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

71%

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 ./openclaw/skills/gstack-openclaw-ceo-review/SKILL.md

Quality

Content

67%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 thorough, well-structured plan-review skill with strong sequencing, explicit approval gates, and concrete per-section evaluation criteria. Its chief weakness is conciseness: the 18 cognitive-patterns aphorisms add length without proportionally adding guidance Claude does not already have.

Suggestions

Trim or collapse the 18-item Cognitive Patterns list into the few instincts that most directly change review behavior, removing widely-known CEO tropes (e.g. "People, products, profits", "wartime awareness") to improve token efficiency.

Add one short worked example of a completed CEO REVIEW SUMMARY so the output template is unambiguous and actionability reaches a 5.

Consider moving the per-section evaluation checklists into a reference file (e.g. REVIEW_SECTIONS.md) so the SKILL.md body stays a lean overview, raising progressive_disclosure toward a 5.

Dimension	Reasoning	Score
Conciseness	Mostly efficient in the Prime Directives and Review Sections, but the 18-item "Cognitive Patterns" list leans on familiar CEO aphorisms ("People, products, profits", "wartime awareness", "founder-mode bias") that partially restate concepts Claude already knows and could be trimmed.	3 / 5
Actionability	Highly actionable for an instruction-only skill: Step 0A–0F with concrete gates, 11 review sections each naming specific evaluation targets ("N+1 query risks", "injection vectors", "rollback posture"), plus an output template; not a 5 because no filled-in example output or worked review is shown.	4 / 5
Workflow Clarity	Clear sequence (Step 0 → 11 sections → summary) with explicit approval gates ("Do NOT proceed without approval"), an anti-skip rule, one-issue-at-a-time enforcement, and a DONE/DONE_WITH_CONCERNS/BLOCKED completion status; minor gaps keep it just under a 5.	4 / 5
Progressive Disclosure	Well-organized into clearly labeled sections with no nested references; for a single-file review methodology this inlining is reasonable, though the cognitive-patterns and per-section criteria could optionally be split into reference files to shorten the top-level overview.	4 / 5
	Total	15 / 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 well-constructed trigger-heavy description that names concrete actions and an explicit Use-when clause, with a distinctive CEO-review niche. Its main limitation is that the actions overlap conceptually and the "what" is implied via the trigger list rather than stated independently.

Dimension	Reasoning	Score
Specificity	Lists several 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"), though several are variations on the same review/challenge act rather than truly distinct capabilities, so it sits at 4 rather than a comprehensive 5.	4 / 5
Completeness	Has an explicit "Use when..." trigger clause and the actions convey the "what", but the description is framed entirely as a when-clause so the "what" is only implicit rather than separately and explicitly stated.	4 / 5
Trigger Term Quality	Natural phrases a user would actually say ("poke holes in an approach", "run a CEO review", "think bigger about scope") with good coverage; not a 5 because synonyms and edge variations are not exhaustively enumerated.	4 / 5
Distinctiveness Conflict Risk	The "CEO review" / scope-expansion framing carves a fairly distinct niche with minimal conflict risk, though it could still overlap with general code-review or planning skills.	4 / 5
	Total	16 / 20 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
Path: openclaw/skills/gstack-openclaw-ceo-review/SKILL.md
Commit: d078622

Reviewed: 2 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.