skill-creator

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

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./nanobot/skills/skill-creator/SKILL.md

Quality

Content

63%Weight 40%Scale 1-5

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

The content is a thorough, well-organized meta-skill with real backing scripts and a clear creation workflow, but it is padded with conceptual framing Claude already knows and references two reference files that are missing from the bundle.

Suggestions

Create the missing references/workflows.md and references/output-patterns.md (or remove the links), since the body instructs the agent to consult them.

Trim conceptual exposition Claude already understands (e.g., the context-window public-good framing and the bridge/cliff metaphor) to tighten conciseness.

Add an explicit validation/verification checkpoint in the creation workflow (e.g., 'validate the skill before packaging') rather than relying solely on the packaging script.

Dimension	Reasoning	Score
Conciseness	The body explains several concepts Claude already grasps at a high level ('the agent is already very smart', context-window-as-public-good, the bridge/cliff metaphor) and includes noticeable conceptual padding, fitting the 'mostly efficient but includes some unnecessary explanation' anchor.	3 / 5
Actionability	Provides concrete executable commands with real flags (init_skill.py, package_skill.py) and specific naming rules backed by real scripts, but leaves minor gaps such as no fully worked SKILL.md body example and references to two non-existent reference files.	4 / 5
Workflow Clarity	The six-step creation process is clearly sequenced with explicit skip guidance, though validation checkpoints are implicit (delegated to the packaging script) rather than spelled out as verify-after-edit steps.	4 / 5
Progressive Disclosure	Structure and sectioning are good and the referenced scripts exist, but the body links to references/workflows.md and references/output-patterns.md that are absent from the bundle, and substantial conceptual material is inlined rather than split out.	3 / 5
	Total	14 / 20 Passed

Description

75%Weight 40%Scale 1-5

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 well-constructed: third-person, concise, and covers both what the skill does and when to use it with concrete action verbs. It stops short of the top anchor only because the trigger context could be more explicitly enumerated.

Dimension	Reasoning	Score
Specificity	Names the domain ('AgentSkills') and lists several concrete actions — 'Create or update', 'designing, structuring, or packaging' — with bundled-resource context, matching the 'several specific actions; minor gaps' anchor.	4 / 5
Completeness	Answers both 'what' ('Create or update AgentSkills') and 'when' ('Use when designing, structuring, or packaging skills...'), but the 'when' clause is somewhat generic and lacks the concrete enumerated triggers of the anchor-5 example.	4 / 5
Trigger Term Quality	Includes natural trigger phrases a user might say ('designing', 'structuring', 'packaging skills', 'scripts, references, and assets') but omits common synonyms like 'build a skill', fitting the 'good coverage; a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	The 'AgentSkills' niche plus the bundling context narrows it to a clear purpose with only minor overlap risk against generic skill-management skills, matching the 'mostly distinct; minor overlap risk' anchor.	4 / 5
	Total	16 / 20 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
Path: nanobot/skills/skill-creator/SKILL.md
Commit: c27b1f1

Reviewed: about 18 hours 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.