gstack-openclaw-ceo-review

Use when asked to review a plan, challenge a proposal, run a CEO review, poke holes in an approach, think bigger about scope, or decide whether to expand or reduce the plan.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

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, highly actionable plan-review skill with explicit gating and feedback loops. Its weaknesses are token efficiency (an aphorism-heavy cognitive-patterns list and repeated rules) and monolithic structure with no progressive disclosure into reference files.

Suggestions

Trim the 18-item 'Cognitive Patterns' list to the few instincts that change review behavior, and dedupe the repeated 'user in control' / 'no code changes' rules to tighten conciseness.

Move the per-section review checklists (Sections 1-11) and the cognitive-patterns catalogue into a references/ file (e.g. REVIEW_SECTIONS.md), keeping SKILL.md as an overview with one-level-deep links, to improve progressive disclosure.

Add a brief concrete example of one completed review (mode selection → one section finding → summary) so the actionable guidance has a copy-paste-ready model to follow.

Dimension	Reasoning	Score
Conciseness	Mostly directive and free of basic-concept filler, but the 18-item 'Cognitive Patterns' aphorism list and repeated scope-control rules ('user in control', 'no code changes' each stated 3×) are content Claude largely already knows and could be tightened.	2 / 3
Actionability	Highly actionable for an instruction-only skill: named shadow paths (nil/empty/upstream-error), node-by-node data-flow trace, named exception/rescue/user-visible-error directive, and a concrete output template — specific, operational guidance rather than vague direction.	3 / 3
Workflow Clarity	Clear sequence (Step 0 sub-steps → 11 review sections → Output) with explicit validation checkpoints ('Do NOT proceed without approval', one-issue-at-a-time), checklists, and a DONE/DONE_WITH_CONCERNS/BLOCKED feedback loop.	3 / 3
Progressive Disclosure	Well sectioned and navigable, but as a ~185-line monolithic single file with no bundle files, the inline cognitive-patterns list and detailed per-section checklists could be offloaded to reference files; content that should be separate is inline.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 with explicit 'Use when' triggers and six concrete, naturally-phrased review actions. It clearly answers both what the skill does and when to invoke it, with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'review a plan', 'challenge a proposal', 'run a CEO review', 'poke holes in an approach', 'think bigger about scope', 'expand or reduce the plan' — matching the multiple-concrete-actions anchor rather than the domain-only level 2.	3 / 3
Completeness	Explicit 'Use when' clause supplies the when, and the enumerated actions supply the what — both answered explicitly, matching the level-3 anchor and not capped at 2 since a clear trigger clause is present.	3 / 3
Trigger Term Quality	Natural user phrasings with good variation ('review a plan', 'challenge a proposal', 'poke holes', 'think bigger about scope', 'expand or reduce') — terms a user would actually say, not jargon.	3 / 3
Distinctiveness Conflict Risk	The 'CEO review / poke holes / scope expand-reduce' framing carves a distinct niche unlikely to trigger unrelated skills, matching the clear-niche anchor.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: garrytan/gstack
Commit: 11de390

Reviewed: 3 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.