CtrlK
BlogDocsLog inGet started
Tessl Logo

comprehensive-review-full-review

Use when working with comprehensive review full review

32

Quality

25%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/comprehensive-review-full-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The content is a well-sequenced multi-phase code-review orchestration workflow with concrete subagent prompts, but it is verbose, lacks validation/feedback checkpoints, leaves placeholder interpolation undefined, and keeps everything inline with no progressive disclosure to reference files.

Suggestions

Add explicit validation/feedback checkpoints between phases (e.g., 'Review Phase 1 outputs; only proceed to Phase 2 once critical issues are triaged') to lift workflow clarity.

Define how {phase1_architecture_context} and similar placeholders are populated, or replace them with concrete instructions for the orchestrating agent to thread context.

Trim the [Extended thinking: ...] block and tighten agent prompts; consider moving per-phase prompt templates into a reference file referenced one level deep.

DimensionReasoningScore

Conciseness

The body is structured and avoids explaining basic concepts Claude knows, but it is verbose — the [Extended thinking: ...] block and lengthy agent prompts add tokens that could be tightened — matching the mostly-efficient-but-could-be-tightened anchor.

2 / 3

Actionability

It gives concrete subagent_type values and copy-able prompt templates, but the placeholder interpolation (e.g. {phase1_architecture_context}) is never defined and the prompts are not executable code, matching the some-concrete-guidance-but-incomplete anchor.

2 / 3

Workflow Clarity

Phases are clearly sequenced with explicit context flow between them, but there are no validation checkpoints or error-recovery feedback loops in this complex pipeline, which caps clarity at the steps-listed-but-validation-gaps anchor.

2 / 3

Progressive Disclosure

The ~140-line body is organized with clear headers but is monolithic and inline-heavy with no reference files (none exist in the bundle), matching the some-structure-but-could-be-better-organized/content-should-be-separate anchor.

2 / 3

Total

8

/

12

Passed

Description

0%

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 placeholder: it states only a meaningless 'when' trigger with no actions, no natural keywords, and no distinguishable niche. It fails to tell Claude what the skill does or when to genuinely use it.

Suggestions

Rewrite the description to name concrete actions, e.g. 'Orchestrates a multi-phase code review across code quality, security, performance, testing, and CI/CD using specialized subagents'.

Add natural trigger terms users would actually say, such as 'code review', 'security audit', 'review a pull request', or 'comprehensive code review'.

Combine what-and-when in one sentence, e.g. '...Use when the user asks for a comprehensive, multi-dimensional code review or security/performance audit of a codebase.'

DimensionReasoningScore

Specificity

The description 'Use when working with comprehensive review full review' names no concrete actions at all, only a meaningless 'when' clause, matching the vague/no-actions anchor rather than the anchor that requires naming some actions.

1 / 3

Completeness

It answers neither 'what does this do' (entirely missing) nor a meaningful 'when' (the trigger is filler), so it falls in the missing-what-OR-weak-when anchor.

1 / 3

Trigger Term Quality

'comprehensive review full review' is a redundant, non-natural phrase no user would actually say; there are no natural trigger keywords, matching the no-natural-keywords anchor.

1 / 3

Distinctiveness Conflict Risk

The phrase is maximally generic and would conflict with virtually any other review-related skill, matching the very-generic/conflicts-with-many-skills anchor.

1 / 3

Total

4

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rmyndharis/antigravity-skills
Reviewed

Table of Contents

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.