using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
56
47%
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 ./.opencode/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 fails as a skill selector because it's designed to trigger on every conversation rather than specific use cases. It lacks concrete actions, natural user keywords, and would conflict with all other skills by design. The meta-nature of the skill (about using other skills) makes it poorly suited for the skill selection mechanism.
Suggestions
Reframe the description around specific user needs rather than 'any conversation' - identify what unique capability this skill provides that others don't
Add concrete actions the skill performs (e.g., 'Lists available skills, searches skill documentation, recommends appropriate skills for tasks')
Include natural trigger terms users might say like 'what skills are available', 'help me find a skill', 'which tool should I use'
| 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 'Use when' clause ('starting any conversation'), but the 'what' is weak and abstract. The trigger is too broad to be useful for skill selection among many options. | 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' would trigger for literally every interaction, creating maximum conflict with all other skills. This is the opposite of a clear niche. | 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 explains when and how to use skills. Its main strength is actionability - the decision flow, priority ordering, and red flags table provide concrete guidance. The main weakness is some verbosity in the red flags table and the inline dot graph that could be trimmed for token efficiency.
Suggestions
Condense the red flags table - many rows convey the same message ('check for skills first') and could be grouped or reduced
Consider removing or simplifying the dot graph - the textual description already conveys the workflow clearly
Move platform-specific instructions (Claude Code, Cursor, etc.) to a separate reference file to keep the main skill leaner
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some redundancy (the red flags table is verbose, the dot graph adds tokens without clear value, and some explanations could be tighter). The emphasis formatting and repetition of 'check for skills' across multiple rows adds bulk. | 2 / 3 |
Actionability | Provides concrete, specific guidance: exact tool names (Skill tool, TodoWrite), clear decision flow, specific platform instructions, and explicit priority ordering. The red flags table gives actionable pattern recognition. | 3 / 3 |
Workflow Clarity | The workflow is crystal clear with an explicit decision graph, numbered priority order, and clear sequencing (invoke → announce → check checklist → follow). For a meta-skill about skill usage, the single-action flow is unambiguous. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is inline in one file. References to README.md for tool developers is good, but the red flags table and platform-specific instructions could potentially be split out for a leaner overview. | 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.
- Repository
- projectbluefin/dakota
- Commit
f062bf8
- 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.