task-analyzer

Performs metacognitive task analysis and skill selection. Use when determining task complexity, selecting appropriate skills, or estimating work scale.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a concise, highly actionable instruction skill that keeps heavy metadata in a single clearly signaled bundle file. Its only real weakness is workflow clarity: the multi-step analysis lacks explicit validation checkpoints before output is produced.

Suggestions

Add an explicit validation checkpoint before the Output Format step (e.g., 'Verify: every selected skill maps to a row in step 3 or 5 before emitting output').

Include a brief completeness check for the tag-matching step so unmatched tags are flagged rather than silently dropped.

Consider an explicit retry/feedback loop when no skill matches the extracted tags, to close the analysis workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean and reference-driven: dense decision tables and explicit rules ('Scale >= Large -> include documentation-criteria'), with no padding explaining concepts Claude already knows, fitting the score-3 anchor of lean and efficient where every token earns its place.	3 / 3
Actionability	Despite being an instruction-only skill with no code, guidance is concrete and executable: explicit scale thresholds, task-type-to-skill mappings, a fully specified output YAML schema with field semantics, and warning patterns paired with mitigations, satisfying the scoring note that actionable guidance is not penalized for lacking code.	3 / 3
Workflow Clarity	The 5-step analysis process (Understand -> Scale -> Type -> Tag Matching -> Implicit Relationships) is clearly sequenced, but there are no explicit validation checkpoints confirming analysis completeness before emitting output, fitting the score-2 anchor of steps listed with implicit or missing checkpoints.	2 / 3
Progressive Disclosure	SKILL.md is a well-organized overview with one clearly signaled, one-level-deep reference ('See [skills-index.yaml](references/skills-index.yaml)', a verified real file), with bulky metadata appropriately split into the bundle, matching the score-3 anchor of a clear overview with well-signaled one-level references.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 cleanly answers both what and when with an explicit 'Use when' trigger, and avoids first/second person. It is held back from top marks by somewhat abstract capability phrasing and trigger terms that could overlap with general planning skills.

Suggestions

Replace the abstract 'metacognitive task analysis' with concrete verbs users would recognize (e.g., 'Breaks down a task into type, scale, and required skills').

Add concrete trigger terms users naturally say (e.g., 'Use when a task spans multiple files, needs skill selection, or when unsure which skill applies').

Sharpen distinctiveness by naming the decision output (e.g., 'Returns a structured skill-selection plan') to separate it from generic planning skills.

Dimension	Reasoning	Score
Specificity	Names two actions ('Performs metacognitive task analysis and skill selection'), but 'metacognitive task analysis' is somewhat abstract rather than a list of multiple concrete actions, matching the score-2 anchor of naming domain and some actions but not comprehensively.	2 / 3
Completeness	It explicitly states both what ('Performs metacognitive task analysis and skill selection') and when ('Use when determining task complexity, selecting appropriate skills, or estimating work scale') with an explicit trigger clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	'Use when determining task complexity, selecting appropriate skills, or estimating work scale' provides natural phrasing users might say, but the terms are meta/abstract and miss common concrete variations, fitting the score-2 anchor of some relevant keywords missing common variations.	2 / 3
Distinctiveness Conflict Risk	'Metacognitive task analysis and skill selection' is a reasonably distinct niche, but 'task complexity' and 'work scale' could overlap with general planning/workflow skills, fitting the score-2 anchor of somewhat specific but could still overlap.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: shinpr/claude-code-workflows
Commit: 66e3b29

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.