agent-dev-backend-api

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

1.08x

Quality

13%

Does it follow best practices?

Impact

85%

1.08x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-dev-backend-api/SKILL.md

Quality

Discovery

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

This description is critically deficient across all dimensions. It functions only as a label with an invocation command, providing zero information about capabilities, use cases, or trigger conditions. Claude would have no basis for selecting this skill appropriately from a list of available skills.

Suggestions

Add specific concrete actions describing what this skill does (e.g., 'Creates REST API endpoints, handles database queries, manages authentication flows').

Include a 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when building backend services, creating APIs, or working with server-side code').

Specify the technology stack or domain to distinguish from other backend skills (e.g., 'Node.js/Express backend development' or 'Python FastAPI services').

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for dev-backend-api' is completely abstract and doesn't describe what the skill actually does.	1 / 3
Completeness	Missing both 'what' and 'when'. The description only provides an invocation command but explains neither what the skill does nor when Claude should use it.	1 / 3
Trigger Term Quality	No natural keywords users would say. 'dev-backend-api' is a technical identifier, not a term users would naturally use when seeking help. The only actionable term is the invocation command.	1 / 3
Distinctiveness Conflict Risk	Extremely generic. 'Agent skill' and 'backend-api' could apply to countless different skills. There's nothing distinguishing this from other backend or API-related skills.	1 / 3
	Total	4 / 12 Passed

Implementation

27%

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

This skill is excessively verbose, spending most of its tokens on TypeScript examples that illustrate a specific framework's API rather than providing actionable guidance Claude can use. The content explains self-learning concepts Claude already understands and includes a massive YAML frontmatter that duplicates information. The actual actionable guidance (best practices, patterns to follow) is buried at the end in brief bullet points.

Suggestions

Remove or drastically reduce the TypeScript code examples - they reference a specific framework API that may not be available and explain concepts Claude already knows

Move the YAML frontmatter hooks and examples to separate reference files, keeping only essential configuration inline

Expand the 'Best practices' and 'Patterns to follow' sections with concrete, executable examples instead of abstract bullet points

Add explicit validation checkpoints (e.g., 'Run npm run lint:api before committing', 'Verify OpenAPI spec validates') to the workflow

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive TypeScript code examples that explain concepts Claude already knows (how to search patterns, store data, track metrics). The YAML frontmatter alone is 150+ lines, and the body repeats similar patterns multiple times with unnecessary commentary.	1 / 3
Actionability	Contains TypeScript code examples but they reference a specific framework (Agentic-Flow v2.0.0-alpha) with APIs like 'reasoningBank.searchPatterns' and 'agentDB.gnnEnhancedSearch' that may not exist or be accessible. The code is illustrative rather than copy-paste executable without that framework.	2 / 3
Workflow Clarity	Has a clear before/during/after structure for the self-learning protocol, but lacks explicit validation checkpoints. The workflow describes what to do conceptually but doesn't provide concrete verification steps or error recovery beyond storing failure patterns.	2 / 3
Progressive Disclosure	Monolithic wall of content with no references to external files. All code examples, patterns, and documentation are inline. The massive YAML frontmatter and lengthy body could be split into separate reference files for hooks, examples, and API patterns.	1 / 3
	Total	6 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: b2618f9

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.