meta-apply is a skill in wanshuiyin/Auto-claude-code-research-in-sleep, last changed 18 Oct 2026. It can run shell commands and pre-approve tools — read the findings before installing.

From the author
Privileged applier that LANDS meta-optimize / corpus-audit patches the user approved — the ONLY skill permitted to mutate the skill corpus from a self-modification proposal, with cross-model jury and human approval at landing. Use when the user says "meta apply", "/meta-apply", "land the staged patches", "应用优化", after a /meta-optimize run.

At a glance

What it can touch

How much a skill can do, not whether it is risky.

Pattern check

1 item to review

Broad tools pre-approved in allowed-tools

R34 · High · SKILL.md:5

Commit 2927b40 · 3 Nov 2026

How the check works

Pattern check:1 item to reviewSee it

Install

Each tab says whether it installs commit 2927b40, the one we checked, or the latest version.

Read this before installing: Broad tools pre-approved in allowed-tools — SKILL.md:5

Read SKILL.md first
MIT
Licence
18.6k
Repo stars
Publisher
Files

What it can touch

From the files and frontmatter at commit 2927b40. This is how much a skill can do, not whether it is risky.

  • Runs shell commands

    Its instructions or files give the agent commands to run on your computer.

  • Pre-approves tools

    Its allowed-tools field lists tools the agent may use without asking you first, in agents that honour it.

    SKILL.md:5 (opens in a new tab)

Pattern check

Pattern check: 1 item to review · commit 2927b40 · 3 Nov 2026

  • R34 · HighBroad tools pre-approved in allowed-tools

    SKILL.md:5 (opens in a new tab)
    allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok…

We checked every text file in this skill, at commit 2927b40 on 3 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses with warnings

    The open format from agentskills.io, held to the strictest version of each rule among the agents we check.

    • Warning

      Fields outside the spec: argument-hint (read by Claude Code and VS Code). Uploads to the Claude apps and API, and the spec's validator, reject the file; most agents ignore these fields. O1

      Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.

    • Warning

      Paths that may not work once the skill is installed: line 10: ../shared-references/reviewer-backends.md (outside the skill folder), line 22: ../meta-optimize/SKILL.md (outside the skill folder), line 51: ../shared-references/reviewer-independence.md (outside the skill folder), line 54: ../shared-references/review-scope-limits.md (outside the skill folder), line 76: ../shared-references/integration-contract.md (outside the skill folder) and 1 more. B6

      Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.

    • Note

      There is no license field, so readers can't tell whether they may reuse the skill. O2

      Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

  • Claude CodePasses with warnings

    Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

    • Warning

      Paths that may not work once the skill is installed: line 10: ../shared-references/reviewer-backends.md (outside the skill folder), line 22: ../meta-optimize/SKILL.md (outside the skill folder), line 51: ../shared-references/reviewer-independence.md (outside the skill folder), line 54: ../shared-references/review-scope-limits.md (outside the skill folder), line 76: ../shared-references/integration-contract.md (outside the skill folder) and 1 more. B6

      Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.

  • Claude apps & API uploadFails

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Error

      Upload and packaging fail on fields outside the spec: argument-hint. O1

      Fix: Delete them, and keep your own data under metadata as text values.

    • Warning

      Paths that may not work once the skill is installed: line 10: ../shared-references/reviewer-backends.md (outside the skill folder), line 22: ../meta-optimize/SKILL.md (outside the skill folder), line 51: ../shared-references/reviewer-independence.md (outside the skill folder), line 54: ../shared-references/review-scope-limits.md (outside the skill folder), line 76: ../shared-references/integration-contract.md (outside the skill folder) and 1 more. B6

      Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.

    • Note

      The description is 341 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

      Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

    • Note

      Line 49 names an MCP tool as mcp__codex__codex. For the Claude apps and API, Anthropic's guidance is Server:tool, such as GitHub:create_issue. B7

      Fix: Write it as codex:codex, using the server's own name.

  • OpenAI (Codex & API)Passes with warnings

    Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.

    • Warning

      Fields outside the spec: argument-hint. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1

      Fix: Delete them, or move your own data under metadata as text values.

    • Warning

      Paths that may not work once the skill is installed: line 10: ../shared-references/reviewer-backends.md (outside the skill folder), line 22: ../meta-optimize/SKILL.md (outside the skill folder), line 51: ../shared-references/reviewer-independence.md (outside the skill folder), line 54: ../shared-references/review-scope-limits.md (outside the skill folder), line 76: ../shared-references/integration-contract.md (outside the skill folder) and 1 more. B6

      Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.

  • VS Code & CopilotPasses with warnings

    VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.

    • Warning

      Paths that may not work once the skill is installed: line 10: ../shared-references/reviewer-backends.md (outside the skill folder), line 22: ../meta-optimize/SKILL.md (outside the skill folder), line 51: ../shared-references/reviewer-independence.md (outside the skill folder), line 54: ../shared-references/review-scope-limits.md (outside the skill folder), line 76: ../shared-references/integration-contract.md (outside the skill folder) and 1 more. B6

      Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.

SKILL.md

Files

1 file

PathSize
SKILL.md (opens in a new tab)8.8 KB

Copies

The same folder appears in 1 other repo. We list it once.

More from wanshuiyin/Auto-claude-code-research-in-sleep

SkillWhat it can touchPattern checkLicenceUpdated
  • Runs shell commands
  • Pre-approves tools
Pattern check: 1 item to reviewMIT6 Sept 2026
  • Runs shell commands
  • Pre-approves tools
Pattern check: 1 item to reviewMIT6 Sept 2026
  • Runs shell commands
  • Reaches the network
  • +2 more
Pattern check: 1 item to reviewMIT28 Sept 2026
  • Runs shell commands
  • Reaches the network
  • +2 more
Pattern check: 1 item to reviewMIT28 Sept 2026
  • Runs shell commands
  • Pre-approves tools
Pattern check: 1 item to reviewMIT12 Jul 2026
  • Instructions only
Pattern check: Nothing flaggedMIT17 Mar 2026
All skills in wanshuiyin/Auto-claude-code-research-in-sleep

Other AI & ML engineering skills

Same category, most repo stars first.

SkillWhat it can touchPattern checkLicenceUpdated
  • Runs shell commands
Pattern check: Nothing flaggedMIT11 Aug 2026
  • Runs shell commands
  • Names web addresses
Pattern check: Nothing flaggedMIT11 Aug 2026
claude-apiReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

anthropics/skills

  • Touches credentials
  • +6 more

Pattern check: 1 item to reviewApache 2.0Updated 9 Oct 2026

  • Touches credentials
  • Downloads software
  • +5 more
Pattern check: 1 item to reviewApache 2.09 Oct 2026
  • Touches credentials
  • Runs shell commands
  • +3 more
Pattern check: Nothing flaggedApache 2.028 Oct 2026
benchmark-modelsCross-model benchmark for gstack skills. (gstack)

garrytan/gstack

  • Touches credentials
  • +2 more

Pattern check: 1 item to reviewMITUpdated 30 Oct 2026

  • Touches credentials
  • Runs shell commands
  • +1 more
Pattern check: 1 item to reviewMIT30 Oct 2026
  • Runs shell commands
  • Pre-approves tools
Pattern check: 1 item to reviewMIT2 Nov 2026

Repo facts from GitHub on 3 Nov 2026. Files read at commit 2927b40.

QAI did not write these skills and is not affiliated with their authors unless a page says so. Logos and icons belong to their owners and are not a mark of approval. How we check