recipe-plan

Create work plan from design document and obtain plan approval

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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 tightly sequenced, highly actionable orchestration workflow with strong validation feedback loops, scoring well on actionability and workflow clarity. It loses points on conciseness due to orchestration meta-language and on progressive disclosure because it is a single inline document with no bundled reference files.

Suggestions

Trim orchestrator-identity meta-language (e.g. the "I am an orchestrator" framing and repeated delegation reminders) to lean out the token budget.

Move the detailed work-planner prompt-construction rules and subagents-orchestration-guide coordination spec into a referenced file, keeping SKILL.md an overview with one-level-deep links.

Consider a brief bundled reference listing the exact reviewer verdict branches and prompt templates so the main body stays a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-structured with minimal concept explanation, but sections like the duplicated "Core Identity / I am an orchestrator" framing and verbose orchestration meta-language add tokens that could be tightened toward the lean score-3 anchor.	2 / 3
Actionability	Steps give concrete, executable guidance: explicit subagent_type values ("dev-workflows:work-planner", "dev-workflows:document-reviewer"), exact prompt templates, a literal `ls -la docs/design/*.md \| head -10` command, and copy-paste response blocks.	3 / 3
Workflow Clarity	A clear 5-step sequence with explicit validation checkpoints and feedback loops: document-reviewer verdict branching (needs_revision → re-invoke and re-review until approved/approved_with_conditions; rejected → escalate), and a user-approval gate with re-run logic, matching the score-3 anchor.	3 / 3
Progressive Disclosure	Content is organized into clear sections, but the body is essentially monolithic inline instruction with no bundle files in references/scripts/assets; pointers to companion skills (subagents-orchestration-guide, acceptance-test-generator) are named but not structured as one-level-deep navigable references.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 in correct third person, naming the core actions and artifact, but it lacks an explicit "Use when..." trigger clause and broader natural keywords, which limits several dimensions. It reads as a competent score-2 description rather than a fully specified one.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to plan implementation work from a design document, review a work plan, or obtain plan approval."

Broaden natural trigger terms to include "planning phase", "work plan review", and "recipe planning" to improve trigger-term coverage and distinctiveness.

Expand the action list to name review and revision steps (e.g. "generate test skeletons, create and review a work plan, obtain approval") to reach the score-3 specificity anchor.

Dimension	Reasoning	Score
Specificity	"Create work plan from design document and obtain plan approval" names two concrete actions (create plan, obtain approval) and the source artifact, but stops short of listing multiple specific actions the way the score-3 anchor does.	2 / 3
Completeness	It answers "what" (create work plan, obtain approval) but the "when" is only implied; the judging guideline caps completeness at 2 when an explicit "Use when..." trigger clause is missing.	2 / 3
Trigger Term Quality	It contains relevant terms like "work plan", "design document", and "plan approval", but omits common natural variations a user would say (e.g. "planning", "plan review", "recipe planning") and has no explicit "Use when..." trigger phrasing.	2 / 3
Distinctiveness Conflict Risk	Tied to a fairly distinct niche (planning phase from a design document), but the generic phrasing could overlap with other planning/recipe skills, so it does not reach the clear-niche anchor of 3.	2 / 3
	Total	8 / 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.