CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

68

1.42x
Quality

52%

Does it follow best practices?

Impact

98%

1.42x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./data/skills-md/0xdarkmatter/claude-mods/skill-creator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

47%

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

This skill has a well-structured workflow with clear sequencing and validation, but suffers significantly from verbosity—it explains many concepts Claude already understands (what skills are, what scripts/references/assets mean, basic organizational principles). The irony is that a skill about creating concise skills is itself not concise. The actionability is moderate: while init/package commands are concrete, much of the writing guidance is conceptual rather than providing executable templates or concrete before/after examples.

Suggestions

Cut the 'About Skills' and 'What Skills Provide' sections drastically—Claude already knows what skills are. Focus only on non-obvious structural requirements (frontmatter fields, directory structure).

Replace the verbose 'Degrees of Freedom' and 'Progressive Disclosure' conceptual explanations with a concise decision table or checklist that Claude can reference quickly.

Add a concrete, complete SKILL.md example (a minimal but real skill) as a template rather than describing what good skills look like in prose.

Move the detailed 'Bundled Resources' explanations and 'Progressive Disclosure Patterns' sections into reference files, practicing the progressive disclosure the skill preaches.

DimensionReasoningScore

Conciseness

The skill is extremely verbose at ~300+ lines, with significant portions explaining concepts Claude already knows (what skills are, what PDFs are, what scripts/references/assets mean conceptually). Sections like 'What Skills Provide' and 'About Skills' are largely unnecessary. The 'What to Not Include' section ironically adds clutter. Many paragraphs could be reduced to single sentences.

1 / 3

Actionability

The skill provides concrete commands for init_skill.py and package_skill.py with usage examples, and includes specific guidance on frontmatter writing. However, much of the content is conceptual rather than executable—the 'degrees of freedom' section, planning steps, and design patterns are described abstractly rather than with concrete, copy-paste-ready examples. The actual SKILL.md writing guidance lacks a concrete before/after example.

2 / 3

Workflow Clarity

The 6-step creation process is clearly sequenced with explicit ordering ('Follow these steps in order, skipping only if there is a clear reason'). Each step has clear entry/exit criteria (e.g., 'Conclude this step when there is a clear sense of the functionality'), validation is built into Step 5 via the packaging script, and the iteration feedback loop in Step 6 is explicit.

3 / 3

Progressive Disclosure

The skill references external files like references/workflows.md and references/output-patterns.md with clear descriptions of when to consult them, and links to external Anthropic resources. However, the SKILL.md itself is monolithic—much of the conceptual content (progressive disclosure patterns, anatomy of a skill, degrees of freedom) could be moved to reference files. The skill teaches progressive disclosure but doesn't fully practice it.

2 / 3

Total

8

/

12

Passed

Description

57%

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 adequately covers when to use the skill with explicit trigger conditions, but falls short on specificity of what concrete actions it performs. The 'what' portion is too abstract—it says 'guide for creating effective skills' without detailing the specific steps or outputs involved. Trigger terms are decent but could include more natural variations.

Suggestions

Add specific concrete actions like 'write YAML frontmatter, define descriptions and trigger terms, structure skill markdown files, validate skill format'

Include more natural trigger term variations such as 'skill.md', 'skill file', 'write a skill', 'skill template', 'add a new capability'

DimensionReasoningScore

Specificity

The description says 'creating effective skills' and mentions 'specialized knowledge, workflows, or tool integrations' but these are abstract categories, not concrete actions. It doesn't list specific things like 'write YAML frontmatter, define trigger terms, structure markdown sections.'

1 / 3

Completeness

It answers both 'what' (guide for creating effective skills that extend Claude's capabilities with specialized knowledge, workflows, or tool integrations) and 'when' (when users want to create a new skill or update an existing skill), with explicit trigger guidance.

3 / 3

Trigger Term Quality

Includes some natural terms like 'create a new skill', 'update an existing skill', and 'skill' which users would likely say. However, it misses variations like 'skill.md', 'skill file', 'write a skill', 'add a skill', 'skill template', or 'skill description'.

2 / 3

Distinctiveness Conflict Risk

The concept of 'creating skills' is fairly distinct, but the vague language about 'specialized knowledge, workflows, or tool integrations' could overlap with general coding or documentation skills. The term 'skill' as a trigger is somewhat specific to this domain but could conflict with general capability questions.

2 / 3

Total

8

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
NeverSight/skills_feed
Reviewed

Table of Contents

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.