CtrlK
BlogDocsLog inGet started
Tessl Logo

create-scratch

Create a new scratch file in .agents/scratches/

63

Quality

75%

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 ./.opencode/skills/create-scratch/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

The body is a clean, actionable instruction set for a simple single-purpose skill: concise, with three concrete executable command forms, a clear sequence, and a well-organized single-file structure. It appropriately assumes Claude's intelligence and needs no external references.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: it states the task steps and three executable bun commands without explaining what scratch files or heredocs are, and every section earns its place; it is not the 2-level padded variant.

3 / 3

Actionability

It provides fully executable, copy-paste-ready commands (direct, heredoc, and pipe invocation forms of bun scripts/create-scratch.ts) plus a concrete example of the resulting file format, matching the 'fully executable code/commands' anchor.

3 / 3

Workflow Clarity

This is a simple single-purpose skill with an unambiguous action and a sequenced three-step task list (determine slug -> gather content -> create file); per the simple_skills note a clear single-action skill can score 3, and there are no destructive/batch operations requiring validation checkpoints.

3 / 3

Progressive Disclosure

The skill is a single short file with no need for external references, and content is organized into clear sections (Task, Usage, Creating the File, File Format, Guidelines, Begin); per the guideline, a simple skill under ~50 lines with well-organized sections can score 3 without external file references.

3 / 3

Total

12

/

12

Passed

Description

50%

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 clear and honest about the single action it performs and its location, but it is terse: it lacks a 'Use when...' trigger clause, natural term variations, and multiple concrete actions. These gaps keep every dimension at the midpoint rather than the top.

Suggestions

Add a 'Use when...' trigger clause, e.g. 'Use when the user wants to jot down temporary notes, exploration ideas, or scratch content in .agents/scratches/'.

Broaden trigger terms to natural user phrasing such as 'notes', 'temporary notes', 'ideas', and 'exploration' to improve trigger_term_quality.

Mention the concrete outcomes (auto-generates a unique three-word ID, dates and titles the file) to lift specificity above a single action.

DimensionReasoningScore

Specificity

The description "Create a new scratch file in .agents/scratches/" names one concrete action and a specific path/domain, matching the 'names domain and some actions, but not comprehensive' anchor; it is below 3 because it lists only a single action rather than multiple specific concrete actions.

2 / 3

Completeness

It states what the skill does (create a new scratch file) but provides no 'Use when...' trigger guidance, so per the rubric a missing explicit trigger clause caps completeness at 2; it is above 1 because the what is clearly stated.

2 / 3

Trigger Term Quality

"scratch file" is a reasonably natural term, but the description omits common variations users might say (notes, temporary notes, ideas, exploration); matching the 'some relevant keywords but missing common variations' anchor rather than the broad 3-level coverage.

2 / 3

Distinctiveness Conflict Risk

The .agents/scratches/ path gives it a fairly distinct niche, but the verb 'create a scratch file' is generic enough to potentially overlap with note-taking skills; it is above 1 (not broadly conflicting) but lacks the explicit distinct triggers needed for 3.

2 / 3

Total

8

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
LibPDF-js/core
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.