skill-creator

Create or update AgentSkills, especially when a user wants the agent to learn a reusable capability, workflow, integration, domain rule, team process, or tool usage pattern for future tasks. Use when designing, structuring, reviewing, validating, packaging, or improving skills with SKILL.md, scripts, references, and assets.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

62%

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

The skill body is well-sequenced with strong workflow clarity and executable scripts, but it is somewhat verbose and, more seriously, references reference files (workflows.md, output-patterns.md) that are absent from the bundle, weakening both actionability and progressive disclosure.

Suggestions

Add the missing references/workflows.md and references/output-patterns.md (or remove the two dangling "See references/..." pointers in Step 4) so signaled navigation resolves to real files.

Trim conceptual framing such as the "narrow bridge with cliffs" analogy and the "Skills are modular, self-contained packages" onboarding paragraph; assume the reader already knows what a skill is.

Move the detailed progressive-disclosure pattern catalogue (Patterns 1–3) into a reference file and keep SKILL.md to the core workflow, staying clearly under the stated 500-line guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and repeatedly reinforces token discipline, but at ~440 lines it carries conceptual framing ("Skills are modular, self-contained packages...", bridge/cliffs analogy) that pads beyond what an already-competent model needs.	2 / 3
Actionability	Provides concrete executable commands (init_skill.py, package_skill.py) and real code blocks, but actionability is undercut by pointing readers to references/workflows.md and references/output-patterns.md which do not exist in the bundle.	2 / 3
Workflow Clarity	The six-step creation process is clearly sequenced with an explicit validate→fix→retry checkpoint in the packaging step, satisfying the feedback-loop anchor.	3 / 3
Progressive Disclosure	It models good one-level-deep patterns, but the actual bundle has no references/ directory while the body references workflows.md and output-patterns.md, so the signaled navigation is broken rather than cleanly structured.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 specific, trigger-rich, and explicitly pairs a what with a Use-when clause in third person, hitting the top anchor on every dimension. It is concise yet comprehensive without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Create or update AgentSkills" plus "designing, structuring, reviewing, validating, packaging, or improving skills" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers what (create/update AgentSkills) and when via a clear "Use when designing, structuring, reviewing, validating, packaging, or improving skills" clause, in third person.	3 / 3
Trigger Term Quality	Covers natural user terms across the space — "reusable capability, workflow, integration, domain rule, team process, or tool usage pattern" and "SKILL.md, scripts, references, and assets" — a user asking to teach or structure a capability would say these.	3 / 3
Distinctiveness Conflict Risk	Scoped to skill authoring with distinct triggers (SKILL.md, packaging, references), unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 6 missing	Warning
referenced_paths_exist	Referenced path issues: 15 missing	Warning

	Total	14 / 16 Passed

Repository: trpc-group/trpc-agent-go
Commit: 737835b

Reviewed: 3 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.