recipe-implement

Orchestrate the complete implementation lifecycle from requirements to deployment

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

62%

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

The content is a thorough, well-sequenced orchestration playbook with strong workflow clarity, explicit validation feedback loops, and concrete subagent identifiers. Its weaknesses are heavy reliance on an external skill for the actual executable detail and repeated compliance directives that add token weight without proportional clarity.

Suggestions

Consolidate the repeated 'follow subagents-orchestration-guide' and 'MANDATORY' reminders into a single authoritative pointer to reduce token weight.

Move the detailed subagent response-field semantics and per-phase rules into a bundled reference file and link one level deep, improving progressive disclosure.

Add a short self-contained quick-start showing a concrete end-to-end example so the skill is actionable without the external guide.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense and procedural with little wasted explanation of concepts Claude already knows, but it repeats compliance directives ('MANDATORY', repeated reminders to follow subagents-orchestration-guide) and could be tightened.	2 / 3
Actionability	It gives concrete subagent_type identifiers and structured response-field checks (status, requiresTestReview, stub_detected), but execution of actual steps is delegated to an external skill and many instructions are references rather than self-contained, executable guidance.	2 / 3
Workflow Clarity	Multi-step processes are explicitly sequenced with validation checkpoints and feedback loops (the 4-step task cycle, post-implementation verify/fix cycle with re-run-on-failure, and [Stop] markers), satisfying the rubric's requirement for explicit validation steps.	3 / 3
Progressive Disclosure	The SKILL.md is well sectioned but is largely an inline reference to the external subagents-orchestration-guide skill rather than a one-level-deep bundle; no references/scripts/assets files exist, and much detail is inlined instead of split into navigable files.	2 / 3
	Total	9 / 12 Passed

Description

30%

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 technically in third person and names a domain, but it is high-level and generic, lacking concrete actions, natural trigger terms, and an explicit 'when to use' clause. Its broad framing creates significant overlap risk with other implementation-oriented skills.

Suggestions

Add concrete actions the skill performs, e.g. 'decomposes requirements into tasks, dispatches sub-agents per task, runs quality-fixer and security reviews, commits per task'.

Append an explicit trigger clause such as 'Use when implementing a feature or fix end-to-end from requirements, or when coordinating multi-agent implementation workflows'.

Narrow the language to a distinct niche (full-stack implementation orchestration via sub-agents) to reduce overlap with generic project-management skills.

Dimension	Reasoning	Score
Specificity	Names the domain (full-cycle implementation) and lists phase labels in parentheses, but these are abstract stage names rather than concrete actions; it does not enumerate specific operations.	2 / 3
Completeness	It states what the skill does (orchestrate the lifecycle) but lacks any 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	It contains only generic orchestration vocabulary ('implementation lifecycle', 'requirements to deployment') with no natural user phrasing such as 'implement a feature' or 'build from requirements'.	1 / 3
Distinctiveness Conflict Risk	'Orchestrate the complete implementation lifecycle from requirements to deployment' is extremely broad and would overlap with many general implementation or project-management skills.	1 / 3
	Total	6 / 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.