recipe-task
Execute tasks following appropriate rules with rule-advisor metacognition
31
25%
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/recipe-task/SKILL.mdQuality
Discovery
0%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 extremely vague and abstract, providing no concrete actions, no natural trigger terms, and no guidance on when to use the skill. It reads more like a philosophical statement about metacognition than a functional skill description. It would be nearly impossible for Claude to correctly select this skill from a pool of available options.
Suggestions
Replace abstract language with concrete actions: specify exactly what tasks this skill performs and in what domain (e.g., 'Validates code changes against project-specific linting rules and style guidelines').
Add an explicit 'Use when...' clause with natural trigger terms that users would actually say (e.g., 'Use when the user asks about rule compliance, coding standards, or style checking').
Define the specific niche this skill occupies to distinguish it from other skills — what makes 'rule-advisor metacognition' different from general task execution?
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses entirely abstract language ('execute tasks', 'appropriate rules', 'rule-advisor metacognition') with no concrete actions specified. There is no indication of what domain or specific capabilities this skill provides. | 1 / 3 |
Completeness | Both 'what' and 'when' are extremely weak. The description does not explain what the skill concretely does, nor does it provide any explicit trigger guidance or 'Use when...' clause. | 1 / 3 |
Trigger Term Quality | The terms used ('rule-advisor metacognition', 'appropriate rules') are technical jargon that no user would naturally say. There are no natural keywords that would help Claude match user requests to this skill. | 1 / 3 |
Distinctiveness Conflict Risk | 'Execute tasks following appropriate rules' is maximally generic and could apply to virtually any skill. There is nothing distinctive that would help Claude differentiate this from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
50%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 reasonable high-level workflow for metacognitive task execution using a rule-advisor subagent, but it lacks the concrete examples, validation checkpoints, and supporting references needed to be truly actionable. The process is clear in sequence but abstract in execution details—Claude would need to infer much about the actual JSON structures, tool parameters, and error handling. The repeated references to rule-advisor output fields without showing their actual shape reduces practical utility.
Suggestions
Add a concrete example of the rule-advisor JSON response structure showing what fields like `taskAnalysis.essence`, `selectedRules`, and `metaCognitiveGuidance` actually look like.
Include an explicit validation/verification step before completion—e.g., checking that all selected rules were applied and warningPatterns were addressed, with a feedback loop if issues are found.
Provide a concrete example of the Agent tool invocation with actual parameter values rather than just listing parameter names.
Add a brief example of a TaskCreate call showing how rule-advisor output maps to task descriptions and priorities.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content has some redundancy—repeating 'rule-advisor' and 'from rule-advisor' excessively, and restating concepts like 'selected rules' multiple times. However, it's not egregiously verbose and mostly stays focused on the process. | 2 / 3 |
Actionability | It provides a structured process with specific tool invocations (Agent tool with subagent_type, TaskCreate, TaskUpdate) and references to JSON response fields, but lacks concrete executable examples—no actual JSON schemas, no sample inputs/outputs, and relies on abstract references like '$ARGUMENTS' and field paths without showing what they look like. | 2 / 3 |
Workflow Clarity | The four steps are clearly sequenced and logically ordered, but there are no validation checkpoints or feedback loops. Step 4 says to 'monitor warningPatterns flags' but provides no concrete mechanism for what to do when issues are detected, and there's no verification step before completion. | 2 / 3 |
Progressive Disclosure | The content is reasonably structured with clear step headers, but it's a monolithic file with no references to supporting documentation. The rule-advisor's JSON response schema, the TaskCreate/TaskUpdate APIs, and the rule format are all referenced but never linked to any documentation, leaving gaps in discoverability. | 2 / 3 |
Total | 8 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- shinpr/claude-code-workflows
- Commit
adf2e4d
- 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.