Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

recipe-plan

Create work plan from design document and obtain plan approval

Quality

73%

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 ./dev-workflows-fullstack/skills/recipe-plan/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 content is a tightly written orchestration recipe: a clearly sequenced five-step workflow with explicit approval checkpoints, review-resolution feedback loops, and concrete subagent invocation details. It is efficient and actionable with only minor trimmable meta-language and small gaps in fully specified prompt bodies. Progressive disclosure is handled well through clean section structure and a single clearly signaled external reference.

Dimension	Reasoning	Score
Conciseness	The body is dense and directive with no explanations of concepts Claude already knows, but a few convoluted meta-sentences ("Local authority gate: Make this recipe's workflow decisions and validate each returned result directly; delegate semantic deliverable production to the named specialist") could be trimmed, matching 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	Steps give concrete, near copy-paste guidance — exact subagent_types ("dev-workflows-fullstack:work-planner"), explicit fields (designDoc, prd, testSkeletons), the full document-reviewer prompt text, and edge cases (empty lanes, multiple design docs, declined findings) — with minor gaps such as the work-planner prompt body being field-listed only and the external "HC-06" reference.	4 / 5
Workflow Clarity	The five numbered steps are clearly sequenced with explicit validation (Review Resolution Gate through correction re-review and convergence), a mandatory approval stop ("Stop and obtain approval for plan content before completion"), and feedback loops for error recovery (user-requested changes re-invoke work-planner and re-run Step 4).	5 / 5
Progressive Disclosure	No bundle files exist, and the body is well organized into headed sections that keep everything appropriately self-contained, with one clearly signaled one-level-deep external reference ("read references/review-resolution.md from the loaded subagents-orchestration-guide skill"); at ~85 lines it exceeds the under-50-line simple-skill exception, so structure is good rather than exceptional.	4 / 5
	Total	17 / 20 Passed

Description

53%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 clear and reasonably specific about the what — creating a work plan from a design document and obtaining approval — but it entirely lacks a 'when to use' trigger clause and natural synonyms, capping completeness and trigger-term quality. It is mostly distinguishable from unrelated skills thanks to the design-document linkage. Adding an explicit 'Use when...' clause with natural user phrasings would lift the two weakest dimensions.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. "Use when the user asks to plan implementation from an approved design document or to create a work plan".

Include natural synonyms and variations users would say, such as "planning phase", "implementation plan", "design doc", and "plan approval", to broaden trigger-term coverage.

Mention the additional concrete actions the skill performs (test-skeleton generation and work-plan review) so the capability list is comprehensive rather than truncated to two actions.

Dimension	Reasoning	Score
Specificity	"Create work plan" and "obtain plan approval" name the planning domain with two concrete actions, but coverage is not comprehensive (test-skeleton generation and plan review are omitted), matching the 'names domain and 1-2 concrete actions' anchor rather than the 'several specific actions' anchor.	3 / 5
Completeness	The description clearly answers 'what' ("Create work plan from design document and obtain plan approval") but contains no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3; it is not 2 because the 'what' is clear rather than vague.	3 / 5
Trigger Term Quality	"work plan", "design document", and "plan approval" are relevant keywords, but common variations users would naturally say ("planning", "design doc", "implementation plan") are missing, matching 'some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	"work plan from design document" plus "plan approval" distinguishes the skill by concrete artifacts in a specific pipeline, making it mostly distinct with only minor overlap risk against closely related planning skills; it is not 5 because it lacks distinctive trigger phrases and "work plan" alone is generic.	4 / 5
	Total	13 / 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: dev-workflows-fullstack/skills/recipe-plan/SKILL.md
Revision: e9118a0

Reviewed: 17 hours ago

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.

recipe-plan

Table of Contents

Is this your skill?