comprehensive-review-full-review

Use when working with comprehensive review full review

Quality

22%

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 ./.agent/skills/comprehensive-review-full-review/SKILL.md

Quality

Content

25%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 an unfinished skeleton: generic filler bullets, a leftover meta-narrative block, a truncated Phase 1 with no steps, and twelve links to sub-skill files that are absent from the bundle. Almost nothing in it is executable as written.

Suggestions

Delete the '[Extended thinking: ...]' narration block and the generic bullets ('Clarify goals', 'Apply relevant best practices'), replacing them with the actual orchestration steps: which agent to launch, with what prompt, and in what order.

Complete the phase sequence (Phases 1-N) with concrete steps per phase and an explicit consolidation/validation step before reporting findings, since review output drives remediation.

Fix progressive disclosure: either ship the referenced sub-skills/*.md and resources/implementation-playbook.md files or remove the dead links, and give each remaining reference a one-line description of when to open it.

Dimension	Reasoning	Score
Conciseness	The bracketed '[Extended thinking: ...]' paragraph is pure meta-narration that instructs nothing, and bullets like 'Clarify goals, constraints, and required inputs' or 'Apply relevant best practices and validate outcomes' state things Claude already knows. It is noticeably padded (anchor 2) though not a long wall of background explanation (anchor 1).	2 / 5
Actionability	The only semi-concrete content is the flags list (--security-focus, --framework [name], etc.); Phase 1 says 'Use Task tool to orchestrate quality and architecture agents in parallel:' and then stops with no steps, prompts, or commands. This is high-level hints missing the specifics to execute — anchor 2.	2 / 5
Workflow Clarity	A phased multi-agent workflow is announced but only 'Phase 1' exists and it contains zero steps; no phases 2+ and no validation checkpoints anywhere. This matches anchor 2's 'rough sequence present but many gaps; steps poorly defined; validation absent' rather than anchor 3, which requires actual listed steps.	2 / 5
Progressive Disclosure	The body lists 12 one-level-deep sub-skill links plus 'resources/implementation-playbook.md', but none of these files exist in the bundle (no references/, scripts/, assets/, resources/, or sub-skills/ directories), so every reference dead-ends. Structure exists on paper but navigation is broken — anchor 2, not 4.	2 / 5
	Total	8 / 20 Passed

Description

20%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 a near-empty template: it restates the skill name twice, provides no capability statement, and offers only a generic trigger phrase. It would rarely be selected for the right task and is indistinguishable from other review skills.

Suggestions

State what the skill does in third person with concrete actions, e.g. 'Orchestrates multi-agent code review covering quality, security, performance, testing, and documentation; consolidates findings into prioritized remediation guidance.'

Add natural trigger terms users would actually say, such as 'code review', 'review my PR', 'review staged changes', or 'security review', instead of repeating 'comprehensive review full review'.

Combine the 'what' and 'when' in one sentence, e.g. '...Use when the user asks for a thorough, multi-dimensional review of a codebase or pull request.'

Dimension	Reasoning	Score
Specificity	The description 'Use when working with comprehensive review full review' names no concrete action or capability at all — only the abstract phrase 'working with comprehensive review full review'. This matches the anchor 'Entirely vague; no concrete actions; pure abstract language'.	1 / 5
Completeness	Only a 'when' clause is present ('Use when working with...') with no statement of what the skill does, matching anchor 2's 'only when is present without what'. Anchor 3 is excluded because no clear 'what' exists.	2 / 5
Trigger Term Quality	The only keyword-like terms are 'comprehensive review' and 'full review', which are generic; natural phrases users would say ('code review', 'review my PR', 'review changes') are missing. This sits between the jargon-only anchor 1 and the relevant-keywords anchor 3, matching anchor 2's 'one or two generic keywords'.	2 / 5
Distinctiveness Conflict Risk	'Comprehensive review' is very broad and would overlap heavily with any code-review, PR-review, or security-review skill, matching anchor 2's 'Very broad; high overlap risk with many similar skills'.	2 / 5
	Total	7 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 12 missing	Warning

	Total	14 / 16 Passed

Repository: Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI
Path: .agent/skills/comprehensive-review-full-review/SKILL.md
Commit: c4a059b

Reviewed: 1 hour 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.