using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
81
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 94%
↑ 1.03xAgent success when using this skill
Validation for skill structure
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 fails to communicate concrete capabilities and uses overly broad trigger conditions that would conflict with every other skill. The meta-nature of the skill (about using other skills) is not clearly explained, and the technical jargon ('Skill tool invocation') would not match natural user language.
Suggestions
Replace vague language with specific actions: e.g., 'Searches available skills, matches user requests to appropriate skill files, and loads relevant skill instructions'
Remove or narrow the overly broad trigger 'starting any conversation' - specify actual scenarios like 'when user asks what skills are available' or 'when no other skill matches the request'
Add natural trigger terms users might say: 'what can you do', 'list skills', 'help me find', 'available capabilities'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'establishes how to find and use skills' without listing any concrete actions. It describes a meta-process rather than specific capabilities. | 1 / 3 |
Completeness | 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 that means concretely. | 2 / 3 |
Trigger Term Quality | Contains no natural keywords users would say. Terms like 'Skill tool invocation' are technical jargon, and 'starting any conversation' is overly generic rather than a natural user trigger. | 1 / 3 |
Distinctiveness Conflict Risk | 'Starting any conversation' is maximally generic and would trigger on literally every interaction, creating conflicts with all other skills. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured meta-skill that clearly instructs Claude on when and how to invoke skills. Its strengths are the explicit decision flowchart and comprehensive red flags table that prevent rationalization. The main weakness is some verbosity in the emphasis block and the red flags section, though the redundancy may be intentional for a critical behavioral skill.
Suggestions
Consider condensing the opening emphasis block - the triple repetition of 'must invoke' could be reduced while maintaining urgency
The Red Flags table could be trimmed to the 5-6 most common rationalizations rather than 12 entries
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundancy. The 'Red Flags' table is useful but verbose, and the opening emphasis block repeats the same point multiple times. The dot graph adds visual complexity that may not be necessary. | 2 / 3 |
Actionability | Provides concrete, specific guidance: invoke Skill tool before responding, announce usage pattern, create todos for checklists. The decision flow and red flags table give clear, actionable criteria for when to invoke skills. | 3 / 3 |
Workflow Clarity | The dot graph provides an explicit decision flowchart with clear sequencing. The skill priority section establishes clear ordering (process skills first, then implementation). The workflow is unambiguous for this meta-skill about skill usage. | 3 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections (The Rule, Red Flags, Skill Priority, Skill Types), but everything is inline in one file. For a meta-skill this may be appropriate, but the red flags table could potentially be a separate reference. | 2 / 3 |
Total | 10 / 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.
- 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.