cc-skill-project-guidelines-example

Project Guidelines Skill (Example)

Quality

24%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/cc-skill-project-guidelines-example/SKILL.md

The canonical home for this skill is cc-skill-project-guidelines-example in sickn33/agentic-awesome-skills

Quality

Content

43%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.

The body is highly actionable with concrete code and commands, but it is verbose, dumping routine patterns Claude already knows inline, and it lacks progressive disclosure: everything lives in one monolithic file with references to non-existent bundle files. The deployment workflow also lacks validation feedback loops.

Suggestions

Move the detailed code patterns (API response format, frontend fetch, Claude integration, useApi hook) into separate reference files and keep SKILL.md as a concise overview that links to them one level deep.

Trim or remove the code examples that restate common knowledge (e.g., the generic fetch wrapper and useApi hook); keep only the Zenith-specific conventions that Claude would not infer.

Add an explicit validation checkpoint to the deployment workflow (e.g., run pytest + npm run build, verify they pass, then deploy), and either create the referenced 'Related Skills' files or remove the dead links.

Dimension	Reasoning	Score
Conciseness	The ~345-line body inlines full code examples of patterns Claude already knows (a generic FastAPI ApiResponse, a standard TS fetch wrapper, a basic useApi React hook, a routine pytest fixture), which is noticeably verbose with several padded sections that could be trimmed or omitted.	2 / 5
Actionability	The content provides concrete, mostly copy-paste-ready code and commands (FastAPI/Pydantic models, TypeScript fetch helper, Claude structured-output integration with a real model id, pytest/playwright commands, gcloud deploy commands) with only minor gaps, matching the 'mostly executable guidance' anchor.	4 / 5
Workflow Clarity	The deployment workflow lists steps and a pre-deployment checklist but lacks validate-then-proceed checkpoints or a fix-and-retry feedback loop for a destructive/batch operation; per the rubric's destructive-operation cap, this caps the score at 3 even though the sequence is present.	3 / 5
Progressive Disclosure	No bundle files exist, yet the body inlines architecture, full code patterns, test structures, and deploy configs that clearly belong in separate reference files, and the 'Related Skills' links point to non-existent files; this matches the 'content that clearly belongs in separate files is inlined' anchor.	2 / 5
	Total	11 / 20 Passed

Description

5%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.

The frontmatter description is essentially a title restatement with no concrete capabilities, trigger terms, or use-when guidance, making it indistinguishable from many other skills. It fails to tell Claude what it does or when to invoke it.

Suggestions

Replace the title-only description with concrete actions, e.g. 'Reference this skill when working on the Zenith codebase: it documents the Next.js + FastAPI architecture, code patterns, testing requirements, and Cloud Run deployment workflow.'

Add an explicit 'Use when...' clause naming natural trigger phrases such as 'working on Zenith', 'deploying the backend', or 'writing tests for the FastAPI routers'.

Drop the '(Example)' qualifier and use third-person voice to make the skill distinguishable from generic coding-standards skills.

Dimension	Reasoning	Score
Specificity	The description only names the domain ("Project Guidelines Skill (Example)") with zero concrete actions; it names the area but gives no specific capabilities, fitting the 'names the domain but actions are minimal' anchor rather than the fully-vague 1 since it does identify the niche.	2 / 5
Completeness	The description answers neither 'what does this do' (beyond restating the title) nor 'when should Claude use it'; there is no 'Use when...' clause, matching the 'missing both what and when' anchor.	1 / 5
Trigger Term Quality	There are no natural keywords a user would say when needing this skill; "Project Guidelines Skill (Example)" is a label, not a trigger phrase, matching the 'no natural keywords; only generic language' anchor.	1 / 5
Distinctiveness Conflict Risk	"Project Guidelines Skill" is entirely generic and would overlap with virtually any project or coding-standards skill, matching the 'entirely generic; would conflict with virtually any skill' anchor.	1 / 5
	Total	5 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/cc-skill-project-guidelines-example/SKILL.md
Commit: 57c135b

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.