analyze-issue

Analyze a GitHub issue and create a detailed technical specification

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/git/skills/analyze-issue/SKILL.md

Quality

Content

68%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 gives an actionable, well-structured procedure with a concrete spec template and save path, but lacks validation/verification checkpoints in the workflow. It is concise and respects Claude's competence without over-explaining.

Suggestions

Add validation checkpoints, e.g. verify the fetched issue matches the requested number and confirm the spec file was saved successfully before reporting completion.

Tighten the vague steps ('Understand the requirements thoroughly', 'Review related code and project structure') into concrete actions such as 'read the issue body and extract acceptance criteria' and 'grep the codebase for modules referenced in the issue'.

Consider moving the spec template into a referenced file (e.g. references/spec-template.md) so the main body stays a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is lean: a short numbered procedure plus a spec template, with no padding or explanation of concepts Claude already knows; only minor template boilerplate keeps it off a 5.	4 / 5
Actionability	Provides concrete file-naming patterns, a referenced load procedure, a full spec template, and an exact save path with a worked example; a few vague steps ('Understand the requirements thoroughly', 'Review related code') prevent a 5.	4 / 5
Workflow Clarity	Steps are clearly sequenced (1-5 with a conditional fetch), but there are no validation checkpoints verifying the issue was fetched correctly or that the spec is complete, matching the 'sequence present but checkpoints missing' anchor.	3 / 5
Progressive Disclosure	Content is well-organized into a procedure and a template with clear headers, and the only external reference (.claude/commands/load-issues.md) is one level deep; no nested references, though the template could arguably live in its own file.	4 / 5
	Total	15 / 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 states a clear purpose and domain but omits any 'Use when' trigger guidance, which caps its completeness. It is reasonably distinct from other skills yet thin on natural trigger-term coverage.

Suggestions

Add an explicit trigger clause, e.g. 'Use when asked to analyze a GitHub issue or produce a technical spec for an issue number.'

Broaden trigger terms with synonyms users actually say: 'spec', 'ticket', 'issue number', 'technical design doc'.

List a couple more concrete actions (e.g. 'review related code', 'draft an implementation plan') to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('GitHub issue') and two concrete actions ('Analyze ... and create a detailed technical specification'), matching the '1-2 concrete actions' anchor; not comprehensive enough for a 4.	3 / 5
Completeness	Has a clear 'what' but no 'Use when...' or equivalent trigger guidance; per the guidelines a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains the natural term 'GitHub issue' and 'technical specification', but lacks common variations/synonyms like 'spec', 'issue number', or 'ticket' that users would actually say.	3 / 5
Distinctiveness Conflict Risk	Targets a fairly distinct niche (GitHub issue -> technical spec) with minimal overlap risk; not a 5 because it lacks explicit trigger phrases that fully separate it from general issue-handling skills.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: NeoLabHQ/context-engineering-kit
Path: plugins/git/skills/analyze-issue/SKILL.md
Commit: 23e2428

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.