CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-dev-backend-api

Agent skill for dev-backend-api - invoke with $agent-dev-backend-api

36

1.08x
Quality

Does it follow best practices?

Impact

85%

1.08x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

12%

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

The body is a verbose, buzzword-heavy wall of pseudocode built around fictional 'Agentic-Flow v2.0.0-alpha' APIs, with no executable guidance, no validation checkpoints, and no file-based structure. It reads as marketing copy rather than a usable skill.

Suggestions

Strip the self-learning/GNN/flash-attention prose and unverifiable performance claims; keep only the concrete backend-development guidance Claude cannot already infer.

Replace the fictional API calls with executable patterns (real library calls, concrete route/controller scaffolding, runnable test commands) so the examples are copy-paste ready.

Add explicit validation/verification steps to the implementation workflow (e.g. run lint + tests, verify endpoint responses) and split detailed reference material into bundle files referenced one level deep from SKILL.md.

DimensionReasoningScore

Conciseness

The body is heavily padded with self-learning/marketing prose, emoji headers, console.log noise, and unverifiable claims ('+12.4% accuracy', '4-7x faster', '~50% memory saved') that explain concepts and add no actionable value.

1 / 3

Actionability

The TypeScript samples call non-existent APIs (reasoningBank.searchPatterns, agentDB.gnnEnhancedSearch, agentDB.flashAttention) and the shell hooks contain broken syntax ('2>$dev$null') and unverified npx invocations, so the guidance is non-executable pseudocode rather than copy-paste instructions.

1 / 3

Workflow Clarity

A Before/During/After implementation sequence is present, but it lacks explicit validation checkpoints or error-recovery feedback loops for the destructive/batch API operations the rubric requires.

2 / 3

Progressive Disclosure

All content is inlined in a single monolithic file with no bundle files (references/, scripts/, assets/ are absent) and no signaled references to other documents, despite containing enough material to warrant splitting.

1 / 3

Total

5

/

12

Passed

Description

0%

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 a minimal label-and-invocation string with no statement of capabilities or usage triggers. It fails to answer either 'what does this do' or 'when should Claude use it'. A complete rewrite is needed.

Suggestions

Replace the description with concrete actions the skill performs, e.g. 'Designs and implements RESTful/GraphQL API endpoints, authentication, and data models'.

Add an explicit 'Use when...' trigger clause listing natural phrases a user would say, such as 'when the user asks to create an endpoint, build a CRUD API, or add a backend route'.

Use third person voice and drop the invocation token ('$agent-dev-backend-api') from the description so it reads as a capability statement rather than a launch instruction.

DimensionReasoningScore

Specificity

The description ('Agent skill for dev-backend-api - invoke with $agent-dev-backend-api') names a domain label but lists no concrete actions; it is effectively a name plus an invocation instruction.

1 / 3

Completeness

It states neither what the skill concretely does nor when to use it; there is no 'Use when...' clause, capping completeness well below 2.

1 / 3

Trigger Term Quality

No natural user keywords are present; the only terms are the skill's own name and an invocation token, which a user would not naturally say when needing backend API help.

1 / 3

Distinctiveness Conflict Risk

A bare domain label with no distinguishing triggers is generic and would conflict with other backend/API-oriented skills.

1 / 3

Total

4

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/claude-flow
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.