CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

project-guidelines-example

Example project-specific skill template based on a real production application.

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/project-guidelines-example/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 well-structured and highly actionable, with concrete commands, code patterns, and a validation-oriented deployment checklist. Its weaknesses are verbosity (generic boilerplate code and meta-explanations that add little project-specific value) and a monolithic single-file layout whose only cross-references point to non-existent files.

Suggestions

Cut or move generic material Claude already knows (the useApi/fetchApi wrappers, boilerplate pytest/RTL test structures, the meta "When to Use" list) and keep only project-specific decisions like the ApiResponse contract and the exact test commands.

Split the long code-pattern, testing, and deployment sections into reference files (e.g., references/patterns.md, references/testing.md, references/deploy.md) and link them one level deep from SKILL.md.

Remove or create the dead "Related Skills" targets (coding-standards.md, backend-patterns.md, frontend-patterns.md, tdd-workflow/) so every referenced path resolves, and pin model/version specifics in a dedicated section so they can be updated in one place.

DimensionReasoningScore

Conciseness

Several sections pad with knowledge Claude already has: a meta "When to Use" section explaining what project skills contain, textbook fetchApi/useApi wrappers, generic pytest and React Testing Library test structures, and tech-stack facts duplicated between the bullet list and the ASCII services diagram. Version-pinned details ("Next.js 15", "claude-sonnet-4-5-20250514") also appear outside any deprecated section.

2 / 5

Actionability

Concrete, mostly copy-paste-ready guidance throughout — pytest/npm/gcloud commands, complete code patterns, a specific environment-variable listing, and an explicit pre-deployment checklist. Minor gaps keep it below 5: the httpx AsyncClient(app=app) fixture uses outdated API and analyze_with_claude mixes an async signature with a synchronous client call.

4 / 5

Workflow Clarity

The deployment workflow has a clear sequence with explicit pre-deployment checkpoints (all tests passing, build succeeds, no hardcoded secrets, migrations ready) followed by concrete deploy commands. Minor validation gaps: no post-deploy verification or smoke test, and the testing workflow lacks a fix-and-retry loop.

4 / 5

Progressive Disclosure

Section headers are clear, but ~340 lines of code patterns, testing detail, and deployment procedure are inlined in a single file that would serve better as separate references. The "Related Skills" links (coding-standards.md, backend-patterns.md, frontend-patterns.md, tdd-workflow/) point to files that do not exist in the bundle.

3 / 5

Total

13

/

20

Passed

Description

25%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 description is a label rather than a functional description: it identifies the artifact as an example template but conveys no capabilities, use cases, or trigger conditions. A user or model scanning descriptions would have no basis for selecting this skill.

Suggestions

State concrete capabilities in the description, e.g., "Documents a project's architecture, file structure, code patterns, testing requirements, and deployment workflow."

Add an explicit trigger clause, e.g., "Use when working on the Zenith codebase or when the user asks about this project's architecture, conventions, or deployment process."

Include distinguishing keywords (architecture overview, tech stack, deployment checklist) so this skill cannot be confused with generic coding-standards skills.

DimensionReasoningScore

Specificity

The description names the domain ("project-specific skill template", "real production application") but lists zero concrete actions or capabilities — it describes what the artifact is, not what it does.

2 / 5

Completeness

It offers a vague 'what' (an example skill template) and no 'when' at all — there is no "Use when..." clause or equivalent trigger guidance, matching the anchor of a vague what with no when.

2 / 5

Trigger Term Quality

Only generic terms like "Example", "template", and "production application" appear; there are no natural phrases a user would say when needing this skill (e.g., "project guidelines", "architecture", "conventions").

2 / 5

Distinctiveness Conflict Risk

"Example project-specific skill template" is very broad and would overlap with any project-guidelines or template skill, with no distinctive triggers to separate it.

2 / 5

Total

8

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

valeriibeck-star/claude-skills

Path

skills/project-guidelines-example/SKILL.md

Reviewed

Table of Contents

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.