skill-staged-review

Use when a PR or feature needs both specification and code-quality review

Quality

66%

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 ./.claude/skills/skill-staged-review/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with real executable scripts and a clear staged-gate workflow, but it is verbose, monolithic, and lacks the validation feedback loops and file-splitting that would lift conciseness, workflow clarity, and progressive disclosure to the top level.

Suggestions

Extract the stub-detection and octopus-dispatch bash into scripts/ files referenced from SKILL.md to improve both conciseness and progressive disclosure.

Add an explicit validate->fix->revalidate loop for the batch stub-detection step rather than only emitting warnings.

Gate the outward gh pr comment step on an explicit user confirmation checkpoint before posting.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable rather than concept-explaining, but at ~315 lines it carries heavy inline bash blocks and repeated report templates that could be tightened or externalized, fitting the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	It provides fully executable, copy-paste-ready bash for intent loading, a 5-check stub-detection loop, multi-LLM dispatch via orchestrate.sh, and gh pr comment posting, matching the executable-and-specific anchor.	3 / 3
Workflow Clarity	The two-stage sequence and Stage 1 gate table are clear, but the batch stub-detection and outward PR-posting steps lack an explicit validate->fix->retry loop, so per the destructive/batch guideline workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	The skill is a single ~315-line file with no references/scripts/assets bundle; inline scripts and report templates that should be separate files are kept in the body, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 has an explicit Use-when trigger that answers both what and when, but it undersells concrete actions and relies on the trigger field for full trigger coverage, leaving specificity and distinctiveness at the mid level.

Suggestions

Add 2-3 concrete actions to the description (e.g., 'validate success criteria, detect stubs, and run multi-LLM quality review') to raise specificity.

Surface one or two natural trigger phrases (e.g., 'staged review', 'two-stage review') directly in the description rather than only in the trigger field.

Sharpen distinctiveness by contrasting with quick code review, e.g. 'for major features needing spec + code-quality review, not quick PR checks'.

Dimension	Reasoning	Score
Specificity	Names the domain and the two review types ('specification and code-quality review') but lists no concrete actions such as validate-success-criteria or stub-detection, matching the 'names domain and some actions' anchor rather than the multiple-concrete-actions level.	2 / 3
Completeness	It explicitly answers both what (spec + code-quality review) and when via an explicit 'Use when a PR or feature needs...' clause, matching the both-what-and-when-with-explicit-triggers anchor.	3 / 3
Trigger Term Quality	Description includes natural terms ('PR', 'feature', 'specification', 'code-quality review') but the richer trigger variants live in the trigger field, not the description; coverage is present but missing common variations.	2 / 3
Distinctiveness Conflict Risk	'Specification and code-quality review' is a somewhat specific niche but the description text itself still overlaps with generic code-review skills, fitting the 'could still overlap with similar skills' anchor.	2 / 3
	Total	9 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-staged-review/SKILL.md
Commit: 9f39f0c

Reviewed: 7 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.