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 ./skills/skill-creator/SKILL.md

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

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.

The body delivers a clearly sequenced, validated creation workflow with executable commands and concrete examples, and its progressive-disclosure patterns are well taught. Its weaknesses are conceptual padding in the introductory sections and a bundle/layout mismatch: the two referenced references/*.md files are missing while an undocumented script ships in scripts/.

Suggestions

Ship the referenced files (references/workflows.md and references/output-patterns.md) or remove the dangling links — currently the "Learn Proven Design Patterns" section points to files that do not exist in the bundle.

Document scripts/quick_validate.py (when to run it and its usage) or remove it from the bundle, so every bundled resource is discoverable from SKILL.md.

Trim the "About Skills" and "What Skills Provide" sections to a few lines — the target reader (an agent creating skills) already knows what skills are; keep only the non-obvious design principles.

Dimension	Reasoning	Score
Conciseness	The actionable sections (commands, examples, steps) are efficient, but the "About Skills" / "What Skills Provide" passages ("Skills are modular, self-contained packages... Think of them as 'onboarding guides'") and the directory-by-directory explanations restate concepts the reading agent already knows, matching anchor 3 (mostly efficient, some unnecessary explanation).	3 / 5
Actionability	Concrete executable commands are given with flags and examples ("scripts/init_skill.py <skill-name> --path <output-directory> [--resources scripts,references,assets] [--examples]", "scripts/package_skill.py <path/to/skill-folder> ./dist") plus naming rules and sample dialog questions; the minor gap is that the bundled scripts/quick_validate.py is never documented, so it does not reach fully copy-paste-ready coverage of anchor 5.	4 / 5
Workflow Clarity	The six-step process is explicitly ordered with per-step skip conditions, packaging includes automatic validation with a feedback loop ("If validation fails, the script will report the errors... Fix any validation errors and run the packaging command again"), and step 4 requires actually running added scripts to test them — a clear match for anchor 5.	5 / 5
Progressive Disclosure	References are clearly signaled from SKILL.md ("See references/workflows.md for sequential workflows", "See references/output-patterns.md for template and example patterns") and sections are well organized, but the referenced files and the references/ directory do not exist in the bundle, and scripts/quick_validate.py is present yet never referenced — structure is present (above anchor 2) but broken navigation and inline pattern material keep it below anchor 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.

The description is concise, uses third person, and explicitly pairs a what-clause with a Use-when clause containing natural trigger phrases. Its main weakness is thin capability coverage on the what-side and missing common trigger variations, which keep specificity and trigger quality below the top anchors.

Suggestions

Expand the what-clause to enumerate concrete capabilities, e.g. "Create, update, validate, and package AgentSkills — includes scaffolding via init_skill.py and packaging/validation via package_skill.py".

Add natural trigger variations and artifacts users would mention, such as "build a skill", "SKILL.md", "skill bundle", or ".skill file".

Dimension	Reasoning	Score
Specificity	"Create or update AgentSkills" names the domain and 1-2 concrete actions; the additional verbs ("designing, structuring, or packaging") sit in the trigger clause and are high-level without concrete objects, so it does not reach the several-specific-actions coverage of anchor 4.	3 / 5
Completeness	It explicitly answers both "what" ("Create or update AgentSkills") and "when" ("Use when designing, structuring, or packaging skills with scripts, references, and assets"), but the what-side is thin and could be more explicit, matching anchor 4 rather than the comprehensive what+when of anchor 5.	4 / 5
Trigger Term Quality	"designing, structuring, or packaging skills" and "scripts, references, and assets" are natural phrases a user would say, but common variations and artifacts ("build a skill", "SKILL.md", ".skill file", "skill template") are missing, matching anchor 4 rather than the comprehensive synonym coverage of 5.	4 / 5
Distinctiveness Conflict Risk	Skill authoring is a clear, mostly distinct niche with triggers unlikely to fire for unrelated skills, but "designing... skills with scripts, references, and assets" has minor overlap risk with generic scaffolding or documentation skills, placing it at anchor 4 rather than 5.	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: Bitterbot-AI/bitterbot-desktop
Path: skills/skill-creator/SKILL.md
Commit: 1c7dc1b

Reviewed: 20 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.