SkillAgentSearch skills...

compound

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

Install / Use

npx skills add oliver-kriska/claude-elixir-phoenix --skill compound

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

85/100

Supported Platforms

Universal

Our assessment of compound

compound scores 85/100 on our quality scale, 682nd of 1,215 Content & Media skills we index.

Its SKILL.md is 3.8 KB long, well organised into 13 sections with 2 code examples: a solid amount of guidance for an agent.

It has 560 GitHub stars, a meaningful sign that others use it.

Substance
26/30
Structure
18/20
Description
15/15
Adoption
12/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 2 days ago, so compound is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

compound compared with similar skills

All 4 of these similar skills score higher than compound; compare them before choosing.

SkillScoreStarsUpdatedFormat
compound (this skill)by oliver-kriska855602d agoSKILL.md
siyuanby siyuan-note10046.6ktodayMCP Server
algorithmic-artby anthropics100177.9k11d agoSKILL.md
pptxby anthropics100177.9k11d agoSKILL.md
designby nextlevelbuilder100130.2k12d agoSKILL.md

Frequently asked questions

How do I install compound?
Run npx skills add oliver-kriska/claude-elixir-phoenix --skill compound. The install tabs above show the steps for each supported agent.
Which AI agents does compound work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is compound safe to use?
It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is compound still maintained?
The repository was last updated 2 days ago, so compound is actively maintained.

name: compound description: Capture solved problems as searchable solution docs. Use after fixing bugs, when "that worked", or after successful /phx:review or /phx:investigate. effort: low argument-hint: "[description of what was fixed]"

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

Related Skills

View on GitHub
GitHub Stars560
CategoryContent
Updated2d ago
Forks44

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions