Skip to main content
ClaudeWave
EN, English
Slash Command67.9k repo starsupdated today

workflow-claude-skills

# workflow-claude-skills This Claude Code slash command compares Anthropic's official Skills Reference documentation and changelog against the local `claude-skills.md` report in the claude-code-best-practice repository to detect drift in frontmatter fields and bundled skills. Users invoke it to surface tracking mismatches over a configurable version window, receive a structured report with detected changes, and decide whether to approve updates to the skills report before implementing them.

Install in Claude Code
Copy
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/shanraisshan/claude-code-best-practice/HEAD/.claude/commands/workflows/best-practice/workflow-claude-skills.md -o ~/.claude/commands/workflow-claude-skills.md
Then start a new Claude Code session; the slash command loads automatically.

workflow-claude-skills.md

# Workflow Changelog — Skills Report

You are a coordinator for the claude-code-best-practice project. Your job is to launch a research agent, wait for its results, and present a report about drift in the **Skills Reference** report (`best-practice/claude-skills.md`).

This workflow checks for exactly **two types of drift**:
1. **Frontmatter fields** — any field added or removed in the official docs
2. **Official bundled skills** — any bundled skill added or removed

**Versions to check:** `$ARGUMENTS` (default: 10 if empty or not a number)

This is a **read-then-report** workflow. Launch the agent, merge findings, and produce a report. Only take action if the user approves.

---

## Phase 1: Launch Research Agent

Spawn the `workflow-claude-skills-agent` with this prompt:

> Research the claude-code-best-practice project for skills report drift. Check the last $ARGUMENTS versions (default: 10).
>
> Fetch these 2 external sources:
> 1. Skills Reference: https://code.claude.com/docs/en/skills
> 2. Changelog: https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md
>
> Then read the local report (`best-practice/claude-skills.md`).
>
> Check for exactly two things:
> 1. **Frontmatter fields**: Compare the official docs' supported skill frontmatter fields against the report's Frontmatter Fields table. Flag any fields that were added or removed.
> 2. **Official bundled skills**: Compare the official docs' bundled skills list (and any new bundled skills mentioned in the changelog) against the report's official skills table. Flag any skills that were added or removed.

---

## Phase 2: Read Previous Changelog Entries

**While the agent is running**, read `changelog/best-practice/claude-skills/changelog.md` to get the last 25 entries. Parse the priority actions to identify:
- **Recurring items** — issues that appeared before and are still unresolved
- **New items** — issues appearing for the first time
- **Resolved items** — previously flagged issues now fixed

---

## Phase 3: Generate Report

**Wait for the agent to complete.** Produce a report with these sections:

1. **Frontmatter Field Changes** — Fields added or removed in official docs vs our report
2. **Official Bundled Skill Changes** — Bundled skills added or removed vs our table

End with a prioritized **Action Items** summary table. Each item must include a `Status` column showing `NEW`, `RECURRING (first seen: <date>)`, or `RESOLVED`:

```
Priority Actions:
#  | Type              | Action                                | Status
1  | New Field         | Add <field> to frontmatter table      | NEW
2  | Removed Field     | Remove <field> from table             | RECURRING (first seen: <date>)
3  | New Skill         | Add <skill> to official skills table   | NEW
4  | Removed Skill     | Remove <skill> from table             | NEW
```

Also include a **Resolved Since Last Run** section listing items from previous runs that are no longer issues.

---

## Phase 3.5: Append Summary to Changelog

**This phase is MANDATORY — always execute it before presenting the report to the user.**

Read the existing `changelog/best-practice/claude-skills/changelog.md` file, then **append** (do NOT overwrite) a new entry at the end. The entry format must be exactly:

```markdown
---

## [<YYYY-MM-DD HH:MM AM/PM PKT>] Claude Code v<VERSION>

| # | Priority | Type | Action | Status |
|---|----------|------|--------|--------|
| 1 | HIGH/MED/LOW | <type> | <action description> | <status> |
| ... | ... | ... | ... | ... |
```

**Status format — MUST use one of these three formats:**
- `COMPLETE (reason)` — action was taken and resolved successfully
- `INVALID (reason)` — finding was incorrect, not applicable, or intentional
- `ON HOLD (reason)` — action deferred, waiting on external dependency or user decision

The `(reason)` is mandatory and must briefly explain what was done or why.

**Rules for appending:**
- Always append — never overwrite or replace previous entries
- The date and time is when the command is executed in Pakistan Standard Time (PKT, UTC+5); get it by running `TZ=Asia/Karachi date "+%Y-%m-%d %I:%M %p PKT"`. The version comes from agent findings
- If `changelog/best-practice/claude-skills/changelog.md` doesn't exist or is empty, create it with the Status Legend table (see top of file) then the first entry
- Each entry is separated by `---`
- **Only include items with HIGH, MEDIUM, or LOW priority** — omit NONE priority items

---

## Phase 3.6: Update Last Updated Badge

**This phase is MANDATORY — always execute it immediately after Phase 3.5, before presenting the report.**

Update the "Last Updated" badge at the top of `best-practice/claude-skills.md`. Run `TZ=Asia/Karachi date "+%b %d, %Y %-I:%M %p PKT"` to get the time, URL-encode it (spaces to `%20`, commas to `%2C`), and replace the date portion in the badge. Also update the Claude Code version in the badge if it has changed.

**Do NOT log badge updates as action items in the changelog or report.** Badge syncing is a routine part of every run, not a finding.

---

## Phase 4: Offer to Take Action

After presenting the report (and confirming both changelog and badge were updated), ask the user:

1. **Execute all actions** — Apply all changes
2. **Execute specific actions** — User picks which numbers to execute
3. **Just save the report** — No changes

When executing:
- **New fields**: Add to the Frontmatter Fields table with correct type, required status, and description from the official docs
- **Removed fields**: Confirm with user before removing
- **New skills**: Add to the official skills table with correct #, skill name, and description
- **Removed skills**: Confirm with user before removing
- After any additions or removals, update the count in the `## Frontmatter Fields (N)` and `## ![Official](...) **(N)**` headings

---

## Critical Rules

1. **Never guess** versions or dates — use data from the agent
2. **Cross-reference field counts** — report field count must match
agent-browserSkill

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

agent-collectionsSlash Command

Update the AGENT COLLECTIONS table by researching all agent-collection repos in parallel

code-reviewerSubagent

Meticulous, constructive reviewer for correctness, clarity, security, and maintainability.

constitutional-validatorSubagent

Validates roadmap items, features, and technical decisions against the project's constitution, principles, and core values. Ensures all proposals align with the mission, established methodology, and design principles before implementation proceeds.

development-workflowsSlash Command

Update the DEVELOPMENT WORKFLOWS table by researching all 11 workflow repos in parallel

development-workflows-research-agentSubagent

Research agent that fetches GitHub repos, counts agents/skills/commands, gets star counts, and analyzes Claude Code workflow repositories

documentation-analyst-writerSubagent

Use this agent when you need to analyze existing documentation and create new or updated documentation that strictly adheres to project-specific documentation standards defined in claude.md. This agent excels at maintaining consistency with established documentation patterns, ensuring technical accuracy, and producing clear, well-structured documentation.

implementSlash Command

Execute phased implementation with validation gates