skill-creator

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

2.13x

Quality

64%

Does it follow best practices?

Impact

92%

2.13x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bot/workspace/skills/skill-creator/SKILL.md

The canonical home for this skill is skill-creator in HKUDS/nanobot

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 body is a thorough, well-sequenced guide to skill creation with concrete commands and a validation feedback loop. Its main weaknesses are verbosity from inlined meta-educational content and references to bundled files that do not actually exist in the package.

Suggestions

Move the 'About Skills', 'What Skills Provide', and progressive-disclosure pattern examples into a references file, keeping SKILL.md to the core creation workflow.

Ensure referenced files exist: ship scripts/init_skill.py, scripts/package_skill.py, references/workflows.md, and references/output-patterns.md, or remove the references.

Trim the 'onboarding guides' analogy and repeated context-window emphasis; the 'Concise is Key' section should itself model brevity.

Dimension	Reasoning	Score
Conciseness	Mostly useful but padded in places (the 'onboarding guides' analogy, the 'What Skills Provide' list, and restated context-window cautions), fitting 'mostly efficient but includes some unnecessary explanation or could be tightened'; not a 2 because the core guidance is substantive.	3 / 5
Actionability	Provides concrete, copy-paste-ready commands with full argument signatures (init_skill.py, package_skill.py) and worked examples; held below 5 because the referenced scripts and reference files do not actually exist in the bundle, so the commands are not verifiably executable as shipped.	4 / 5
Workflow Clarity	A clear six-step sequence (Understand, Plan, Initialize, Edit, Package, Iterate) with an explicit validation checkpoint and fix-and-retry feedback loop in the packaging step; not a 5 because validation is concentrated only at packaging rather than throughout, and mid-process checkpoints are implicit.	4 / 5
Progressive Disclosure	Good section structure, but the body inlines substantial educational content (anatomy, 'What Skills Provide', three full progressive-disclosure pattern code blocks) that the skill's own advice says belongs in references, and it references files (scripts/init_skill.py, scripts/package_skill.py, references/workflows.md, references/output-patterns.md) that are not present in the bundle.	3 / 5
	Total	14 / 20 Passed

Description

66%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-formed with an explicit 'Use when' clause, a distinct niche, and reasonable trigger verbs. It is held back by somewhat abstract action language and missing synonym/extension variations in the trigger terms.

Suggestions

Replace high-level verbs ('designing, structuring') with more concrete actions (e.g., 'scaffold, generate, validate, and package skill bundles').

Add user-voice trigger phrasings and synonyms, e.g., 'Use when the user asks to build, scaffold, or package a skill, or mentions SKILL.md, scripts/, references/, or .skill files.'

Tighten the 'what' to enumerate a couple of concrete capabilities (e.g., 'generates SKILL.md frontmatter and bundles scripts/references/assets') to lift specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('AgentSkills') and several actions ('Create or update', 'designing, structuring, or packaging') plus components ('scripts, references, and assets'), but the actions are high-level rather than concrete like the score-4 anchor's 'extracts text, fills forms'.	3 / 5
Completeness	Explicitly states both what ('Create or update AgentSkills...with scripts, references, and assets') and when ('Use when designing, structuring, or packaging skills'); the 'when' is explicit with concrete triggers but lacks user-voice phrasings like 'when the user asks to build a skill', so not a 5.	4 / 5
Trigger Term Quality	Includes relevant natural terms ('designing, structuring, or packaging skills') but misses common variations, synonyms, and concrete file/extension triggers a user might say, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (skill creation/packaging) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	15 / 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: 20 missing	Warning

	Total	14 / 16 Passed

Repository: volcengine/OpenViking
Path: bot/workspace/skills/skill-creator/SKILL.md
Commit: dbf3fcc

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.