cc-skill-project-guidelines-example

Project Guidelines Skill (Example)

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

The body is highly actionable with executable, project-specific code and clear sections, but it is a monolithic single file with no reference bundle and a deployment workflow lacking explicit validation checkpoints. Splitting detail into referenced files and adding a deploy verification step would lift the weaker dimensions.

Suggestions

Move the code-pattern examples and full file-structure tree into referenced files (e.g. references/code-patterns.md) and keep SKILL.md as a concise overview with one-level-deep links.

Add an explicit validation/feedback step to the deployment workflow, e.g. 'After deploy, verify the service is healthy; if the health check fails, roll back to the previous revision.'

Trim generic code Claude already knows (e.g. the useApi hook) or move it to a reference, retaining only project-specific conventions in the main body.

Dimension	Reasoning	Score
Conciseness	The ~350-line body avoids explaining basic concepts but includes generic code Claude already knows (e.g. a full useApi React hook) plus heavy ASCII diagrams, so it is mostly efficient yet could be tightened — matching the score-2 anchor.	2 / 3
Actionability	It provides complete, copy-paste-ready executable code and commands throughout — FastAPI ApiResponse, TS fetchApi, Claude tool-use integration, pytest fixtures, and gcloud deploy commands — matching the score-3 anchor.	3 / 3
Workflow Clarity	The deployment workflow lists steps with a pre-deployment checklist but lacks an explicit validate→fix→retry feedback loop for a destructive-ish batch operation, matching the score-2 anchor and capping at 2 per the missing-validation guideline.	2 / 3
Progressive Disclosure	No bundle files exist and all content is inline in one ~350-line file; 'Related Skills' references unbundled paths, so structure exists but content that should be separate is inline — matching the score-2 anchor.	2 / 3
	Total	9 / 12 Passed

Description

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a bare label with no capabilities, triggers, or use-when guidance, scoring at the floor across all dimensions. It needs concrete actions and an explicit 'Use when...' clause.

Suggestions

Replace the label with concrete capabilities, e.g. 'Documents architecture, file structure, code patterns, testing, and deployment workflow for the Zenith project.'

Add an explicit trigger clause such as 'Use when working on the Zenith codebase or when the user mentions Zenith, FastAPI, Next.js 15, or Supabase project conventions.'

Use third-person active voice and include natural terms users would say to distinguish it from other project skills.

Dimension	Reasoning	Score
Specificity	The description is only "Project Guidelines Skill (Example)" — it labels the skill type but names no concrete actions, matching the score-1 anchor for vague/abstract language.	1 / 3
Completeness	It lacks both a substantive 'what does this do' (only a label) and any 'when should Claude use it' trigger, and there is no 'Use when...' clause, matching the score-1 anchor and capping at 2 per the missing-trigger guideline.	1 / 3
Trigger Term Quality	No natural trigger terms a user would say appear; "Project Guidelines Skill" is generic labeling rather than keywords users actually voice, matching the score-1 anchor.	1 / 3
Distinctiveness Conflict Risk	"Project Guidelines Skill" is generic and would overlap with many project-specific skills, matching the score-1 anchor for a very generic description that conflicts broadly.	1 / 3
	Total	4 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Commit: 615669b

Reviewed: 4 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.