Borrowing it
Nothing to install: this file belongs to Rito-w/claude-code-best-practice-zh. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Rito-w/claude-code-best-practice-zh/main/.claude/commands/workflows/skill-collections.mdgit clone --depth 1 https://github.com/Rito-w/claude-code-best-practice-zhWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/rito-w/claude-code-best-practice-zh/skill-collections)<a href="https://agentmods.dev/commands/rito-w/claude-code-best-practice-zh/skill-collections"><img src="https://agentmods.dev/badge/commands/rito-w/claude-code-best-practice-zh/skill-collections.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.01895 |
| Opus 5 | $0.00009 | $0.00948 |
| Sonnet 5 | $0.00004 | $0.00379 |
| Haiku 4.5 | $0.00002 | $0.00189 |
Grade A, and why
skill-collections scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to skill-collections — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow — Skill Collections
Update the SKILL COLLECTIONS table in README.md by researching 5 repos in parallel. Launch a research agent, merge results, present changes, update table if approved.
The 5 Repos
| # | Repo | Owner |
|---|---|---|
| 1 | anthropics/skills |
Anthropic (official) |
| 2 | wshobson/agents |
William Shobson |
| 3 | mattpocock/skills |
Matt Pocock |
| 4 | K-Dense-AI/scientific-agent-skills |
K-Dense-AI |
| 5 | VoltAgent/awesome-agent-skills |
VoltAgent (curated awesome-list) |
Table Format
The README table has these columns:
| Name | ★ | <img src="!/tags/s.svg" height="14"> |
- Name:
[Short Name](github-url)— use repo's short name (e.g.,mattpocock/skills, or justskillsif owner is the project), not the full owner/repo unless ambiguous - ★: Star count rounded to
k(e.g., 125k, 35k, 1.2k). Under 1000 show exact number - Skill count: Just the number. For awesome-lists where skills are links not files, use
N+ (curated list)form
Sort order: Sorted by stars descending (highest first).
Phase 0: Read Current State
Read these files:
README.md— the## 🧰 SKILL COLLECTIONStable (note current stars and skill counts)changelog/skill-collections/changelog.md— previous changelog entries (may not exist yet)
Phase 1: Launch Research Agent
Immediately spawn one development-workflows-research-agent covering all 5 repos. (The existing research agent is generic — it counts skills/stars/etc. for any repo.)
Research these 5 Claude Code skill-collection repositories. Each is primarily a library of
SKILL.mdfiles, NOT a full workflow methodology.Repo 1: anthropics/skills (https://github.com/anthropics/skills) — official Anthropic skills repo Repo 2: wshobson/agents (https://github.com/wshobson/agents) — plugin-scoped skills (skills nested under domain plugins) Repo 3: mattpocock/skills (https://github.com/mattpocock/skills) — TypeScript-focused Repo 4: K-Dense-AI/scientific-agent-skills (https://github.com/K-Dense-AI/scientific-agent-skills) — science/research vertical Repo 5: VoltAgent/awesome-agent-skills (https://github.com/VoltAgent/awesome-agent-skills) — curated awesome-list (links to external skills, not SKILL.md files in repo)
For EACH repo, return:
- Stars — use GitHub API
https://api.github.com/repos/{owner}/{repo}, readstargazers_count. Round tok.- Skill count — count
SKILL.mdfiles in the repo via the GitHub git tree API:https://api.github.com/repos/{owner}/{repo}/git/trees/HEAD?recursive=1and grep paths forSKILL.md.
- For
wshobson/agents: skills are nested insideplugins/<domain>/skills/— count all SKILL.md across all plugins.- For
VoltAgent/awesome-agent-skills: count the listed skills in README.md (e.g., bullets / table rows). Mark explicitly as "curated list, not files".- For
K-Dense-AI/scientific-agent-skills: subdirectories underskills/may use SKILL.md or.md; count whichever the repo uses, and report which.- For
anthropics/skills: skills live in subdirectories underskills/withSKILL.mdinside.- For
mattpocock/skills: include only active skills, not deprecated ones (note both numbers if obvious).- Notable changes — any significant additions or removals in last 30 days?
Return structured report per repo:
REPO: anthropics/skills STARS: <number>k (<exact>) SKILLS: <count> (<file pattern used, e.g., "SKILL.md files via git tree">) NOTES: <anything unusual — flat .md vs SKILL.md, deprecated skills, language variants, curated-list disclaimer> CHANGES: <changes or "No significant changes"> CONFIDENCE: <0-1>
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 165 lines · 18 tokens per session scan A 5b9d778644f0
skill-collections is a command published in the GitHub repository Rito-w/claude-code-best-practice-zh (10 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 1,895 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to skill-collections, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.