task-analyzer
Performs metacognitive task analysis and skill selection. Use when determining task complexity, selecting appropriate skills, or estimating work scale.
57
64%
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/task-analyzer/SKILL.mdQuality
Discovery
52%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has good structural completeness with explicit 'what' and 'when' clauses, but suffers from abstract, jargon-heavy language that users would not naturally use. The capabilities described are meta-level and somewhat vague—'metacognitive task analysis' and 'skill selection' don't convey concrete, tangible actions. The trigger terms are unlikely to match natural user language.
Suggestions
Replace jargon like 'metacognitive task analysis' with natural language users would actually say, such as 'break down complex tasks', 'figure out what approach to take', or 'plan how to tackle a problem'.
Add more concrete, specific actions—e.g., 'Breaks tasks into subtasks, estimates effort level, routes work to the appropriate skill or tool' instead of abstract phrases like 'determining task complexity'.
Include natural trigger terms users might say, such as 'how should I approach this', 'what's the best way to do this', 'plan', 'break down', or 'estimate effort'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('metacognitive task analysis and skill selection') and some actions ('determining task complexity, selecting appropriate skills, estimating work scale'), but these are fairly abstract and not concrete actions like 'extract text' or 'fill forms'. | 2 / 3 |
Completeness | It explicitly answers both 'what' (performs metacognitive task analysis and skill selection) and 'when' (Use when determining task complexity, selecting appropriate skills, or estimating work scale) with a clear 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Terms like 'metacognitive task analysis' and 'skill selection' are internal/technical jargon that users would never naturally say. Users would say things like 'how complex is this task' or 'which tool should I use', not 'metacognitive task analysis'. | 1 / 3 |
Distinctiveness Conflict Risk | The concept of 'skill selection' and 'task complexity' is somewhat meta and could overlap with planning, orchestration, or routing skills. However, the specific combination of metacognitive analysis and work scale estimation provides some distinctiveness. | 2 / 3 |
Total | 8 / 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 analytical skill with clear decision tables and a concrete output format that makes it highly actionable. The workflow is logically sequenced with explicit rules at each step. The main weaknesses are moderate verbosity (some tables explain things Claude already knows) and all content being inline rather than leveraging reference files for secondary concerns like warning patterns and metacognitive questions.
Suggestions
Trim the Surface Work → Fundamental Purpose table; Claude already understands these mappings. Replace with a brief instruction like 'Identify the fundamental purpose beyond the surface-level request.'
Consider moving Warning Patterns and Metacognitive Question Design into separate reference files to reduce the main skill's token footprint and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured with tables for quick reference, but includes some unnecessary explanation (e.g., the Surface Work → Fundamental Purpose table explains concepts Claude already understands like 'Fix this bug = Problem solving'). The implicit relationships table and metacognitive question design section add bulk that could be trimmed. | 2 / 3 |
Actionability | The skill provides concrete, structured guidance with specific YAML output formats, explicit matching rules, clear decision tables for scale/type/priority, and a worked example of tag-based skill matching. The instructions are specific enough to be directly executable. | 3 / 3 |
Workflow Clarity | The 5-step process is clearly sequenced (Understand → Estimate Scale → Identify Type → Tag Match → Implicit Relationships) with explicit decision rules at each step (e.g., 'Scale >= Large → include documentation-criteria'). Warning patterns serve as validation checkpoints. For this analytical/non-destructive task, the workflow is appropriately structured. | 3 / 3 |
Progressive Disclosure | The skill references skills-index.yaml appropriately, but the body itself is fairly long with all content inline. The metacognitive question design and warning patterns sections could potentially be split into reference files. However, no bundle files are provided to verify the referenced skills-index.yaml exists, which weakens the progressive disclosure structure. | 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
- 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.