gstack-openclaw-office-hours

Use when asked to brainstorm, evaluate whether an idea is worth building, run office hours, or think through a new product idea or design direction before any code is written.

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 highly actionable, well-sequenced instruction skill with strong feedback checkpoints, but it is long for a single file with some redundancy across its posture/rules sections and no progressive disclosure via reference files.

Suggestions

Consolidate the overlapping guidance in Operating Principles, Response Posture, Anti-Sycophancy Rules, and Pushback Patterns into a single section to remove redundancy and cut length.

Move the Six Forcing Questions (with red flags) and the design-doc templates into reference files under references/ and link to them one level deep, keeping SKILL.md as a lean overview.

Trim a few of the BAD/GOOD pushback dialogues to one representative example each while preserving the pattern.

Dimension	Reasoning	Score
Conciseness	The body is dense and free of basic-concept filler, but at ~370 lines it repeats the same 'be specific / push hard' message across Operating Principles, Response Posture, Anti-Sycophancy Rules, and Pushback Patterns, and could be tightened.	2 / 3
Actionability	Copy-paste-ready forcing questions, BAD/GOOD pushback scripts, mode-mapping tables, and full design-doc templates give concrete executable guidance rather than vague direction.	3 / 3
Workflow Clarity	Phases 1-6 are explicitly sequenced with STOP checkpoints, a HARD GATE, premise confirm/loop-back feedback, and an Approve/Revise/Start-over gate, and no destructive/batch operations exist to require additional validation.	3 / 3
Progressive Disclosure	Sections are well-organized by phase, but the skill is a single monolithic ~370-line file with no bundle references; the question bank, templates, and pushback patterns are inline content that could be split out.	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 description with concrete actions, natural trigger terms, explicit when-guidance, and a clear niche that avoids conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('brainstorm, evaluate whether an idea is worth building, run office hours, or think through a new product idea or design direction'), matching the multiple-specific-actions anchor.	3 / 3
Completeness	The verb list conveys what the skill does and the explicit 'Use when ...' clause conveys when to invoke it, covering both what and when with explicit triggers.	3 / 3
Trigger Term Quality	Uses natural user phrasing — 'brainstorm', 'is this idea worth building', 'office hours', 'product idea', 'design direction' — that a user would actually say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	The office-hours / pre-implementation idea-evaluation niche plus 'before any code is written' clearly separates it from implementation skills, making wrong-skill triggering unlikely.	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: 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.