Tessl • The management layer for AI agent skills

A tight, highly actionable review workflow with concrete commands, a specific architecture checklist, and clean structure that earns full marks on conciseness and progressive disclosure. The main weaknesses are the undefined $SCOPE variable, an unspecified report format, and the absence of error-recovery guidance when automated checks fail.

Suggestions

Define the scope variable consistently: replace "$SCOPE" in step 2b with "$ARGUMENTS" (or define $SCOPE) so the command is executable as written (actionability).

Specify the report structure and what each verdict (Approved | With caveats | Requires changes) requires, so output is deterministic (actionability).

Add a brief step for handling failed checks (e.g., whether failures auto-classify as VIOLATION or block approval) to close the feedback-loop gap (workflow_clarity).

Dimension	Reasoning	Score
Conciseness	The body is lean and checklist-driven ("Services: no try/catch, no transformation, fetch only"; "Adapters: pure functions") with zero padding and no explanation of concepts Claude already knows like git or npx, so every token earns its place.	5 / 5
Actionability	Steps 1-2 provide copy-paste-ready commands (git diff, npx astro check, eslint, vitest) plus a concrete pattern checklist, but "$SCOPE" in step 2b is never defined (the Scope line uses "$ARGUMENTS") and the report format and verdict criteria are unspecified, leaving minor gaps.	4 / 5
Workflow Clarity	The numbered sequence 1-5 is clear and the automated checks plus "/review-check-architecture $SCOPE" act as validation checkpoints, but there is no feedback loop instructing what to do when checks fail; since the skill is analytical rather than destructive or batch, the cap-at-3 rule does not apply.	4 / 5
Progressive Disclosure	The skill is under 50 lines with well-organized sections and no bundle files; its only references (docs/ARCHITECTURE.md and /review-check-architecture) are clearly signaled and one level deep, meeting the simple-skill exception for a top score.	5 / 5
	Total	18 / 20 Passed

Description

75%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.

A concise, third-person description that clearly states both what it does and when to use it, with concrete validation actions. It falls just short of top marks on trigger-term coverage and distinctiveness because it lacks common synonyms (PR, code review) and overlaps slightly with security/test-focused skills.

Suggestions

Add natural trigger phrases such as 'pull request', 'PR', or 'code review' to the when-clause to broaden keyword coverage (trigger_term_quality).

Lead the when-clause with the most common user phrasing, e.g. 'Use when asked to review a PR, code changes, or a diff before merge' to sharpen completeness and distinctiveness.

Dimension	Reasoning	Score
Specificity	"validates architecture, types, security, and test coverage" lists four concrete actions in a named domain (pre-merge code review), matching the anchor for several specific actions with minor gaps; it stops short of comprehensive since it omits classification and report/verdict outputs the skill actually performs.	4 / 5
Completeness	Both parts are explicit: "Use when code changes need review before merge" answers when, and "validates architecture, types, security, and test coverage" answers what; the when-clause could be more specific with concrete trigger phrases, which keeps it below a 5.	4 / 5
Trigger Term Quality	Natural terms like "code changes", "review", "merge", and "test coverage" are present, but common user phrasings such as "pull request", "PR", and "code review" are missing, placing it at good-but-not-comprehensive keyword coverage.	4 / 5
Distinctiveness Conflict Risk	The pre-merge framing carves a clear niche, but the "security" and "test coverage" validation claims overlap with dedicated security-review and testing skills, presenting minor overlap risk with closely related skills rather than minimal conflict.	4 / 5
	Total	16 / 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: fernandezbaptiste/specialist-agent
Path: packs/astro/skills/review-review/SKILL.md
Revision: cd716d9

Reviewed: 8 days ago

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.

review-review

Table of Contents

Is this your skill?