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

35%

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

Content

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 critical constraint of single-file output. However, it operates at a high architectural level without providing concrete examples of the actual output format, subagent prompts, or YAML frontmatter schema, which limits actionability. The absence of bundle files for referenced agents and templates weakens progressive disclosure.

Suggestions

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

Include at least abbreviated prompt templates or key instructions for each Phase 1 subagent, rather than just describing what they return.

Add an example showing a complete run — from a sample problem context to the final written file path and content — to make the skill fully actionable.

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 the trigger phrases section and some explanatory text could be tightened. However, it avoids explaining concepts Claude already knows.	2 / 3
Actionability	The skill provides a clear architectural blueprint (parallel subagents, phases, categories) but lacks concrete executable details — there are no actual subagent prompt templates, no example YAML frontmatter schema, no example of what the final output file should look like, and no actual code for mkdir/write operations. It describes the process at a high level without copy-paste-ready specifics.	2 / 3
Workflow Clarity	The multi-phase workflow is clearly sequenced (Phase 0.5 → Phase 1 parallel → Phase 2 assembly → Phase 2.5 selective refresh → Phase 3 optional). Critical constraints are highlighted (subagents return text only, orchestrator writes one file). The 'Common Mistakes' table serves as an effective validation checkpoint. The conditional logic for Phase 2.5 refresh is well-specified with clear decision criteria.	3 / 3
Progressive Disclosure	The skill references external agents (superpowers-ruby:compound-refresh, performance-oracle, security-sentinel, etc.) and mentions MEMORY.md, but no bundle files are provided to support these references. The content is well-organized with clear sections, but for a skill of this complexity, the lack of supporting files (e.g., subagent prompt templates, output format examples, YAML schema) means important details are either missing or would need to be inlined.	2 / 3
	Total	9 / 12 Passed

Description

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 reads as a trigger condition without ever stating what the skill actually does. It lacks concrete actions, natural user keywords, and a clear 'what' component. While the timing context (post-fix capture) provides some distinctiveness, the absence of any capability description makes it nearly unusable for skill selection.

Suggestions

Add explicit capability statements describing what the skill does, e.g., 'Documents the root cause, investigation steps, and solution of a recently fixed bug into a structured postmortem or knowledge base entry.'

Include natural trigger terms users would say, such as 'document this fix', 'write up the solution', 'postmortem', 'lessons learned', 'save debugging notes'.

Restructure to clearly separate 'what' from 'when', e.g., 'Creates structured documentation of bug fixes including root cause analysis and solution steps. Use when a problem has just been solved and the user wants to capture the fix for future reference.'

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions — it doesn't say what the skill actually does (e.g., 'documents the fix', 'creates a postmortem', 'writes a knowledge base entry'). It only describes when to use it, using abstract language like 'capture for future reference'.	1 / 3
Completeness	The 'when' is present but vague and situational rather than trigger-based. The 'what' is entirely missing — the description never states what the skill does, only when it should be invoked. This fails both halves of the completeness requirement.	1 / 3
Trigger Term Quality	There are no natural user-facing trigger terms. Users would not say 'the fix is fresh' or 'investigation is in recent history.' Missing terms like 'document fix', 'save solution', 'postmortem', 'lessons learned', 'write up', or 'knowledge base'.	1 / 3
Distinctiveness Conflict Risk	The scenario described (post-fix documentation) is somewhat specific and wouldn't overlap with most skills. However, without naming concrete actions or outputs, it could still conflict with general documentation or note-taking skills.	2 / 3
	Total	5 / 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: 712d734

Reviewed: 7 days 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.