skill-tuning
Universal skill diagnosis and optimization tool. Detect and fix skill execution issues including context explosion, long-tail forgetting, data flow disruption, and agent coordination failures. Supports Gemini CLI for deep analysis. Triggers on "skill tuning", "tune skill", "skill diagnosis", "optimize skill", "skill debug".
82
78%
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 ./.claude/skills/skill-tuning/SKILL.mdQuality
Discovery
100%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 is a strong skill description that clearly communicates its purpose, lists specific capabilities with concrete issue types it addresses, and provides explicit trigger terms. It uses proper third-person voice throughout and is concise without being vague. The only minor note is that 'Universal skill diagnosis and optimization tool' is slightly grandiose as an opener, but the rest of the description backs it up with specifics.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Detect and fix skill execution issues including context explosion, long-tail forgetting, data flow disruption, and agent coordination failures.' Also mentions Gemini CLI support for deep analysis. | 3 / 3 |
Completeness | Clearly answers both what ('Detect and fix skill execution issues including context explosion, long-tail forgetting, data flow disruption, and agent coordination failures') and when ('Triggers on "skill tuning", "tune skill", "skill diagnosis", "optimize skill", "skill debug"'). | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger terms: 'skill tuning', 'tune skill', 'skill diagnosis', 'optimize skill', 'skill debug'. These are terms users would naturally say when needing this functionality, with good variation coverage. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around skill diagnosis and optimization with very specific trigger terms like 'skill tuning' and 'skill debug' that are unlikely to conflict with other skills. The specific issue types (context explosion, long-tail forgetting) further distinguish it. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%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-organized overview of a complex diagnostic and optimization workflow with strong progressive disclosure and clear navigation to supporting documents. Its main weaknesses are that actionability is limited since nearly all concrete implementation details are deferred to external files, and the workflow lacks explicit inline validation/error recovery steps. Some sections (architecture diagram, workflow table, action reference) have overlapping content that could be consolidated.
Suggestions
Add at least one concrete, inline example of a diagnosis detection pattern or fix implementation so the skill body itself is actionable without requiring external file reads.
Include explicit validation/error recovery instructions in the workflow section (e.g., 'If action-verify fails: review state.issues, re-run action-propose-fixes, re-apply') rather than deferring entirely to orchestrator.md.
Consolidate the architecture diagram, workflow table, and action reference table to reduce redundancy—consider merging the workflow and action reference into a single annotated workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but includes some redundancy—the architecture diagram, workflow table, and action reference table overlap significantly. The priority table and state JSON schema are useful but the overall document could be tightened by consolidating overlapping sections. | 2 / 3 |
Actionability | The usage examples show invocation patterns, and the state JSON schema is concrete. However, the actual diagnosis and fix logic is entirely deferred to external files—the skill body itself contains no executable code, detection patterns, or concrete fix implementations. The actions are named but not defined here. | 2 / 3 |
Workflow Clarity | The workflow table provides a clear sequence of steps with orchestrator decisions, and the architecture diagram shows the flow. However, validation/verification is mentioned only as a step in the table ('action-verify') without explicit feedback loops or error recovery instructions in the main body—these are deferred to phases/orchestrator.md. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview in the main file and well-signaled one-level-deep references to specs, phases, and action implementations. The reference documents table at the end provides clean navigation to all supporting files. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- catlog22/Claude-Code-Workflow
- Commit
0f8e801
- 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.