agent-base-template-generator

Agent skill for base-template-generator - invoke with $agent-base-template-generator

1.01x

Quality

—

Does it follow best practices?

Impact

94%

1.01x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

42%

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 well-organized agent persona that defines role, approach, categories, and quality standards, but it is entirely abstract: no code, commands, or concrete templates, and padded with generic best-practice exposition Claude already knows. As an instruction-only skill its guidance is not sufficiently actionable to compensate for the absence of executable examples.

Suggestions

Replace abstract directives with at least one concrete, copy-paste-ready template skeleton (e.g. a sample React component or API endpoint scaffold) demonstrating the expected output.

Trim generic best-practice exposition ('follow industry best practices', 'maintain consistency') that Claude already knows, keeping only skill-specific guidance.

Add a validation/verification checkpoint to the generation workflow (e.g. confirm the generated template compiles or lints before delivering it).

Dimension	Reasoning	Score
Conciseness	The body is coherent and sectioned but padded with generic best-practice statements Claude already knows ('follow industry best practices', 'maintain consistency', 'provide clear extension paths'). It is mostly efficient yet could be tightened, matching anchor 2 rather than the lean anchor 3.	2 / 3
Actionability	The body provides no executable code, commands, or concrete template skeletons; it describes rather than instructs ('Include proper TypeScript definitions', 'Incorporate appropriate testing scaffolding'). This matches anchor 1 (vague/abstract; no concrete code/commands), and the scoring-note exemption for instruction-only skills does not apply because the guidance is abstract, not actionable.	1 / 3
Workflow Clarity	The six-step 'template generation approach' is sequenced, but the steps are abstract and lack validation checkpoints or feedback loops. This matches anchor 2 (steps listed but validation gaps; checkpoints missing or implicit).	2 / 3
Progressive Disclosure	This is a single-file skill with no bundle files and is under 50 lines, organized into clear sections (responsibilities, approach, categories, quality standards). Per the simple-skills scoring note, well-organized single-file content with no external references scores 3.	3 / 3
	Total	8 / 12 Passed

Description

17%

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 SKILL.md contains two YAML frontmatter blocks; a standard top-down parse extracts the first, whose description ('Agent skill for base-template-generator - invoke with $agent-base-template-generator') is a self-referential invocation hint with no concrete capabilities or natural trigger terms. The richer intended description is structurally misplaced in the body and does not function as the parsed description field.

Suggestions

Collapse the two frontmatter blocks into one and make the rich 'Use this agent when...' description the actual `description` field so it is parsed correctly.

Replace the literal '$agent-base-template-generator' invocation token with natural trigger terms users would say (e.g. 'starter template', 'boilerplate', 'scaffold a new component').

Add an explicit 'Use when...' clause stating when Claude should invoke the skill, including concrete capability verbs (generate, scaffold, stub out).

Dimension	Reasoning	Score
Specificity	The operative description 'Agent skill for base-template-generator - invoke with $agent-base-template-generator' names the domain (template generation) but offers no concrete capabilities, only an invocation instruction. It is above the vague 'Helps with documents' floor but falls short of listing multiple specific actions, matching anchor 2.	2 / 3
Completeness	It answers neither 'what does this do' (concretely) nor 'when should Claude use it'; there is no 'Use when...' clause, which the rubric says should cap completeness at 2, and the operative description is even weaker than that floor. It is closest to anchor 1 (missing what OR when, or both very weak).	1 / 3
Trigger Term Quality	The only trigger-like phrase is the literal invocation token '$agent-base-template-generator', which is technical jargon a user would never naturally say. This matches anchor 1 (no natural keywords; technical jargon), and is not rescued by the misplaced richer description in the body.	1 / 3
Distinctiveness Conflict Risk	The 'base-template-generator' niche is somewhat specific, but 'foundational templates, boilerplate code, or starter configurations' overlaps broadly with general code-generation skills, matching anchor 2 (somewhat specific but could still overlap).	2 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: 03d4f84

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.