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 Compose

by ccplugins in ccplugins/awesome-claude-code-plugins

Propose a weft workflow from conversation context. An agent skill from ccplugins/awesome-claude-code-plugins.

Apache-2.0Auto-check: notes

Install Wf Compose

skills CLI
$ npx skills add ccplugins/awesome-claude-code-plugins --skill wf-compose -a claude-code

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

GitHub CLI
$ gh skill install ccplugins/awesome-claude-code-plugins wf-compose --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/ccplugins/awesome-claude-code-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/weft/skills/wf-compose .claude/skills/wf-compose && 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-compose
GitHub stars
968
Token cost
~1.4k tokens
SKILL.md length
570 words
Files
1
Skills in repo
66
Repo updated
First seen
Licence
Apache-2.0

At a glance

Propose a weft workflow from conversation context. An agent skill from ccplugins/awesome-claude-code-plugins.

  • Works in 6 steps: Gather Context → Scan Skill Registry → Gap Analysis → …
  • SKILL.md covers Arguments, Modes, Step 1: Gather Context and Step 2: Scan Skill Registry, plus 5 more sections
  • Calls git and python3

What it does

Wf Compose is an agent skill from ccplugins/awesome-claude-code-plugins. Propose a weft workflow from conversation context. Scans skills, identifies gaps, builds template with loops.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Awesome Claude Code plugins — a curated list of slash commands, subagents, MCP servers, and hooks for Claude Code. The licence is Apache-2.0.

Example prompts

  • “/wf-compose”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Bash, Read, Write, Glob, Grep

Workflow steps

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

  1. Gather Context
  2. Scan Skill Registry
  3. Gap Analysis
  4. Generate Template
  5. Present to User
  6. Save and Start

What it can do on your machine

Read from SKILL.md and the folder at commit 5bd4f16. 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:

    • Bash
    • Read
    • Write
    • Glob
    • Grep

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • python3

    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 Compose loads about 1.4k tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 570 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write, Glob, Grep

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 ccplugins/awesome-claude-code-plugins at commit 5bd4f16, republished under its Apache-2.0 licence (© ccplugins). 570 words, ~1,436 tokens.

Download SKILL.mdSave it as .claude/skills/wf-compose/SKILL.md (or your agent's skills folder).
name
wf-compose
description
Propose a weft workflow from conversation context. Scans skills, identifies gaps, builds template with loops.
allowed-tools
Bash, Read, Write, Glob, Grep
argument-hint
[description] [--from template-name]

Compose a Weft Workflow

Read the conversation context, scan available skills, identify gaps, and propose a v2 workflow template with loops and skill blocks.

Arguments

$ARGUMENTS

Modes

UsageBehavior
/wf-compose "review, fix, iterate until clean"One-shot: propose from description
/wf-compose (no args)Interactive: ask "What are you trying to accomplish?"
/wf-compose --from feature-workflowStart from existing template, modify based on context

Step 1: Gather Context

Understand what the user is trying to do:

  1. Review the recent conversation for intent (what task, what repo, what outcome).
  2. Check git state:
    bash
    git branch --show-current 2>/dev/null
git diff --stat 2>/dev/null | tail -5
  3. Check if a weft workflow is already active:
    bash
    python3 "${CLAUDE_PLUGIN_ROOT}/core/cli.py" status 2>/dev/null
  4. If --from <template> was provided, load it as the starting point:
    bash
    python3 "${CLAUDE_PLUGIN_ROOT}/core/cli.py" preview <template>

Step 2: Scan Skill Registry

Build a map of what skills are available:

  1. Read the local skills registry, if any (path varies by setup):
    bash
    cat "${CLAUDE_SKILLS_REGISTRY:-$HOME/.claude/skills-registry.json}" 2>/dev/null
  2. List weft templates:
    bash
    python3 "${CLAUDE_PLUGIN_ROOT}/core/cli.py" start
  3. Categorize skills by function (examples — substitute what you have available):
    • Review: staff-review, arch-review, code-review, differential-review
    • Fix/Polish: fix-polish, refactor, simplify
    • Test: infra-test, webapp-testing
    • Plan: aot-plan, spec-first
    • Research: perplexity, context7, research-loop
    • Deploy: deploy-service, pr-ready

Step 3: Gap Analysis

Compare what the user described against available skills:

  1. Extract skill references from the user's description (explicit names like "/staff-review" or implicit like "review code", "test it", "deploy").
  2. For each referenced skill, check if it exists in the registry.
  3. For missing skills, present options:
    Missing skill: /devils-advocate
Options:
1. Create a stub skill (I'll generate a skeleton)
2. Use /staff-review instead (similar purpose)
3. Skip this step
  4. Wait for user choice on each gap before proceeding.

Step 4: Generate Template

Build a v2 template JSON:

  1. Map each step in the user's described workflow to a template step.

  2. For each step, set:

    • name: kebab-case identifier
    • skill: the matching skill name (e.g., "/staff-review"), or null if manual
    • on_fail: "retry" for review/test steps, "block" for critical gates, "continue" for optional steps
    • guards: add logical guards (e.g., no git push before review)
    • description: one-line summary of what the step does

  3. For iterative segments (user said "until", "repeat", "loop", "iterate"):

    • Identify the loop boundary (which steps repeat)
    • Set loop_back_to on the last step of the loop, pointing to the first
    • Set max_iterations (default 3, or what the user specified)
    • Set exit_condition from the user's description (natural language)

  4. Add schema_version: 2 to the template root.

Show full SKILL.md (216 more words)Show less

Step 5: Present to User

Show the proposed workflow in two formats:

ASCII Diagram

Draw the workflow as a flow diagram showing loops:

  ┌────────────┐     ┌───────────────┐     ┌─────────────┐
  │   review    │────>│  fix-issues   │────>│  run-tests   │
  │ /staff-rev  │     │ /fix-polish   │     │              │
  └────────────┘     └───────────────┘     └──────┬──────┘
        ^                                         │
        │        ↻ until clean (max 3)            │
        └─────────────────────────────────────────┘
                          │ done
                          v
                   ┌─────────────┐
                   │    ship     │
                   │  /pr-ready  │
                   └─────────────┘

For linear segments, use a simple arrow chain:

  setup ──> plan ──> implement ──> verify
JSON Preview

Show the full template JSON, formatted for readability.

Prompt

Ask the user:

Approve this workflow? (approve / edit / cancel)
- approve: Save template and optionally start it
- edit: Describe what to change
- cancel: Discard

Step 6: Save and Start

On approve:

  1. Save the template:
    bash
    echo '<json>' | python3 "${CLAUDE_PLUGIN_ROOT}/core/cli.py" save-template
  2. Ask: "Start this workflow now? (y/n)"
  3. If yes: invoke /wf-start <template-name>

On edit:

  1. Ask what to change
  2. Modify the template
  3. Go back to Step 5 (re-present)

On cancel:

  1. Discard and confirm

Design Rules

  • Every step with a matching skill gets a skill field. This is metadata — Claude reads it from context.md and knows which skill to invoke.
  • Loops are defined by loop_back_to on the last step of the repeating segment. The state machine handles the rest.
  • exit_condition is evaluated by Claude (natural language), not by scripts. Keep conditions specific and observable: "no MEDIUM+ issues" not "code is good enough".
  • max_iterations defaults to 3. If the user says "until done" without a cap, set it to 5 and note the cap.
  • Guards should prevent premature actions: no git push before review, no deploy before tests.
  • Template names are kebab-case. If the user doesn't name it, derive from the description.

© ccplugins, Apache-2.0. 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 plugins/weft/skills/wf-compose of ccplugins/awesome-claude-code-plugins.

Open the folder on GitHubat commit 5bd4f16

Compare with similar skills

Wf Compose 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 Compose compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wf Compose this skillccplugins/awesome-claude-code-plugins968—~1.4kAutomated safety check: NotesApache-2.0
Scanwshobson/agents40k—~2.2kAutomated safety check: PassMIT
Repo Scanaffaan-m/ECC275k—~1.5kAutomated safety check: PassMIT
Repo Scanaffaan-m/ECC275k—~1.3kAutomated safety check: PassMIT
Geo Proposalsickn33/agentic-awesome-skills47k1 repos~3.2kAutomated safety check: NotesMIT
Better Proposals AutomationComposioHQ/awesome-claude-skills77k3 repos~764Automated safety check: PassNone

Similar skills

  • Scan

    wshobson/agents

    Scans the codebase to generate project-doc.md and AGENTS.md.

    40k GitHub stars~2.2k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

  • Repo Scan

    affaan-m/ECC

    固定されレビュー可能なコミットから外部の repo-scan スキルをインストールするブートストラップ用ポインター。クロススタックのソースコード資産監査を実行する前に repo-scan のインストールが必要な場合に使用する。この ECC ポインター自体は監査を実行しない。

    275k GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed

  • Repo Scan

    affaan-m/ECC

    用于从固定且可审查的提交安装外部 repo-scan 技能的引导指针。在运行跨栈源代码资产审计前需要安装 repo-scan 时使用；此 ECC 指针本身不执行审计。

    275k GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed

  • Geo Proposal

    sickn33/agentic-awesome-skills

    Auto-generate a professional, client-ready GEO service proposal from audit data.

    47k GitHub starsUsed in 1 repo~3.2k tokens
    Sales & SupportAuto-check: notes

  • Better Proposals Automation

    ComposioHQ/awesome-claude-skills

    Automate Better Proposals tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~764 tokens
    Productivity & AutomationAuto-check passed

  • Vulnerability Scanning

    sickn33/agentic-awesome-skills

    Scan systems and dependencies for CVEs and security vulnerabilities.

    47k GitHub starsUsed in 1 repo~2.8k tokens
    SecurityAuto-check passed

More from ccplugins/awesome-claude-code-plugins

All 66 skills in this repo

  • AI Meeting

    ccplugins/awesome-claude-code-plugins

    Run structured AI meetings for plans, product ideas, technical designs, business decisions, feature proposals, and strategy choices.

    968 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check: notes

  • Fastapi App

    ccplugins/awesome-claude-code-plugins

    Bootstrap a new FastAPI backend with async SQLAlchemy 2.0, asyncpg, Alembic, Pydantic v2, and no deprecated APIs.

    968 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check: notes

  • Flutter App

    ccplugins/awesome-claude-code-plugins

    Bootstrap a new Flutter mobile app with clean architecture, Riverpod, FVM-pinned SDK, current packages, and no deprecated APIs.

    968 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check: notes

  • Nextjs App

    ccplugins/awesome-claude-code-plugins

    Bootstrap a new Next.js (App Router, TypeScript) web app with current packages and no deprecated APIs.

    968 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check: notes

  • Dev Report

    ccplugins/awesome-claude-code-plugins

    Write up a coding session for a non-technical stakeholder — the context, what was built, and the engineering reasoning behind it — the way a senior engineer briefs a product manager who does not…

    968 GitHub stars~3.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Difesa Attacchi

    ccplugins/awesome-claude-code-plugins

    Aggiunge a un sito/app un agente di difesa che rileva e blocca richieste malevole (SQL injection, XSS, path traversal, brute force, bot) con rate limiting, blocklist IP e modalità lockdown che…

    968 GitHub stars~781 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Wf Compose

What does Wf Compose do?

Propose a weft workflow from conversation context. An agent skill from ccplugins/awesome-claude-code-plugins. Wf Compose is an agent skill from ccplugins/awesome-claude-code-plugins. Propose a weft workflow from conversation context.

How do I install Wf Compose in Claude Code?

Run `npx skills add ccplugins/awesome-claude-code-plugins --skill wf-compose -a claude-code`. Or copy the skill folder (plugins/weft/skills/wf-compose in ccplugins/awesome-claude-code-plugins) into .claude/skills/wf-compose in your project. Claude Code loads it when a task matches its description.

How do I install Wf Compose in Codex?

Run `npx skills add ccplugins/awesome-claude-code-plugins --skill wf-compose -a codex`. Or copy the skill folder (plugins/weft/skills/wf-compose in ccplugins/awesome-claude-code-plugins) into .agents/skills/wf-compose in your project. Codex loads it when a task matches its description.

Can I use Wf Compose 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 ccplugins/awesome-claude-code-plugins --skill wf-compose -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-compose, .gemini/skills/wf-compose, .github/skills/wf-compose and .opencode/skills/wf-compose in your project.

What does Wf Compose need to run?

Going by SKILL.md and its folder, Wf Compose needs the command-line tools its instructions call (git and python3). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash, Read, Write, Glob, Grep.

Does Wf Compose 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 Compose safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Wf Compose use?

Wf Compose is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Wf Compose use?

About 1.4k tokens (SKILL.md is roughly 5.7k 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 Compose?

Skills that share tags, products or a category with Wf Compose: Scan (wshobson/agents, 40k stars), Repo Scan (affaan-m/ECC, 275k stars), Repo Scan (affaan-m/ECC, 275k stars) and Geo Proposal (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Wf Compose?

ccplugins (a GitHub organization) maintains it in ccplugins/awesome-claude-code-plugins, which has 968 GitHub stars. The repository holds 66 skills in this directory. The repository was last updated on August 12, 2026.

Source: ccplugins/awesome-claude-code-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.