skill-creator

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

Quality

70%

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

70%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.

A well-sequenced, largely executable guide whose workflow with validation feedback loops is its strongest aspect. Its weaknesses are conceptual padding that dilutes token efficiency and a progressive-disclosure structure undermined by referencing reference files that are absent from the actual bundle.

Suggestions

Add the missing references/workflows.md and references/output-patterns.md (or remove the links in the 'Learn Proven Design Patterns' section) so the body's navigation does not dead-end.

Trim the 'About Skills' conceptual section and the repeated 'the agent loads X only when needed' explanations to tighten token efficiency.

Reference scripts/quick_validate.py in the body (e.g., as a pre-packaging check) so every bundled script is discoverable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural guidance, but contains unnecessary padding: the "About Skills" conceptual section re-explains what skills are, the bridge/field metaphor, and the pattern examples repeat "the agent loads X only when needed" three times. More than minor over-explanation, so below the 'efficient, minor trim' anchor.	3 / 5
Actionability	Provides executable commands with real flags (scripts/init_skill.py <skill-name> --path ... --resources scripts,references), concrete naming rules, and a full worked example description. Minor gaps: scripts/quick_validate.py is bundled but never referenced, and some guidance (e.g., Step 6 iterate) stays high-level.	4 / 5
Workflow Clarity	Six clearly sequenced steps with explicit skip conditions, an automatic validation checkpoint in packaging, and a feedback loop ("If validation fails... fix any validation errors and run the packaging command again"), plus a requirement to test added scripts. Matches the anchor for clear sequence with explicit validation and error-recovery loops.	5 / 5
Progressive Disclosure	The body is well-structured and signals its references clearly (references/workflows.md, references/output-patterns.md), but those files do not exist in the bundle, so navigation dead-ends; the bundled scripts/quick_validate.py is likewise unreferenced, and lengthy inline pattern examples would live better in reference files. Broken references exceed the 'minor organization gaps' of a 4.	3 / 5
	Total	15 / 20 Passed

Description

70%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.

A solid, concise description that answers both what the skill does and when to use it in third person with natural trigger gerunds. Its main limits are modest action coverage (create/update only) and a few missing common trigger phrasings.

Dimension	Reasoning	Score
Specificity	Names the domain ("Create or update AgentSkills") with 1-2 concrete actions, but coverage is not comprehensive — no mention of iterating on, validating, or packaging workflows. Matches the 'names domain and 1-2 concrete actions' anchor rather than the 'several specific actions' anchor above.	3 / 5
Completeness	Explicitly answers both what ("Create or update AgentSkills") and when ("Use when designing, structuring, or packaging skills"), in third person. The when clause is present and explicit but could name more trigger contexts, matching the anchor 'both what and when; when could be more explicit or specific'.	4 / 5
Trigger Term Quality	"designing, structuring, or packaging skills with scripts, references, and assets" gives good natural keyword coverage, but a few common phrasings are missing (e.g., "SKILL.md", "new skill", "skill authoring"). Better than 'some relevant keywords' (3), short of the synonym-and-extension comprehensiveness of a 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche — authoring/updating skills rather than using them — with distinct trigger terms around skill design and packaging. Minor overlap risk with general documentation/packaging tasks keeps it below the 'clear niche, minimal conflict' anchor.	4 / 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: 14 missing	Warning

	Total	14 / 16 Passed

Repository: HKUDS/nanobot
Path: nanobot/skills/skill-creator/SKILL.md
Commit: 6eccc28

Reviewed: 5 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.