CtrlK
BlogDocsLog inGet started
Tessl Logo

superpowers-ruby:compound

Use when a problem has just been solved and verified working — the fix is fresh, the investigation is in recent history, and the solution is non-trivial enough to capture for future reference

Invalid
This skill can't be scored yet
Validation errors are blocking scoring. Review and fix them to unlock Quality, Impact and Security scores. See what needs fixing →
SKILL.md
Quality
Evals
Security

Compound

Overview

Captures problem solutions while context is fresh, creating structured documentation in docs/solutions/ with YAML frontmatter for searchability. Uses parallel subagents to gather context, extract the solution, find related docs, develop prevention strategies, and classify the category — then the orchestrator assembles and writes a single final file.

<critical_requirement> Only ONE file gets written — the final documentation.

Phase 1 subagents return TEXT DATA to the orchestrator. They must NOT write files. Only the orchestrator (Phase 2) writes the final documentation file. </critical_requirement>

When to Use

Trigger phrases: "that worked", "it's fixed", "working now", "problem solved", "tests are passing"

Use when:

  • Problem is solved and solution is verified working
  • Solution is non-trivial (not a simple typo or obvious error)
  • Context is fresh — investigation steps are in recent conversation history

Don't use when:

  • Fix is still in progress or unverified
  • Problem was trivial

Quick Reference

/superpowers:compound                    # Document the most recent fix
/superpowers:compound [brief context]    # Provide additional context hint
/compound --compact          # Single-pass mode for context-constrained sessions

Output location: docs/solutions/[category]/[filename].md

Categories auto-detected from problem type: build-errors · test-failures · runtime-errors · performance-issues · database-issues · security-issues · ui-bugs · integration-issues · logic-errors

Implementation

Always run full mode by default. Use compact-safe mode only when explicitly requested.

Phase 0.5: Auto Memory Scan

Before Phase 1, read MEMORY.md from the auto memory directory. If relevant entries exist for the problem being documented, pass them as a labeled supplementary excerpt to the Context Analyzer and Solution Extractor prompts. Tag any memory-sourced content incorporated into the final doc with "(auto memory [claude])".

Phase 1: Parallel Research

Launch these five subagents IN PARALLEL — each returns text data only, no files:

SubagentReturns
Context AnalyzerYAML frontmatter skeleton (problem type, component, symptoms)
Solution ExtractorRoot cause + working solution with code examples
Related Docs FinderCross-references, related issues, stale doc candidates
Prevention StrategistPrevention strategies and test cases
Category ClassifierFinal docs/solutions/[category]/[filename].md path

Phase 2: Assembly & Write

WAIT for all Phase 1 subagents to complete, then:

  1. Collect all text results from Phase 1 subagents
  2. Assemble complete markdown file
  3. Validate YAML frontmatter
  4. mkdir -p docs/solutions/[category]/
  5. Write the single final file: docs/solutions/[category]/[filename].md

Phase 2.5: Selective Refresh

After writing, check whether older docs should be refreshed. superpowers:compound-refresh is not a default follow-up — invoke it selectively:

ConditionAction
New fix contradicts a prior doc's recommendationInvoke superpowers:compound-refresh [doc-name]
New fix supersedes an older solutionInvoke with narrowest useful scope
Multiple related candidates in same areaAsk user whether to run targeted refresh
No related docs found, or docs still consistentSkip

Never invoke superpowers:compound-refresh without a scope argument.

Phase 3: Optional Enhancement

After Phase 2, optionally invoke specialized agents based on problem type:

Problem typeAgent
performance_issueperformance-oracle
security_issuesecurity-sentinel
database_issuedata-integrity-guardian
test_failurecora-test-reviewer
Code-heavykieran-rails-reviewer + code-simplicity-reviewer

Compact-Safe Mode

When context is tight: skip Phase 1 subagents entirely. In one sequential pass, extract problem/root cause/solution from conversation history (plus any relevant MEMORY.md notes), classify the category, and write a minimal doc with YAML frontmatter, 1-2 sentence problem description, root cause, key code snippets, and one prevention tip. Skip Phase 3 reviews.

Common Mistakes

❌ Wrong✅ Correct
Subagents write files like context-analysis.md, solution-draft.mdSubagents return text data; orchestrator writes one final file
Research and assembly run in parallelResearch completes → then assembly runs
Multiple files created during workflowSingle file: docs/solutions/[category]/[filename].md
Repository
lucianghinda/superpowers-ruby
Last updated
Created

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.