skill-creator

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

Quality

66%

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 ./skills/skill-creator/SKILL.md

The canonical home for this skill is skill-creator in deepgram/dglabs-deepclaw

Quality

Content

57%

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

The skill delivers strong actionable commands and a clear creation workflow, but it over-explains concepts Codex already knows and references two design-pattern files that are absent from the bundle, breaking progressive disclosure navigation.

Suggestions

Trim generic explanation (the 'About Skills' overview, context-window rationale, and bridge/field metaphor) since Codex already knows these concepts; keep only the skill-authoring-specific guidance.

Make the packaging validation loop explicit with a checkpoint: 'Run package_skill.py; if validation fails, read the reported errors, fix, and re-run — do not proceed until validation passes.'

Add the missing references/workflows.md and references/output-patterns.md files (or remove the references to them) so the one-level-deep navigation resolves to real files.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-structured, but it explains general concepts Codex already knows (what skills are, the context-window-as-public-good rationale, freedom metaphors like 'narrow bridge with cliffs'), adding token cost without proportional value.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands (init_skill.py and package_skill.py invocations with concrete examples) and concrete file-layout examples, giving clear actionable guidance.	3 / 3
Workflow Clarity	The 6-step process is clearly sequenced, but the packaging step's validation feedback loop is implicit ('fix errors and run again') rather than an explicit validate-fix-retry checkpoint, and the editing step lacks a verification gate despite scripts needing testing.	2 / 3
Progressive Disclosure	The body instructs Codex to 'See references/workflows.md' and 'See references/output-patterns.md' for core design patterns, but those reference files do not exist in the bundle, leaving broken navigation to missing one-level-deep references.	1 / 3
	Total	8 / 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 is concise, third-person, and clearly answers both what the skill does and when to use it, with distinct niche triggers. Specificity and trigger keyword coverage are solid but not exhaustive.

Suggestions

Broaden trigger terms with natural phrasings users actually say, e.g. 'Use when building, scaffolding, or bundling an AgentSkill, or when organizing scripts, references, and assets into a skill'.

List more concrete actions beyond 'Create or update' (e.g., 'scaffold, validate, and package skills') to reach a fully comprehensive multi-action description.

Dimension	Reasoning	Score
Specificity	It names the domain ('Create or update AgentSkills') and some actions ('designing, structuring, or packaging') with skill components, but 'update' is vague and the action set is not as comprehensive as a full multi-action list, matching the names-domain-and-some-actions anchor.	2 / 3
Completeness	It states both what the skill does ('Create or update AgentSkills') and an explicit 'Use when designing, structuring, or packaging skills' trigger clause, satisfying both what and when.	3 / 3
Trigger Term Quality	It includes some natural terms a user might say ('designing, structuring, or packaging skills') but lacks common keyword variations like 'build a skill', 'skill bundle', or 'AgentSkills creation', so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The narrow focus on AgentSkill authoring (scripts/references/assets packaging) is a clear niche with distinct triggers unlikely to collide with other skills.	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: Bitterbot-AI/bitterbot-desktop
Path: skills/skill-creator/SKILL.md
Commit: e73c717

Reviewed: about 16 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.