deep-review

In-depth code review with design pre-flight + parallel specialist agents (correctness, security, performance, DRY, tests, observability, design). Works on PRs, branches, paths, or local uncommitted changes. Use when asked to deeply review a PR, branch, path, or local/staged changes.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%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.

A well-structured, highly actionable multi-phase review skill with clear sequencing, validation checkpoints, and clean progressive disclosure into real reference files. Its only weakness is moderate rationale prose that could be tightened for token efficiency.

Suggestions

Tighten the rationale paragraphs (e.g. the 'why reconcile runs concurrently' justification in Phase 1.5 and the 'False positives are cheap' note in Phase 1) to one line each — the operational instruction already implies the reasoning.

Consider moving the Phase 4 report template and severity ladder into references/report.md, keeping SKILL.md as the phase/sequence overview, to further reduce the inline token footprint.

The state-variables list (Phase 1) is useful but could be condensed to a table of name → phase → one-word purpose instead of full sentences per variable.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational, assuming Claude's competence without explaining basic concepts, but contains several rationale paragraphs (e.g. why reconcile runs concurrently, "False positives are cheap") that are minor over-explanation and could be trimmed.	4 / 5
Actionability	Concrete, copy-paste-ready commands throughout — `gh pr diff <N>`, `git worktree add --detach ...`, the `lane()` awk function — with executable bash blocks covering the common cases.	5 / 5
Workflow Clarity	Phases 0–5 are explicitly sequenced with validation checkpoints (worktree materialization fallback, size gate, pre-flight VERDICT gating) and feedback loops (PIVOT/ASK handling, approval-gated fix flow).	5 / 5
Progressive Disclosure	SKILL.md is an overview with one-level-deep, clearly signaled references (preflight.md, reconcile.md, specialists.md, submit.md, two harness adapters), all of which exist as real files; bulk briefs are correctly split out rather than inlined.	5 / 5
	Total	19 / 20 Passed

Description

100%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 strong, third-person description that names concrete capabilities and gives an explicit trigger clause with natural synonyms. It cleanly answers both what the skill does and when to use it, with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "design pre-flight + parallel specialist agents (correctness, security, performance, DRY, tests, observability, design)" and "Works on PRs, branches, paths, or local uncommitted changes" — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what ("In-depth code review with design pre-flight + parallel specialist agents...") and when ("Use when asked to deeply review a PR, branch, path, or local/staged changes") with concrete trigger phrases.	5 / 5
Trigger Term Quality	The "Use when asked to deeply review a PR, branch, path, or local/staged changes" clause covers the natural phrases a user would say, including synonyms (PR, branch, path, local/staged) for the relevant trigger surface.	5 / 5
Distinctiveness Conflict Risk	The "in-depth / deeply review" framing plus the named specialist dimensions carve a clear niche distinct from linting or general coding skills, with minimal overlap risk.	5 / 5
	Total	20 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: getlarge/themoltnet
Path: .agents/skills/deep-review/SKILL.md
Commit: 5daa9ca

Reviewed: ~15 hours 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.