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

Quality

31%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/compound/SKILL.md

Quality

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description fails on all dimensions. It describes a vague situational context ('after a problem is solved') without ever stating what the skill actually does — whether it writes documentation, creates a postmortem, updates a knowledge base, or something else entirely. It lacks concrete actions, natural trigger terms, and any distinguishing characteristics that would help Claude select it appropriately from a pool of skills.

Suggestions

Add explicit actions describing what the skill produces, e.g., 'Documents the root cause, investigation steps, and solution into a structured postmortem or knowledge base entry'

Add a 'Use when...' clause with natural trigger terms like 'document this fix', 'write a postmortem', 'save this solution', 'lessons learned', 'capture what we learned'

Specify the output format or artifact (e.g., markdown file, knowledge base entry, incident report) to distinguish this skill from general documentation or debugging skills

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'a problem has just been solved' and 'capture for future reference' without specifying any concrete actions. It doesn't say what the skill actually does — no verbs like 'documents', 'creates a report', 'writes a postmortem', etc.	1 / 3
Completeness	The description only vaguely addresses 'when' (after a problem is solved) but completely fails to answer 'what does this do'. There is no explanation of the skill's actions or outputs. The 'when' guidance is also imprecise — it describes a situational context rather than explicit triggers.	1 / 3
Trigger Term Quality	There are no natural keywords a user would say. Terms like 'fix is fresh' and 'investigation is in recent history' are abstract descriptions of a situation, not terms a user would type. Missing keywords like 'document fix', 'save solution', 'postmortem', 'lessons learned', 'write up', etc.	1 / 3
Distinctiveness Conflict Risk	The description is extremely generic — 'a problem has just been solved' could apply to virtually any debugging, troubleshooting, or documentation skill. Without specifying what it produces or its domain, it would easily conflict with many other skills.	1 / 3
	Total	4 / 12 Passed

Implementation

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides a well-structured orchestration workflow with clear phase sequencing and good guardrails around the single-file-write constraint. However, it lacks concrete executable examples — no sample output document, no YAML frontmatter schema, and no subagent prompt templates — which limits actionability. The content is moderately concise but could be tightened, and the absence of bundle files for referenced agents and formats weakens progressive disclosure.

Suggestions

Add a concrete example of the final output document showing the expected YAML frontmatter schema and markdown structure, so the orchestrator knows exactly what to produce.

Include at least one sample subagent prompt or return format specification so the parallel research phase has executable guidance rather than just role descriptions.

Provide a bundle file (e.g., TEMPLATE.md or SCHEMA.md) with the expected output format and reference it from the main skill, improving both actionability and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably well-structured but includes some unnecessary verbosity. The overview paragraph restates what the phases already explain. The 'Common Mistakes' table is useful but slightly redundant given the critical_requirement callout. Some sections like Phase 0.5 and Phase 2.5 add complexity that could be tightened.	2 / 3
Actionability	The skill provides a clear architectural blueprint with phases, subagent roles, and output paths, but lacks concrete executable examples. There are no actual subagent prompt templates, no example YAML frontmatter schema, no sample output document, and no example of what the final markdown file should look like. The guidance is structural rather than copy-paste ready.	2 / 3
Workflow Clarity	The multi-phase workflow is clearly sequenced with explicit dependencies (Phase 1 parallel → wait → Phase 2 assembly → Phase 2.5 conditional → Phase 3 optional). The critical requirement callout about file writing is a strong validation checkpoint. The conditional logic in Phase 2.5 includes clear decision criteria for when to invoke refresh.	3 / 3
Progressive Disclosure	The skill references external agents (superpowers-ruby:compound-refresh, performance-oracle, security-sentinel, etc.) and a compact mode, but no bundle files are provided to support these references. The content is moderately well-organized with tables and phases, but everything is inline in one file — the subagent prompt details, output format specs, and YAML frontmatter schema could be split into referenced files for better organization.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: lucianghinda/superpowers-ruby
Commit: c037ce3

Reviewed: about 19 hours ago

Table of Contents

Discovery Implementation Validation

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.