CtrlK
BlogDocsLog inGet started
Tessl Logo

create-skill

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.

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/skills/create-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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, highly actionable skill-creation workflow with real bundled scripts, exact invocations, per-step skip conditions, and an explicit validation feedback loop. Its weaknesses are padded prose and inlined background material (skill anatomy, per-OS install instructions) that inflate the token budget without adding procedural value.

Suggestions

Cut marketing-fluff sentences such as 'The script conveniently generates... making the skill creation process much more efficient and reliable' and keep only the factual effects of the script.

Move the 'About Skills' background (what skills provide, anatomy tree, progressive-disclosure principle) and the per-OS Python install instructions into a references/ file, keeping SKILL.md focused on the 7-step procedure.

Make Step 6 'Iterate' actionable by specifying how to capture observed struggles (e.g. which file or section to update and how to re-run quick_validate.py afterwards).

DimensionReasoningScore

Conciseness

The body is mostly efficient procedural guidance, but contains padding and over-explanation: 'The script conveniently generates a new template skill directory... making the skill creation process much more efficient and reliable', plus a multi-paragraph meta-explanation of what skills are ('Skills are modular, self-contained packages... Think of them as "onboarding guides"') that partially duplicates the anatomy tree. This matches anchor 3 ('mostly efficient but includes some unnecessary explanation or could be tightened') rather than anchor 4, since several sentences are pure fluff.

3 / 5

Actionability

Concrete, executable commands are given for every operational step (python3 scripts/init_skill.py <skill-name> --path <output-directory>, python3 scripts/quick_validate.py <path/to/skill-folder>, packmind-cli skills add <path/to/skill-folder>), and both referenced scripts exist in the bundle. It falls short of anchor 5 because Step 6 'Iterate' is abstract direction ('Notice struggles or inefficiencies') without concrete commands, and Step 1's elicitation questions are illustrative rather than executable.

4 / 5

Workflow Clarity

The 7-step creation process is explicitly sequenced with skip conditions per step ('Skip this step only when...'), prerequisite verification before each script run, and an explicit validation feedback loop in Step 5 ('If validation fails, fix the reported errors and run the validation again'). This matches anchor 5's 'clear sequence with explicit validation steps; feedback loops for error recovery'.

5 / 5

Progressive Disclosure

Structure is good: clear section headers, and the two bundle references (scripts/init_skill.py, scripts/quick_validate.py) are real files, clearly signaled at point of use. Some inline content that could live in a reference file remains in SKILL.md (the multi-section 'About Skills' anatomy explanation and per-OS Python install instructions), so it matches anchor 4 rather than anchor 5's cleanly split overview.

4 / 5

Total

16

/

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 third-person description with an explicit use-when clause and natural trigger phrasing for a distinct niche. Its main weakness is the vague opening 'Guide for creating effective skills', which conveys the domain without concrete capability statements or common trigger synonyms.

Suggestions

Replace the generic 'Guide for creating effective skills' opening with concrete capabilities, e.g. 'Create, structure, validate, and distribute skills that extend Claude's capabilities...'.

Add common trigger synonyms users would say, such as 'build a skill', 'make a skill', 'author a skill', or 'write a SKILL.md', to improve trigger term coverage.

Mention the concrete outcomes of the skill (init skill scaffolding, validation via quick_validate.py, distribution via packmind-cli) to sharpen the 'what' half of the description.

DimensionReasoningScore

Specificity

The description names the domain ('creating effective skills') and 1-2 concrete actions ('create a new skill (or update an existing skill)'), but the opening 'Guide for creating effective skills' is generic and it does not list several specific actions like structuring, validating, or distributing skills. It is above anchor 2 (which names only a domain with minimal actions) but does not reach anchor 4's 'several specific actions'.

3 / 5

Completeness

Both what ('Guide for creating effective skills... extends Claude's capabilities with specialized knowledge, workflows, or tool integrations') and when ('This skill should be used when users want to create a new skill (or update an existing skill)') are present and in third person. The 'what' portion is a single fairly vague sentence rather than concrete capabilities, so it does not clearly match anchor 5.

4 / 5

Trigger Term Quality

Natural user phrases are present ('when users want to create a new skill', 'update an existing skill', 'skills'), matching how a user would phrase the request. A few natural variations are missing ('build a skill', 'make a skill', 'SKILL.md', 'skill authoring'), so it falls short of anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Skill creation/updating is a clear niche with distinct triggers and minimal conflict risk with other skills. The broad phrase 'extends Claude's capabilities with specialized knowledge, workflows, or tool integrations' could weakly overlap with skill-usage or tool-integration skills, keeping it below anchor 5.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 12 missing

Warning

Total

15

/

16

Passed

Repository
cteyton/packmind
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.