skill-creator

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

75%

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, highly actionable meta-skill with a clearly sequenced creation workflow and validation feedback loops. Its main weaknesses are some concept-level verbosity and two referenced guide files that are cited but missing from the bundle.

Suggestions

Add the missing references/workflows.md and references/output-patterns.md files, or remove the citations to them in the 'Learn Proven Design Patterns' section, so all referenced paths resolve.

Tighten or cut the introductory conceptual prose (e.g., the 'Skills are modular, self-contained packages...' paragraph and the bridge/field metaphors) that a capable agent already knows.

Consider listing a few more concrete creation actions in the description (e.g., scaffold, validate, package) to lift the description specificity and trigger-term coverage.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural guidance, but sections like 'Skills are modular, self-contained packages...' and the metaphor explanations explain concepts a competent agent largely already knows and could be tightened, matching the 'mostly efficient but includes some unnecessary explanation' anchor.	2 / 3
Actionability	It provides fully executable commands with concrete flags (e.g., 'scripts/init_skill.py my-skill --path ./workspace/skills --resources scripts,references' and 'scripts/package_skill.py <path/to/skill-folder>') and specific example directory layouts, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The six-step process is explicitly ordered ('Follow these steps in order, skipping only if...') and the packaging step includes a validation feedback loop ('Validate first... if validation fails, fix and re-run'), matching the score-3 anchor for a clear sequence with explicit validation and error-recovery checkpoints.	3 / 3
Progressive Disclosure	Structure and one-level-deep references are clearly signaled in the body, but the referenced files references/workflows.md and references/output-patterns.md do not exist (the references/ directory is absent), so the navigation is broken despite the scripts/ references being valid; per the guideline to score against the actual bundle structure, broken reference links cap this at 2.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 cleanly answers both what the skill does and when to use it with an explicit trigger clause and a distinct niche. It is held back from a perfect score by somewhat generic action verbs and incomplete coverage of natural trigger-term variations.

Dimension	Reasoning	Score
Specificity	Names the domain ('AgentSkills') and a couple of actions ('Create or update') but does not list multiple specific concrete actions like the score-3 anchor requires; the verbs are broad rather than enumerating distinct operations.	2 / 3
Completeness	It answers both 'what' ('Create or update AgentSkills') and 'when' with an explicit 'Use when' clause listing concrete triggers, matching the score-3 anchor for clearly answering both with explicit triggers.	3 / 3
Trigger Term Quality	'designing, structuring, or packaging skills with scripts, references, and assets' gives several relevant trigger terms a user might say, but lacks common natural variations (e.g., 'build a skill', 'make a skill', 'add references to a skill'), matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The niche (creating/packaging AgentSkills) is distinct and the triggers (designing/structuring/packaging skills) are unlikely to fire for unrelated skills, matching the score-3 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 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: 14 missing	Warning

	Total	14 / 16 Passed

Repository: HKUDS/nanobot
Commit: c9c69e4

Reviewed: 1 day 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.