Skills

skill-creator

skill-creator is a skill in feiskyer/claude-code-settings, last changed 27 Sept 2026. It can touch credentials, change agent settings, run shell commands, reach the network, name web addresses and bundle scripts — read the findings before installing. Our pattern check flagged nothing at commit 95dab59 on 27 Oct 2026.

Pattern check: nothing flagged · commit 95dab59 · 27 Oct 2026

Install
From the author
Create, refine, and benchmark agent skills. Use when building a new skill, updating an existing one, running evals, checking trigger quality, or improving a skill description.
Licence
Apache 2.0
Repo stars
1.7k
Folder last changed
27 Sept 2026 (opens in a new tab)
Publisher
feiskyer
Files
24 files
Checked
95dab59 (opens in a new tab) · 27 Oct 2026

Install

Each tab says whether it installs commit 95dab59, the one we checked, or the latest version.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.

Pinned to commit 95dab59, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/feiskyer/claude-code-settings.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 95dab59a62b2031adcb7abf25ae0a60b8a13fdb2 &&
  git -C "$tmp" sparse-checkout set -- skills/skill-creator &&
  git -C "$tmp" checkout -q 95dab59a62b2031adcb7abf25ae0a60b8a13fdb2 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/skill-creator &&
  cp -R "$tmp"/skills/skill-creator/. .claude/skills/skill-creator/ &&
  rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Or install the claude-code-settings plugin it ships in. Installs the latest version, not the one we checked. Installs everything in the plugin, including any hooks, MCP servers and scripts our check doesn't cover.

claude plugin marketplace add feiskyer/claude-code-settings --scope project &&
  claude plugin install claude-code-settings@claude-code-settings --scope project
Claude Code docs (opens in a new tab)

What it can touch

From the files and frontmatter at commit 95dab59. This is how much a skill can do, not whether it is risky.

What it can touch: Shell, network or credentials

  • Runs shell commands

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

  • Reaches the network

    It sends or fetches data over the internet, for example with curl, an HTTP library or a package install.

  • Names web addresses

    It mentions outside web addresses the agent may visit. We list them but don't follow them.

  • Bundles scripts

    The folder holds code files the agent may run.

  • Touches credentials

    It reads, asks for or contains keys, tokens, passwords or similar secrets.

    scripts/improve_description.py:248 · scripts/platforms/claude_code.py:71

  • Changes agent settings

    It writes to agent memory or settings files such as CLAUDE.md, AGENTS.md or .claude/settings.json.

    scripts/platforms/claude_code.py:32

Pattern check

Pattern check: nothing flagged · commit 95dab59 · 27 Oct 2026

We checked every text file in this skill, at commit 95dab59 on 27 Oct 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

Outside links we did not follow

  • http://www.apache.org/licenses/
  • http://www.apache.org/licenses/LICENSE-2.0
  • https://github.com/anthropics/skills/tree/main/skills/skill-creator
  • https://fonts.googleapis.com
  • https://fonts.gstatic.com
  • https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&display=swap
  • https://cdn.sheetjs.com/xlsx-0.20.3/package/dist/xlsx.full.min.js

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 what the strictest agents enforce, so one folder loads everywhere.

    • Warning

      The body is 502 lines; the spec suggests under 500. B1

      Fix: Move detailed sections into reference files and link to them from SKILL.md.

    • Warning

      The body is about 7,573 tokens (approx.); the spec suggests under 5,000. B2

      Fix: Move detail into reference files that the agent reads only when needed.

    • 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.

    • Note

      Reference files over 100 lines with no table of contents at the top: agents/analyzer.md (280 lines), agents/comparator.md (197 lines), agents/grader.md (229 lines) and references/schemas.md (425 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • Claude CodePasses

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

    • Note

      The body is 502 lines; the spec suggests under 500. Claude Code's docs say the same. B1

      Fix: Move detailed sections into reference files and link to them from SKILL.md.

    • Note

      The body is about 7,573 tokens (approx.); the spec suggests under 5,000. After compaction Claude Code keeps only the first 5,000 tokens of a skill. B2

      Fix: Move detail into reference files that the agent reads only when needed.

    • Note

      Reference files over 100 lines with no table of contents at the top: agents/analyzer.md (280 lines), agents/comparator.md (197 lines), agents/grader.md (229 lines) and references/schemas.md (425 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • Claude apps & API uploadPasses

    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.

    • Note

      The body is 502 lines; the spec suggests under 500. Anthropic's guidance says the same. B1

      Fix: Move detailed sections into reference files and link to them from SKILL.md.

    • Note

      The body is about 7,573 tokens (approx.); the spec suggests under 5,000. Anthropic's guidance says the same. B2

      Fix: Move detail into reference files that the agent reads only when needed.

    • Note

      Reference files over 100 lines with no table of contents at the top: agents/analyzer.md (280 lines), agents/comparator.md (197 lines), agents/grader.md (229 lines) and references/schemas.md (425 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • OpenAI (Codex & API)Passes
  • VS Code & CopilotPasses

SKILL.md

Files

24 files

PathSize
LICENSE.txt (opens in a new tab)11.1 KB
README.md (opens in a new tab)462 B
SKILL.md (opens in a new tab)30 KB
agents/analyzer.md (opens in a new tab)10.4 KB
agents/comparator.md (opens in a new tab)6.9 KB
agents/grader.md (opens in a new tab)9.1 KB
assets/eval_review.html (opens in a new tab)6.9 KB
eval-viewer/generate_review.py (opens in a new tab)16 KB
eval-viewer/viewer.html (opens in a new tab)43.9 KB
references/schemas.md (opens in a new tab)11.6 KB
scripts/__init__.py (opens in a new tab)0 B
scripts/aggregate_benchmark.py (opens in a new tab)14.5 KB
scripts/generate_report.py (opens in a new tab)13 KB
scripts/improve_description.py (opens in a new tab)16.2 KB
scripts/package_skill.py (opens in a new tab)4.1 KB
scripts/platforms/__init__.py (opens in a new tab)54 B
scripts/platforms/base.py (opens in a new tab)2.2 KB
scripts/platforms/claude_code.py (opens in a new tab)6.3 KB
scripts/platforms/codex.py (opens in a new tab)5.4 KB
scripts/platforms/openclaw.py (opens in a new tab)4.3 KB
Show 4 more
PathSize
scripts/quick_validate.py (opens in a new tab)9.6 KB
scripts/run_eval.py (opens in a new tab)8.2 KB
scripts/run_loop.py (opens in a new tab)15 KB
scripts/utils.py (opens in a new tab)3.4 KB

More from feiskyer/claude-code-settings

  • brainstorming

    feiskyer/claude-code-settings

    Explore user intent, requirements, and design options through collaborative dialogue before implementation. Use before building new features, components, or systems — whenever the user describes something to build and design decisions are involved. Triggers: "brainstorm", "help me design", "think through the requirements", "头脑风暴", "设计方案", "梳理需求". Not for bug fixes, config changes, or tasks with an obvious implementation path.

    • Runs shell commands
    • Reaches the network
    • +1 more
    Pattern check: Nothing flagged

    MIT · 1.7k repo stars · Updated 27 Sept 2026

  • codex-skill

    feiskyer/claude-code-settings

    Leverage OpenAI Codex/GPT models for autonomous code implementation, code review, and plan review. Triggers: "codex", "use gpt", "gpt-5", "let openai", "full-auto", "adversarial review", "second opinion review", "用codex", "让gpt实现", "对抗式审查", "让codex审查计划", "第二意见". Use this skill whenever the user wants to delegate coding tasks to OpenAI models, run code or plan reviews via codex, get a second-opinion review from a different model, or execute tasks in a sandboxed environment.

    • Touches credentials
    • Runs shell commands
    • +4 more
    Pattern check: 1 item to review

    MIT · 1.7k repo stars · Updated 27 Sept 2026

  • deep-research

    feiskyer/claude-code-settings

    Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless `claude -p` subprocesses, aggregate results into a polished report file. Use for systematic web/document research, competitive or industry analysis, batch link/dataset processing, and long-form evidence synthesis. Triggers: "深度调研", "deep research", "wide research", "多 Agent 调研", "系统调研".

    • Runs shell commands
    • Reaches the network
    • +1 more
    Pattern check: 1 item to review

    MIT · 1.7k repo stars · Updated 27 Sept 2026

  • github-fix-issue

    feiskyer/claude-code-settings

    Fix GitHub issues end-to-end — analysis, branch creation, implementation, testing, and PR submission. Use whenever the user mentions fixing a GitHub issue, says "fix issue

    • Runs shell commands
    • Pre-approves tools
    Pattern check: 1 item to review

    MIT · 1.7k repo stars · Updated 27 Sept 2026

  • github-review-pr

    feiskyer/claude-code-settings

    Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for local uncommitted changes — this skill only reviews pull requests on GitHub.

    • Runs shell commands
    • Reaches the network
    • +2 more
    Pattern check: Nothing flagged

    MIT · 1.7k repo stars · Updated 24 Sept 2026

  • gpt-image-skill

    feiskyer/claude-code-settings

    Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). Use ONLY when the user explicitly names OpenAI or GPT as the provider: "gpt image", "openai image", "generate image with openai", "用 openai 画图", "用 GPT 生成图片". For generic image requests without a provider, use nanobanana-skill instead. Do NOT use for diagrams (架构图/流程图) — draw those with Mermaid or code.

    • Runs shell commands
    • Reaches the network
    • +2 more
    Pattern check: 1 item to review

    MIT · 1.7k repo stars · Updated 11 Jul 2026

All skills in feiskyer/claude-code-settings