,status,depends_on,affects,effort,created,updated,author,dispatched_task_id. - Determine leaf vs non-leaf: a spec is non-leaf if a subdirectory with the
same name (without
.md) exists and contains at least one child spec. - Build the full spec tree (parent-child from filesystem) and the dependency
DAG (from
depends_onedges).
Step 2: Per-spec validation
For each spec, check these rules. Classify each finding as error or
warning per the severity column.
Required fields (error)
title, status, effort, created, updated, author must all be present in
the frontmatter. Report each missing field. (track may be a frontmatter field or
derived from the path, depending on the repo's layout; see Valid track.)
Valid status (error)
status must be one of: vague, drafted, validated, testing, complete,
stale, archived — the seven lifecycle states. testing
is the transient drift-verdict state between validated and complete; a spec in
testing is valid (not an error), though a long-lived testing carrying a
testing_pending reason is worth a warning. The server may also set the optional
fields implementation_commit (base..tip, present during testing) and
testing_pending (a reason string when the drift tester failed); both are valid.
Valid track (error)
Grouping and ordering are independent axes, and they compose —
specs/local/003-live-serve.md is grouped by directory and numbered. Check
each separately; never infer one from the other, and never decide a single
layout for the whole repo from a majority vote.
Grouping. Every spec must have a track from exactly one source:
- A directory under
specs/supplies it — the segment immediately afterspecs/. Atrack:key that merely restates the directory is a removable no-op. - A spec sitting directly under
specs/must carry atrack:frontmatter field. A spec with neither is an error.
Ordering. An NNN- filename prefix is an optional, per-directory reading
order. Judge it within each directory, never across the tree:
- A directory whose specs are numbered should number all of them; flag an unnumbered straggler.
- Flag duplicate numbers inside one directory. The same number in two different directories is fine — they are separate number spaces.
- A directory with no numbering at all is not an error. Do not ask for numbers that were never adopted.
- An archived spec keeps the number it had (
specs/.archive/…/042-foo.md), sodepends_onpaths pointing at it still resolve.
Numbers are never the dependency order. That is depends_on, checked below.
Valid effort (error)
effort must be one of: small, medium, large, xlarge.
Date format (error)
created and updated must be valid ISO dates (YYYY-MM-DD). updated must
be greater than or equal to created.
Dispatch consistency (error)
Non-leaf specs must have dispatched_task_id: null (or absent). Leaf specs
may have null or a valid UUID.
depends_on targets exist (error)
Every path in depends_on must resolve to an existing spec file relative to
the repository root.
No self-dependency (error)
A spec must not appear in its own depends_on list.
affects paths exist (warning)
Every path in affects should resolve to an existing file or directory in the
codebase. Only a warning because code may not exist yet for vague/drafted
specs. Suppressed for archived specs — deleted paths are not actionable.
Body not empty (warning)
Specs with status beyond vague should have meaningful content below the
frontmatter (more than just a title heading). Suppressed for archived specs —
a stub with only frontmatter is valid.
Show full SKILL.md (413 more words)Show less
Step 3: Cross-spec validation (tree-wide)
Run these checks across the full spec tree.
DAG is acyclic (error)
Perform a topological sort on the depends_on graph. If a cycle is detected,
report the full cycle path (e.g., A -> B -> C -> A).
No orphan directories (warning)
A <name>/ subdirectory under a spec track should have a corresponding
<name>.md parent spec file in the same directory.
No orphan specs (warning)
A <name>.md file that has a <name>/ subdirectory should have at least one
child spec inside that directory.
Status consistency (warning)
A complete non-leaf spec should not have incomplete leaves in its subtree.
Check recursively: if any leaf in the subtree has a status other than
complete, warn. Skipped when the non-leaf is archived — the subtree is
considered below glass regardless of leaf states.
Stale propagation (warning)
If a spec is stale, check all specs that list it in their depends_on.
Those that are still validated should be flagged for review — their
assumptions about the stale spec may no longer hold. Does not fire for
archived dependencies — a validated spec depending on an archived spec
receives a dependency-is-archived advisory note instead (see below).
Track location (warning)
Where a spec sits in a track directory, warn if it also carries a track: key —
the directory already supplies it and the loader ignores the field. Where a spec
sits directly under specs/, there is no directory to cross-check, so this
warning does not apply; a missing track: there is the error above.
dependency-is-archived (warning)
A live spec whose depends_on includes an archived spec. Advisory only —
recommend removing the edge or documenting why it still matters. Does not
count as a stale-propagation warning.
Unique dispatches (error)
No two specs may share the same non-null dispatched_task_id value. Collect
all dispatched_task_id values and report duplicates.
Step 4: Generate report
Present findings grouped by severity, then by spec:
## Spec Validation Report
Specs scanned: N
Errors: N
Warnings: N
### Errors
#### specs/shared/sandbox-backends.md
- [error] Missing required field: author
- [error] depends_on target does not exist: specs/shared/nonexistent.md
#### specs/local/foo.md
- [error] Invalid status: "wip" (must be vague|drafted|validated|testing|complete|stale|archived)
### Cross-Spec Errors
- [error] Cycle detected: A.md -> B.md -> C.md -> A.md
- [error] Duplicate dispatched_task_id "abc-123": specs/a.md, specs/b.md
### Warnings
#### specs/cloud/bar.md
- [warning] affects path does not exist: internal/cloud/bar.go
- [warning] Body is empty for a "drafted" spec
### Cross-Spec Warnings
- [warning] Orphan directory: specs/shared/old-feature/ has no parent spec
- [warning] Stale propagation: specs/shared/api.md is stale, but
specs/local/client.md (validated) depends on it
### Verdict: PASS / N errors, M warningsIf there are zero errors, the verdict is PASS. If there are errors, list the count. Warnings alone do not cause a failure.
Notes
- This skill is read-only. It does not modify any files.
- When validating a single spec (
$ARGUMENTSprovided), still run cross-spec checks that involve that spec (itsdepends_ontargets, specs that depend on it, cycle detection through it). - Specs without YAML frontmatter are reported as having all required fields missing — they may be legacy specs that predate the document model.
- When the repo implements its own spec validator, these rules mirror it. Report a disagreement rather than silently preferring one side.
© 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-validate of changkun/wallfacer.
Open the folder on GitHubat commit 5b3cea1
Compare with similar skills
Wf Spec Validate 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 Validate this skillchangkun/wallfacer | 112 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Vercel Composition Patternssupabase/supabase | 111k | 59 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
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 Review Impl
changkun/wallfacer
Read-only verdict on whether an implementation meets its spec: each acceptance criterion classified, unintended changes flagged, test coverage checked.
Related
Categories
Questions about Wf Spec Validate
What does Wf Spec Validate do?
Structural lint over the spec tree — required frontmatter fields, valid status and effort values, track location, DAG acyclicity, dispatch consistency, orphans, status consistency. Wf Spec Validate is an agent skill from 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.
When should I use Wf Spec Validate?
Wf Spec Validate fits situations like: check the tree is well-formed; use report for what the specs say about progress.
How do I install Wf Spec Validate in Claude Code?
Run `npx skills add changkun/wallfacer --skill wf-spec-validate -a claude-code`. Or copy the skill folder (.claude/skills/wf-spec-validate in changkun/wallfacer) into .claude/skills/wf-spec-validate in your project. Claude Code loads it when a task matches its description.
How do I install Wf Spec Validate in Codex?
Run `npx skills add changkun/wallfacer --skill wf-spec-validate -a codex`. Or copy the skill folder (.claude/skills/wf-spec-validate in changkun/wallfacer) into .agents/skills/wf-spec-validate in your project. Codex loads it when a task matches its description.
Can I use Wf Spec Validate 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-validate -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-validate, .gemini/skills/wf-spec-validate, .github/skills/wf-spec-validate and .opencode/skills/wf-spec-validate in your project.
What does Wf Spec Validate need to run?
SKILL.md names no scripts, command-line tools or credentials: Wf Spec Validate is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep, Glob, Bash(ls *).
Does Wf Spec Validate 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 Validate 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 Validate use?
Wf Spec Validate 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 Validate use?
About 2.2k tokens (SKILL.md is roughly 8.6k 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 Validate?
Skills that share tags, products or a category with Wf Spec Validate: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Wf Spec Validate?
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.