comprehensive-review-full-review

Use when working with comprehensive review full review

1.13x

Quality

23%

Does it follow best practices?

Impact

85%

1.13x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/comprehensive-review-full-review/SKILL.md

The canonical home for this skill is comprehensive-review-full-review in sickn33/agentic-awesome-skills

Quality

Content

38%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 lays out a well-sequenced multi-phase review orchestration with concrete agent prompts, but it is bloated with redundant prose, relies on apparently non-existent subagent types and unbound placeholders, and inlines everything that should be split into reference files. It also lacks the validation/feedback checkpoints a batch review process requires.

Suggestions

Move the per-phase agent prompts and the consolidated report templates into separate reference files (e.g. references/agent-prompts.md, references/report-templates.md) and point to them from SKILL.md, fixing the non-existent 'resources/implementation-playbook.md' path.

Add explicit validation checkpoints between phases, e.g. 'After Phase 2, verify findings are reproducible before passing context to Phase 3' and a retry loop for failed agent runs.

Remove the redundant '[Extended thinking: ...]' paragraph and trim buzzwords from the prompts; verify every subagent_type and placeholder variable is real and bound before publishing.

Dimension	Reasoning	Score
Conciseness	The '[Extended thinking: ...]' paragraph redundantly restates what the phase sections already show and the agent prompts are padded with buzzwords, making it noticeably verbose with several unnecessary explanatory sections; not 3 because the padding is substantial rather than minor.	2 / 5
Actionability	Concrete subagent prompts with specific analysis tasks are provided, but the subagent_type values appear non-executable/fabricated and placeholders like {phase1_architecture_context} are unbound, leaving incomplete executable guidance matching the score-3 pseudocode anchor.	3 / 5
Workflow Clarity	Phases are clearly sequenced 1-4 with dependency context, but this batch consolidation workflow has no validation checkpoints or error-recovery feedback loops before assembling the report; per the batch-operation cap, workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	The body is a ~140-line monolithic wall of inlined prompts and report templates that belong in separate reference files, and its single reference 'resources/implementation-playbook.md' does not exist; minimal structure for offloading content, matching the score-2 anchor.	2 / 5
	Total	10 / 20 Passed

Description

8%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 placeholder-grade trigger with no concrete capabilities, no natural user phrasing, and no 'what does this do' content, making it nearly indistinguishable from other skills. It needs to be rewritten to state the concrete review actions performed and the natural terms users say when they need a multi-dimensional code review.

Suggestions

Rewrite the description to state concrete actions, e.g. 'Orchestrates a multi-phase code review across quality, security, performance, testing, and documentation using specialized agents'.

Add a real 'when' trigger with natural user phrasing, e.g. 'Use when the user asks for a comprehensive, multi-dimensional code review or a prioritized remediation report'.

Replace the tautological 'comprehensive review full review' phrase with specific keywords users would actually say (code review, security audit, performance profiling, technical debt assessment).

Dimension	Reasoning	Score
Specificity	The description 'Use when working with comprehensive review full review' names no concrete actions or capabilities, only repeating the placeholder domain name; pure abstract tautology matching the score-1 anchor.	1 / 5
Completeness	A 'when' trigger clause is present but the 'what' (capability) is entirely missing, matching the score-2 anchor of 'only when present without what'; not 1 because a trigger exists, not 3 because nothing concrete is described.	2 / 5
Trigger Term Quality	'comprehensive review full review' is a non-natural placeholder string no user would actually say, with no synonyms or concrete trigger keywords, matching the score-1 anchor of only generic/technical jargon.	1 / 5
Distinctiveness Conflict Risk	The generic placeholder phrasing would conflict with virtually any review-related skill, matching the score-1 anchor of entirely generic with broad conflict risk.	1 / 5
	Total	5 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/comprehensive-review-full-review/SKILL.md
Commit: 57c135b

Reviewed: 2 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.