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 Dispatch

by changkun in 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.

MITAuto-check passedDevelopment

Install Wf Spec Dispatch

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

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

GitHub CLI
$ gh skill install changkun/wallfacer wf-spec-dispatch --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-dispatch .claude/skills/wf-spec-dispatch && 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-dispatch
GitHub stars
112
Token cost
~1.6k tokens
SKILL.md length
841 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

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.

  • Works in 7 steps: Parse arguments → Read the spec → Validate prerequisites → …
  • A design is settled and work should start — the spec must be validated and its dependencies complete
  • SKILL.md covers Step 0: Parse arguments, Step 1: Read the spec, Step 2: Validate prerequisites and Step 3: Resolve dependencies, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Wf Spec Dispatch is an agent skill from 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. Also undispatches. Use when a design is settled and work should start — the spec must be validated and its dependencies complete.

Its SKILL.md is about 1.6k 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

  • A design is settled and work should start — the spec must be validated and its dependencies complete

Example prompts

  • “/wf-spec-dispatch”

Requirements

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

Workflow steps

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

  1. Parse arguments
  2. Read the spec
  3. Validate prerequisites
  4. Resolve dependencies
  5. Execute
  6. Update spec file
  7. Summary

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:

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

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    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 Dispatch loads about 1.6k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 841 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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). 841 words, ~1,607 tokens.

Download SKILL.mdSave it as .claude/skills/wf-spec-dispatch/SKILL.md (or your agent's skills folder).
name
wf-spec-dispatch
description
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. Also undispatches. Use when a design is settled and work should start — the spec must be validated and its dependencies complete.
allowed-tools
Read, Grep, Glob, Edit, Agent, Bash(ls *), Bash(curl *)
argument-hint
<spec-file.md> [undispatch]

Dispatch Spec to Task Board

Send a validated spec to the board as a task, or undispatch a previously dispatched spec.

Step 0: Parse arguments

$ARGUMENTS has the form: <spec-file.md> [undispatch]

  • The first token is the spec file path.
  • If the second token is undispatch, perform an undispatch (cancel the linked task and clear dispatched_task_id).

Step 1: Read the spec

  1. Read the spec file in full. Parse YAML frontmatter — extract title, status, depends_on, affects, effort, dispatched_task_id.
  2. Read the spec body to use as the task prompt.

Step 2: Validate prerequisites

For dispatch:
  1. Status check — spec must be validated. If drafted, suggest /wf-spec-validate first. If stale, suggest /wf-spec-refine first.
  2. Already dispatched check — if dispatched_task_id is non-null, warn the user and stop. They must undispatch first or confirm re-dispatch.
  3. Dependency check — for each path in depends_on, read that spec's frontmatter:
    • If the dependency has status: complete, it's satisfied.
    • If the dependency has dispatched_task_id set (task in progress), note it — the board task will block on the dependency's task via DependsOn.
    • If the dependency is neither complete nor dispatched, warn: the spec has unresolved dependencies. The user can proceed (the task will block) or resolve dependencies first.
  4. Leaf check — determine if the spec is a leaf (no child directory with specs). Non-leaf specs can be dispatched, but warn the user: dispatching a parent spec means "implement this entire design as one task." If children exist, suggest dispatching the children individually instead.
For undispatch:
  1. Has dispatch link — dispatched_task_id must be non-null.
  2. Task status — check the linked task's status. If it's in_progress or committing, warn: undispatching will cancel a running task.

Step 3: Resolve dependencies

For dispatch, build the task's DependsOn list:

  1. For each spec in depends_on that has a non-null dispatched_task_id, add that task UUID to DependsOn.
  2. For dependencies that are complete (no active task), omit them from DependsOn — the work is already done.
  3. For dependencies that are neither complete nor dispatched, omit them but flag a warning — the task won't have a dependency edge for these.

Step 4: Execute

Dispatch has two implementations. Detect which applies before acting.

Default: file-based dispatch

Most repos have no task board. Dispatching then means recording the intent in the spec itself:

  1. Set status: validated if it is not already.
  2. Leave dispatched_task_id: null — there is no task to point at.
  3. Set updated to today.
  4. Commit the frontmatter change.
  5. Report what would be built and in what order, so the user (or a following /wf-spec-implement) can pick it up.
Show full SKILL.md (415 more words)Show less
When a task board with a transition API is present

Some repos expose a server that owns dispatch atomically: it creates the board task with a pre-assigned UUID, resolves dependency edges, sets the spec validated, writes dispatched_task_id, and commits the frontmatter in one transaction (a folder/non-leaf path expands into its subtree leaves and promotes drafted ancestors to validated). Detect it by probing the API; when it answers, use it and do not hand-roll task creation or edit frontmatter yourself.

Dispatch:

json
POST /api/specs/transition
{ "action": "dispatch", "paths": ["<workspace-relative spec path>"], "run": false }
  • paths takes one or more specs (batch). run: true also moves the created task to in_progress immediately; default false leaves it queued.
  • The response carries the created task UUID(s). The server has already written dispatched_task_id + status: validated and committed — you do not edit the file or commit.

Undispatch:

json
POST /api/specs/transition
{ "action": "undispatch", "paths": ["<path>"] }

The server cancels the linked task if still active, clears dispatched_task_id, resets status to validated, and commits.

If the transition endpoint fails but the task endpoints answer, fall back to POST /api/tasks/batch with one tasks entry per spec: prompt = the spec body, spec_source_path = the spec path (the server's task-done hook finds the spec through it), depends_on_refs = the resolved task UUIDs (Step 3); then edit the spec frontmatter (dispatched_task_id, updated) by hand and commit. Flag clearly that this path loses the server's atomicity: a failed task create can leave a dangling link.

Step 5: Update spec file

On the file-based path, the frontmatter edit from Step 4 is the whole of it.

With a transition API there is normally nothing to do — the server already wrote and committed dispatched_task_id, status, and updated. Only on the unreachable-server fallback do you edit the YAML frontmatter in place (changed fields only), leaving the markdown body untouched.

Step 6: Summary

Report to the user:

  • What was dispatched/undispatched and the task UUID
  • Dependency wiring: which task dependencies were resolved, which were skipped
  • Any warnings (unresolved dependencies, non-leaf dispatch, running task cancel)
  • Next steps: "Monitor on the task board" or "Dispatch dependencies first"

Guidelines

  • This skill is the bridge between designing and building. It should feel like a single action, not a multi-step process.
  • Never assume a task board exists. Probe for it; the file-based path is the default, not the degraded mode.
  • Where the transition API is present, prefer it over hand-rolling: it creates the task, sets validated + dispatched_task_id, and commits in one transaction.
  • For batch dispatch through the API, pass multiple specs in one paths array so the server wires dependencies and creates tasks together.
  • Commit the frontmatter change; do not push.

© 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-dispatch of changkun/wallfacer.

Open the folder on GitHubat commit 5b3cea1

Compare with similar skills

Wf Spec Dispatch 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 Dispatch compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wf Spec Dispatch this skillchangkun/wallfacer112—~1.6kAutomated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k59 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Vercel Composition Patterns

    supabase/supabase

    Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 59 repos~726 tokens
    DevelopmentAuto-check passed

  • 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.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • 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.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed

  • 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.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • 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.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • 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.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-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 4 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 4 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 4 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 4 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 4 days ago
    Auto-check passed

  • 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.

    112 GitHub stars~2.2k tokensUpdated 4 days ago
    Auto-check passed

Categories

Questions about Wf Spec Dispatch

What does Wf Spec Dispatch do?

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 Dispatch is an agent skill from 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.

When should I use Wf Spec Dispatch?

Wf Spec Dispatch fits situations like: A design is settled and work should start — the spec must be validated and its dependencies complete.

How do I install Wf Spec Dispatch in Claude Code?

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

How do I install Wf Spec Dispatch in Codex?

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

Can I use Wf Spec Dispatch 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-dispatch -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-dispatch, .gemini/skills/wf-spec-dispatch, .github/skills/wf-spec-dispatch and .opencode/skills/wf-spec-dispatch in your project.

What does Wf Spec Dispatch need to run?

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

Does Wf Spec Dispatch 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 Dispatch 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 Dispatch use?

Wf Spec Dispatch 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 Dispatch use?

About 1.6k tokens (SKILL.md is roughly 6.4k 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 Dispatch?

Skills that share tags, products or a category with Wf Spec Dispatch: 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 Dispatch?

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.