recipe-plan

Create work plan from design document and obtain plan approval

Quality

67%

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-plan/SKILL.md

Quality

Content

85%

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 tight, highly actionable orchestration guide with exact tool parameters, a well-sequenced five-step workflow, and explicit review/approval feedback loops. Its only weakness is mild redundancy from repeated cross-references to the subagents-orchestration-guide skill.

Suggestions

Consolidate the repeated "Follow subagents-orchestration-guide" directives into a single reference near the top to reduce redundancy.

Remove the filler line "Follow the planning process below:" since the "## Execution Process" heading already signals what follows.

Dimension	Reasoning	Score
Conciseness	The body is largely procedural and delegates detail to peer skills rather than re-explaining concepts, but it repeats the cross-reference to subagents-orchestration-guide in several places and includes a redundant "Follow the planning process below:" line just before the Execution Process heading, fitting the anchor for mostly efficient content that could be tightened.	2 / 3
Actionability	Steps give exact, executable parameters: concrete subagent_type values ("dev-workflows:work-planner", "dev-workflows:document-reviewer"), an actual shell command (`! ls -la docs/design/*.md \| head -10`), and a precise conditional prompt-construction recipe for lane status, matching the anchor for fully concrete, copy-paste-ready guidance.	3 / 3
Workflow Clarity	A clear five-step sequence is present with explicit validation checkpoints and a feedback loop in Step 4 (branch on verdict.decision, re-review until approved/approved_with_conditions, escalate repeated blockers and rejections) plus an approval gate in Step 5, matching the anchor for clear sequencing with explicit validation and error-recovery loops.	3 / 3
Progressive Disclosure	No bundle files exist; the body is a well-sectioned overview (Scope Boundaries, Execution Process steps, Response at Completion) with one-level-deep, clearly signaled references to peer skills (subagents-orchestration-guide, acceptance-test-generator, work-planner, document-reviewer) rather than nested file chains, matching the anchor for a clear overview with well-signaled one-level references.	3 / 3
	Total	11 / 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 states concrete actions in a clear domain but is missing an explicit "when to use" trigger clause and natural trigger variations, which caps both completeness and trigger quality at 2. It is distinct enough to avoid most conflicts but would benefit from explicit trigger guidance.

Suggestions

Append an explicit trigger clause, e.g. "Use when starting the planning phase from an approved design document, before any implementation begins."

Add natural trigger variations users would say (e.g. "work plan", "planning phase", "plan approval", "break down the design doc") to improve trigger-term coverage.

Optionally surface the secondary actions (test skeleton generation, plan review) so specificity reflects the full workflow rather than only two steps.

Dimension	Reasoning	Score
Specificity	The description names two concrete actions ("Create work plan from design document" and "obtain plan approval") in a specific domain, but the verbs are somewhat high-level and the body reveals several more actions (test skeleton generation, review loop) not captured here, matching the anchor that names a domain and some actions without being comprehensive.	2 / 3
Completeness	It clearly states what the skill does ("Create work plan from design document and obtain plan approval") but provides no explicit "when to use it" trigger, so per the guideline a missing Use-when clause caps completeness at 2.	2 / 3
Trigger Term Quality	It contains a couple of relevant keywords a user in this workflow might say ("work plan", "design document", "plan approval") but offers no "Use when..." phrasing and no common variations, fitting the anchor for some relevant keywords missing common variations.	2 / 3
Distinctiveness Conflict Risk	The planning niche (design doc -> work plan -> approval) is fairly specific, but without explicit trigger terms it could overlap with general planning or implementation-planning skills, matching the anchor for somewhat specific but still potentially overlapping.	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
Path: skills/recipe-plan/SKILL.md
Commit: 56ab6c1

Reviewed: 4 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.