recipe-build

Execute decomposed tasks in autonomous execution mode

Quality

31%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/recipe-build/SKILL.md

Quality

Discovery

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 critically weak across all dimensions. It relies on abstract jargon ('decomposed tasks', 'autonomous execution mode') without specifying concrete actions, natural trigger terms, or when the skill should be selected. It would be nearly impossible for Claude to reliably choose this skill from a pool of alternatives.

Suggestions

Replace abstract jargon with concrete actions: specify what types of tasks are executed (e.g., 'Runs multi-step workflows such as data processing pipelines, batch file operations, or sequential build steps').

Add an explicit 'Use when...' clause with natural trigger terms users would actually say (e.g., 'Use when the user asks to run a series of steps, automate a workflow, or execute a multi-part plan').

Clarify the unique niche of this skill to distinguish it from other task-execution or automation skills (e.g., specify the execution environment, the type of task decomposition, or the domain it applies to).

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like 'decomposed tasks' and 'autonomous execution mode' without specifying any concrete actions. It does not describe what kinds of tasks are executed or what the skill actually does.	1 / 3
Completeness	The description barely addresses 'what' (execute tasks) in extremely vague terms and completely lacks any 'when' guidance or explicit trigger clause.	1 / 3
Trigger Term Quality	The terms 'decomposed tasks' and 'autonomous execution mode' are technical jargon that users would almost never naturally say. There are no natural keywords a user would use to invoke this skill.	1 / 3
Distinctiveness Conflict Risk	'Execute decomposed tasks' is extremely generic and could overlap with virtually any skill that performs multi-step operations. There is nothing to distinguish this from other task-execution skills.	1 / 3
	Total	4 / 12 Passed

Implementation

62%

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 orchestration recipe with excellent workflow clarity, featuring clear decision tables, explicit validation checkpoints, and well-defined escalation paths. Its main weaknesses are moderate verbosity from repeated pattern-matching rules and the lack of fully executable commands for key operations. The skill would benefit from splitting some detailed subsections into referenced files and providing more concrete command examples.

Suggestions

Reduce redundancy by defining the Consumed Task Set pattern-matching rules once and referencing that definition, rather than restating the exclusion patterns in multiple sections.

Add concrete, copy-paste-ready commands for key operations like git commits, file deletion, and file listing (e.g., exact shell commands or tool invocations).

Split detailed subsections (Pre-execution Prerequisites, Post-Implementation Verification) into separate referenced files to improve progressive disclosure and reduce the monolithic feel.

Dimension	Reasoning	Score
Conciseness	The skill is fairly detailed and well-structured for a complex orchestration workflow, but contains some redundancy — the Consumed Task Set computation rules are repeated/referenced multiple times, and some sections (like the scope boundary block) could be tighter. It doesn't explain concepts Claude already knows, but the overall length could be reduced.	2 / 3
Actionability	The skill provides concrete steps, decision tables, and specific file patterns, which is good. However, it relies heavily on subagent invocations without providing executable code or exact command syntax for most operations. Key actions like 'Execute git commit' or 'Delete every file' lack specific commands. The TaskCreate step references 'Map preloaded skills to applicable concrete rules' which is unclear without more context.	2 / 3
Workflow Clarity	The multi-step workflow is exceptionally well-sequenced with explicit validation checkpoints at every stage: implementation readiness check → consumed task set computation → task generation decision flow → 4-step execution cycle with escalation branches → post-implementation verification with fix loops → final cleanup. Feedback loops are clearly defined (quality-fixer rejection → return to task-executor, verifier failure → consolidated fix cycle).	3 / 3
Progressive Disclosure	The skill references external skills (subagents-orchestration-guide) and subagent types but has no bundle files to support progressive disclosure. The content itself is a long monolithic document that could benefit from splitting detailed sections (e.g., Pre-execution Prerequisites, Post-Implementation Verification) into separate referenced files. The internal organization with headers is decent but the document is dense.	2 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 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: 68ecb4a

Reviewed: about 11 hours 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.