recipe-diagnose

Investigate problem, verify findings, and derive solutions

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/recipe-diagnose/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 body is a well-sequenced orchestration recipe with strong workflow clarity, concrete sub-agent prompts, explicit validation checkpoints and feedback loops, and efficient procedural prose; its only weak spot is a monolithic single-file structure with no progressive disclosure of detail into reference files.

Dimension	Reasoning	Score
Conciseness	The body is dense procedural control with no concept-padding and assumes Claude's intelligence; minor redundancy (scope-envelope and coverage-disposition language restated across steps) keeps it just below the lean anchor of 5.	4 / 5
Actionability	Provides concrete sub-agent prompts with exact subagent_type, named field mappings, a mechanical-extraction instruction, expected JSON outputs, and enumerated quality-check checklists; placeholders like [user-reported problem verbatim] are inherent to dynamic input, leaving minor gaps versus copy-paste-ready.	4 / 5
Workflow Clarity	Steps 0-7 are explicitly ordered with an Execution Gate, Step 2 is an explicit quality-check checklist, Step 4 defines a convergence feedback loop (re-investigate named gaps then re-verify), and a Completion Criteria checklist closes the process, matching the anchor for explicit validation with feedback loops and checklists.	5 / 5
Progressive Disclosure	No bundle files exist and the single SKILL.md is well-organized with clear headers and no nested references, but at ~260 lines it is monolithic with report templates and checklists inlined rather than split into reference files, keeping it below the one-level-deep reference anchor of 5.	4 / 5
	Total	17 / 20 Passed

Description

50%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 conveys a clear three-phase methodology but is domain-generic, lacks a 'Use when' trigger clause, and omits natural synonyms, leaving it broadly applicable and at risk of overlapping with other diagnosis skills.

Suggestions

Add an explicit 'Use when...' clause with concrete triggers, e.g. 'Use when diagnosing the root cause of bugs, errors, or unexpected behavior'.

Include natural user synonyms such as 'diagnose', 'debug', 'troubleshoot', and 'root cause' to improve trigger-term matching.

Narrow the problem domain (e.g., software/code defects) to reduce overlap with unrelated investigative skills.

Dimension	Reasoning	Score
Specificity	Lists three named action phases ('Investigate problem', 'verify findings', 'derive solutions') but names no concrete domain, matching the anchor for 1-2 concrete actions without comprehensive coverage; not a 4 because the actions are generic verbs with no specifics.	3 / 5
Completeness	The 'what' is reasonably clear (investigate, verify, derive solutions) but the 'when' is entirely absent with no 'Use when...' clause, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	'Investigate' and 'problem' are semi-natural, but there is no 'Use when' trigger phrasing and no common synonyms like 'diagnose', 'debug', 'root cause', or 'troubleshoot', matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Investigate problem' is generic enough to overlap with many debugging/diagnosis skills, but the explicit three-phase investigate-verify-derive framing provides some specificity, placing it at the low end of anchor 3 rather than 2.	3 / 5
	Total	12 / 20 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-diagnose/SKILL.md
Commit: 83cf695

Reviewed: about 22 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.