using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
46
32%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/using-superpowers/SKILL.mdQuality
Discovery
17%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 functions as a meta-skill or bootstrap instruction rather than a task-specific skill description. It lacks concrete actions, natural trigger terms, and domain specificity. Its instruction to trigger on 'any conversation' makes it maximally conflicting with all other skills and provides no meaningful selection signal.
Suggestions
Replace the overly broad 'any conversation' trigger with specific conditions that would actually require this skill, such as 'Use when the user asks what skills are available, how to use a skill, or requests a skill directory.'
Add concrete actions describing what this skill does, e.g., 'Lists available skills, searches skill descriptions by keyword, and recommends the most relevant skill for a given task.'
Include natural trigger terms users might say, such as 'list skills', 'what can you do', 'available tools', 'help me find a skill', to improve selection accuracy.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description does not list any concrete actions or capabilities. It vaguely mentions 'establishes how to find and use skills' and 'Skill tool invocation' without specifying what the skill actually does beyond being a meta-process for other skills. | 1 / 3 |
Completeness | It has a 'when' clause ('Use when starting any conversation') but the 'what' is extremely weak — it only says it 'establishes how to find and use skills' without explaining what concrete value it provides. The 'when' is present but overly broad (every conversation), which undermines its usefulness. | 2 / 3 |
Trigger Term Quality | There are no natural user-facing keywords. Terms like 'Skill tool invocation' and 'establishes how to find and use skills' are internal/technical jargon that no user would naturally say. 'Starting any conversation' is overly generic and not a meaningful trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | Triggering on 'any conversation' means this would conflict with every other skill. It has no distinct niche or specific domain — it's a catch-all meta-skill that would fire indiscriminately. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill serves as a meta-bootstrapper that forces skill invocation before any action. Its main strength is the comprehensive skills catalog with clear categorization and invocation names, plus a well-defined workflow sequence. Its main weakness is extreme verbosity and repetition — the core message ('always check for and invoke relevant skills first') is hammered home through redundant tables, emphatic warnings, and repetitive phrasing that wastes significant token budget on what is fundamentally a simple instruction.
Suggestions
Consolidate the 'Red Flags' table into 2-3 representative examples or a single principle ('Any rationalization to skip skill invocation is wrong — invoke first, decide relevance after') instead of 12 repetitive entries.
Remove the emphatic HTML-like tags and repeated warnings (EXTREMELY-IMPORTANT, 'not negotiable', 'not optional') — state the rule once clearly and trust Claude to follow it.
Move the full skills catalog to a separate referenced file (e.g., SKILLS-CATALOG.md) and keep only the top 3-5 most commonly needed skills inline, reducing the bootstrapping skill's token footprint significantly.
Remove the DOT graph notation and replace with a simple numbered list — the graph adds parsing overhead without meaningful clarity improvement over a 4-step list.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The 'Red Flags' table with 12 entries all saying the same thing ('check for skills first') is massively redundant. The emphatic warnings ('EXTREMELY-IMPORTANT', 'This is not negotiable') and repeated insistence on invoking skills waste tokens on a concept that could be stated once. The DOT graph notation adds complexity without proportional value. | 1 / 3 |
Actionability | The skills catalog with exact invocation names is concrete and useful. The workflow diagram provides a clear decision tree. However, the core action ('invoke the Skill tool before responding') is simple and doesn't need this much scaffolding. The actual mechanics of how to invoke skills are somewhat vague beyond 'use the Skill tool.' | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced via the DOT digraph and the textual rule. The decision flow (message received → check for skills → invoke → announce → check for checklist → follow skill → respond) is explicit with clear branching. Priority ordering for multiple skills is well-defined. | 3 / 3 |
Progressive Disclosure | The skills catalog is well-organized into categories with clear 'When to Use' guidance, and references to external files (copilot-tools.md, codex-tools.md) are appropriate. However, the main content is monolithic — the Red Flags table, instruction priority section, and extensive catalog could be split into referenced files rather than inlined in what should be a bootstrapping skill. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%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
cb03f92
- Reviewed
Table of Contents
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.