跳到正文
FunCoding

搜索

搜索文档、Skill 和 MCP

compound

Capture solved problems as searchable solution docs. Use after fixing bugs, when "that worked", or after successful /phx:review or /phx:investigate.

AI 与智能体565plugins/elixir-phoenix/skills/compound/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/oliver-kriska/claude-elixir-phoenix/compound/install.md ，按里面的步骤帮我安装这个 Skill。

SKILL.md

Compound — Capture Solutions as Knowledge

After fixing a problem, capture the solution as searchable institutional documentation.

Usage

/phx:compound Fixed N+1 query in user listing
/phx:compound Resolved LiveView timeout in dashboard
/phx:compound   # Auto-detects from recent session context

Philosophy

Each unit of engineering work should make subsequent units easier — not harder.

Workflow

Step 1: Detect Context

  1. If $ARGUMENTS provided, use as description
  2. If no args, check scratchpad DEAD-END/DECISION entries, git diff, .claude/plans/{slug}/progress.md for recent completions
  3. If unclear, ask: "What problem did you just solve?"

Only document non-trivial problems that required investigation.

Step 2: Search Existing Solutions

Create .claude/solutions/ directory if it doesn't exist (run mkdir -p .claude/solutions). Then search .claude/solutions/ for relevant keywords using Grep.

If found: Create new (different root cause), Update existing (same root cause, new symptom), or Skip.

Step 3: Gather Details and Create Solution

Extract from session context: module, symptoms, investigation steps, root cause, solution code, and prevention advice.

Validate frontmatter against ${CLAUDE_PLUGIN_ROOT}/skills/compound-docs/references/schema.md, then create file using ${CLAUDE_PLUGIN_ROOT}/skills/compound-docs/references/resolution-template.md.

Write-blocked fallback: if writing to .claude/solutions/ is denied by permissions, do NOT silently drop the solution. Output the full solution doc inline (fenced markdown the user can paste), then suggest /phx:permissions to allow .claude/solutions/ writes for next time.

Step 4: Decision Menu

  1. Continue (default)
  2. Promote to Iron Law check — Add to iron-law-judge
  3. Update skill reference — Add to relevant skill
  4. Update CLAUDE.md — Add prevention rule

Auto-Trigger Phrases

When user says "that worked", "it's fixed", "problem solved", "the fix was" — suggest /phx:compound.

Supply-chain finding auto-feed (Phase 3)

When /phx:deps-audit produces a BLOCK-severity finding that the user investigates and confirms is a real malicious pattern (not a false positive), suggest:

Caught a high-severity finding in <pkg>@<version>. Run /phx:compound to capture this for future audits?

If accepted, the resulting solution doc goes to .claude/solutions/supply-chain/<pkg>-<cve_or_pattern>.md and includes the exact rule-id + snippet + diff window that triggered the finding. This compounds the audit corpus: future runs of /phx:deps-audit grep solutions/supply-chain/ for snippet matches and pre-elevate severity on known-bad patterns.

Always prompt; never auto-write. Solution docs are durable and shape future trust calls — the user reviews before committing.

Iron Laws

  1. YAML frontmatter validates or STOP
  2. Symptoms must be specific — not "it broke"
  3. Root cause is WHY, not WHAT
  4. One problem per file
  5. NEVER document a fix before verifying it works — run mix compile && mix test first; unverified solutions poison the knowledge base

Integration with Workflow

/phx:review → Complete → /phx:compound  ← YOU ARE HERE
                              │
                 .claude/solutions/{category}/{fix}.md
                              │
              /phx:investigate and /phx:plan search here

References

  • ${CLAUDE_SKILL_DIR}/references/compound-workflow.md — Detailed step-by-step
  • See also: compound-docs skill for schema and templates

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