review-automation-orchestrator

Use when running or scheduling periodic repository review cycles that must dispatch the correct reviewer, aggregate findings, and escalate outcomes into reports, issues, or corrective PRs across API contracts, documentation freshness, code quality, and CloudBase skill quality.

Quality

77%

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 ./skills/review-automation-orchestrator/SKILL.md

Quality

Content

77%

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

A well-sequenced, actionable orchestration skill with a useful self-check checklist, undermined by duplicated routing/escalation content and two missing reference files that break progressive disclosure.

Suggestions

Add the missing `references/repo-skill-review.md` and `references/cloudbase-skill-review.md`, or remove the references to them from Phase 2 so all cited paths resolve.

De-duplicate routing: keep either the Phase 2 dispatch list or the Routing table, and let `references/escalation-matrix.md` own the escalation detail rather than restating it in Phase 4.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with no concept explanations Claude already knows, but routing is stated twice (Phase 2 dispatch list and the Routing table) and escalation logic is restated in Phase 4 despite the dedicated escalation-matrix reference, which is notable duplication for a skill that itself warns against duplicating checklists.	2 / 3
Actionability	It gives concrete, executable routing: exact reviewer skill names, exact reference files to load, and a precise finding-normalization schema (scope, severity, confidence, smallest useful fix batch), which is fully actionable for an instruction-only orchestrator.	3 / 3
Workflow Clarity	Five phases are clearly sequenced and the closing "Minimum self-check" acts as an explicit validation checklist for the routing and escalation decisions, satisfying the clear-sequence-with-checklist anchor; no destructive batch step is present that would require an in-flow feedback loop.	3 / 3
Progressive Disclosure	Structure is appropriate and references are clearly signaled one level deep, but only one of the three referenced files exists — `references/escalation-matrix.md` resolves while `references/repo-skill-review.md` and `references/cloudbase-skill-review.md` are absent — so navigation is partially broken.	2 / 3
	Total	10 / 12 Passed

Description

77%

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 strong, mostly complete description with concrete actions and an explicit trigger, but it reads more formally than natural user speech and its broad domain list risks overlap with the specialized reviewers it dispatches to.

Suggestions

Soften the trigger language toward phrasing users actually say (e.g., "Use when running a weekly repo review" or "...setting up a recurring review that routes findings to the right reviewer").

Lead with the orchestration/routing role so it is unmistakably distinct from the single-dimension reviewers it dispatches to, reducing conflict risk with api-contract-review, doc-freshness-review, etc.

Dimension	Reasoning	Score
Specificity	The description names several concrete actions — "dispatch the correct reviewer, aggregate findings, and escalate outcomes into reports, issues, or corrective PRs" — matching the anchor that lists multiple specific concrete actions.	3 / 3
Completeness	It explicitly answers both what (dispatch/aggregate/escalate across four named dimensions) and when (an explicit "Use when..." clause), satisfying the highest anchor; voice is third-person so no penalty applies.	3 / 3
Trigger Term Quality	It opens with a natural "Use when running or scheduling periodic repository review cycles" trigger, but the body leans formal/technical ("dispatch the correct reviewer", "aggregate findings", "escalate outcomes") and lacks plainer user-language variations, so coverage is good but not comprehensive.	2 / 3
Distinctiveness Conflict Risk	The orchestrator framing (periodic cycles, routing, escalation) is a distinct niche, but enumerating the same domains as the child reviewers (API contracts, docs, code quality, skill quality) creates overlap risk where single-dimension requests could surface this skill instead.	2 / 3
	Total	10 / 12 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
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: TencentCloudBase/CloudBase-AI-Toolkit
Path: skills/review-automation-orchestrator/SKILL.md
Commit: d329622

Reviewed: about 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.