recipe-build

Execute materialized task files in autonomous execution mode

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/recipe-build/SKILL.md

Quality

Content

81%Weight 40%Scale 1-5

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 well-sequenced orchestration recipe with strong workflow clarity: explicit phases, validation gates, feedback loops, and a checklist. It is lean and actionable, with minor room to tighten dense jargon and surface cross-skill references more clearly.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with no padding about concepts Claude already knows; a few over-specified sentences (e.g. 'Corrections produced outside that cycle reuse its executor-result branching and quality gate, and defer only the commit...') could be trimmed, matching the 'efficient; minor instances of over-explanation' anchor rather than fully lean (5) or padded (3).	4 / 5
Actionability	It gives concrete executable guidance for an instruction-only orchestration skill: specific subagent_type values ('dev-workflows:task-executor', 'dev-workflows:task-decomposer') and named fields (task_file, diffBase, mutationEvidence) with explicit status routing; minor gaps remain where routing defers to external skills ('Apply subagents-orchestration-guide Specialist Result Acceptance'), so not 5.	4 / 5
Workflow Clarity	A clear phased sequence (Prerequisites -> Materialization -> Checklist -> 4-step Cycle -> Post-Implementation Review -> Final Cleanup -> Completion Report) with explicit validation gates (quality-fixer 'approved'/'verification_incomplete', Commit Boundary Check, Review Resolution convergence), feedback loops (stub_detected/needs_revision -> retry), a decision-flow table, and a checklist; the batch-operation cap at 3 does not apply because validation checkpoints are present throughout.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections and delegates detail one level deep to named sibling skills (subagents-orchestration-guide, llm-friendly-context) with no own-bundle files; not score 5 because several references are buried in dense prose rather than cleanly signposted, and not score 3 because the section structure and named cross-skill references are genuinely navigable.	4 / 5
	Total	17 / 20 Passed

Description

42%Weight 40%Scale 1-5

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 is concise and states a clear purpose but is jargon-heavy, lacks natural trigger terms, and omits any 'when to use' guidance. It is moderately distinct within an orchestration skill family.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when the user asks to run, execute, or batch-process materialized task files from a work plan in autonomous mode.'

Soften jargon with natural synonyms users would say ('run task files', 'batch-execute tasks', 'work plan execution') to improve trigger-term quality.

Briefly enumerate 1-2 more concrete actions (e.g. 'execute task files, run per-task quality gates, commit, and clean up') to lift specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain ('materialized task files') and one concrete action ('Execute') plus a mode ('autonomous execution mode'), matching the '1-2 concrete actions, not comprehensive' anchor; it is more specific than a bare 'Processes PDF files' (score 2) but lists no multiple actions (score 4).	3 / 5
Completeness	It states a clear 'what' (execute materialized task files in autonomous execution mode) but provides no 'when'/Use-when clause at all, which caps completeness at 3 per the judging guidelines; not score 4 because no trigger guidance is present.	3 / 5
Trigger Term Quality	Phrases like 'materialized task files' and 'autonomous execution mode' are technical jargon a user would rarely say naturally; it has a couple of generic keywords ('execute', 'task files') but misses the natural phrases users would actually use, fitting the score-2 anchor rather than the jargon-only score 1 or the keyword-coverage of score 3.	2 / 5
Distinctiveness Conflict Risk	It targets a specific niche (task-set execution) but shares the orchestration domain with sibling skills like work-planner and task-decomposer referenced in the body, giving real overlap risk; not score 4 because the family overlap is non-trivial.	3 / 5
	Total	11 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: shinpr/claude-code-workflows
Path: skills/recipe-build/SKILL.md
Commit: 9b7f687

Reviewed: 2 days 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.