跳到正文
FunCoding

搜索

搜索文档、Skill 和 MCP

footgun-scan

Scan a Kotlin or Compose Multiplatform diff for known footgun shapes and open the matching trap to confirm each hit. Use before committing, when reviewing a Kotlin change, or to audit a codebase.

AI 与智能体1.1kskills/footgun-scan/SKILL.md

安装

把这段话发给 Claude Code、Codex 或 Cursor。智能体会先检查安全性,你确认后才安装。

读取 https://funcoding.ai/skills/maxrave-dev/kotlin-footguns/footgun-scan/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

Footgun scan

scripts/scan.py matches 32 patterns against the lines a change adds. Each pattern is tied to one trap file in the kotlin-footguns area skills. It finds shapes, not bugs: every hit needs the trap's judgment before it becomes a finding.

Run it

From inside the user's git repository, with this skill's base directory as <skill>:

python3 <skill>/scripts/scan.py                     # lines added in the working tree and index since HEAD
python3 <skill>/scripts/scan.py --base origin/main  # lines added on this branch since it left main
python3 <skill>/scripts/scan.py --all src/          # every line under a path: an audit, and noisier

Pick the scope from the request. Uncommitted work takes the default. A branch or pull request takes --base with its target branch. "Audit the codebase" takes --all, narrowed to the paths that matter. For a pre-commit hook or CI step, add --fail to exit 1 on any likely hit.

Triage every hit

  1. Read the trap file the hit points to (the -> path).
  2. Read the code around the hit and decide, by the trap's own conditions, whether it applies. A likely hit is wrong unless the exception the trap names holds. A look hit is a place the trap says to inspect before trusting it.
  3. Report each confirmed problem with the trap's fix and its Verifying step. List dismissed hits one line each with the reason, for example "column is NOT NULL" or "the fade goes to black".

Hits of one detector in one file are grouped: triage the group once, then check the listed lines for exceptions.

When the scanner cannot run

It needs python3 and git. Without them, read scripts/scan.py: the DETECTORS list gives each pattern, its message and its trap. Run those patterns with the Grep tool over the changed files and triage the same way.

相似的 Skill

brand-guidelines
anthropics/skills180k

brand-guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

AI 与智能体

internal-comms
anthropics/skills180k

internal-comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

AI 与智能体

template-skill
anthropics/skills180k

template-skill

Replace with description of the skill and when Claude should use it.

AI 与智能体

mcp-builder
anthropics/skills180k

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

AI 与智能体

algorithmic-art
anthropics/skills180k

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

AI 与智能体

academy-guide
anthropics/skills180k

academy-guide

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

AI 与智能体