using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
36
32%
Does it follow best practices?
Impact
—
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 is a meta-level system instruction rather than a proper skill description. It lacks concrete actions, natural user trigger terms, and specificity. Its universal trigger condition ('any conversation') makes it indistinguishable from other skills and essentially unusable in a multi-skill selection context.
Suggestions
Replace the universal trigger ('any conversation') with specific, distinguishable conditions that describe when this skill is uniquely needed versus other skills.
Add concrete actions describing what this skill actually does (e.g., 'Lists available skills, searches skill directory, recommends relevant skills based on user request').
Include natural user keywords that would trigger this skill, such as 'what skills are available', 'help me find a skill', 'what can you do', etc.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description does not list any concrete actions or capabilities. 'Establishes how to find and use skills' is abstract and meta-level, not describing what the skill actually does in terms of user-facing tasks. | 1 / 3 |
Completeness | It has a 'when' clause ('Use when starting any conversation') but the 'what' is extremely vague — it only says it 'establishes how to find and use skills' without explaining what concrete value it provides. The 'when' is also overly broad (every conversation). | 2 / 3 |
Trigger Term Quality | There are no natural user keywords present. Users would never say 'starting any conversation' or 'Skill tool invocation' — these are internal system concepts, not terms a user would use in a request. | 1 / 3 |
Distinctiveness Conflict Risk | Triggering on 'any conversation' means this would conflict with every other skill. It has no distinct niche or specific trigger conditions that would differentiate it from other skills. | 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 has a clear and well-structured workflow for when and how to invoke skills, but it is significantly undermined by extreme verbosity and repetition. The 'Red Flags' table, ALL-CAPS warnings, and repeated insistence on the same point consume many tokens to convey what could be said in 2-3 sentences. The actionability is moderate — it tells Claude what to do but spends more effort on behavioral conditioning than concrete executable steps.
Suggestions
Drastically reduce the 'Red Flags' table to 2-3 representative examples or a single concise rule like 'If any skill might apply, invoke it before doing anything else — no exceptions.'
Remove the ALL-CAPS EXTREMELY-IMPORTANT block and the repeated 'not negotiable' language; a single clear directive is more effective and token-efficient.
Consider splitting platform-specific adaptation details into a separate reference file to keep the main skill focused on the core workflow.
Remove explanatory phrases like 'Questions are tasks' and 'Action = task' that belabor the point — Claude can infer these from the core rule.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The 'Red Flags' table alone contains 12 rows hammering the same point ('check for skills first'). The ALL-CAPS warnings, the repeated insistence that this is 'not negotiable,' and the extensive rationalization table all explain something Claude should grasp from a single clear instruction. The dot graph adds tokens for a relatively simple flow. | 1 / 3 |
Actionability | It provides concrete guidance on invoking the Skill tool and a clear workflow (check skills → invoke → announce → follow), but much of the content is motivational/behavioral rather than executable. The dot graph and red flags table describe mindset rather than specific commands or code. The platform adaptation section is somewhat actionable but vague ('check your platform's documentation'). | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced via the dot graph and the textual description: receive message → check if skills apply → invoke Skill tool → announce → check for checklist → create todos → follow skill. The priority ordering (process skills first, then implementation) and the rigid vs flexible distinction add useful structure. For a meta-skill about skill invocation, this is a clear and complete workflow. | 3 / 3 |
Progressive Disclosure | References to external files exist (references/copilot-tools.md, references/codex-tools.md) which is good, but no bundle files are provided to support them. The skill itself is monolithic — the red flags table, platform adaptation, and instruction priority sections could be split out. The content is reasonably organized with headers but everything is inline in one large file. | 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
- obra/superpowers
- Commit
f2cbfbe
- 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.