CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-creator-skill

Triggers when the user wants to create, edit, improve, or debug an OpenLoaf custom Skill. Typical phrasings: "help me create a skill", "build a new skill", "turn what we just did into a skill", "write a skill that auto-XX", "tweak this skill", "why isn't this skill triggering", "edit my custom skill", "add a global skill", "add a skill to the current project". Any create / modify / tune request touching a `SKILL.md` under `.openloaf/skills/` should load this skill. Also applies when the user wants to understand the skill format, troubleshoot triggering issues, or solidify a conversation workflow into a reusable capability. Not for: modifying built-in skills (e.g. file-ops, email-ops) — those are read-only capabilities shipped with the platform.

73

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 is a well-structured, actionable instructional guide with a clear sequenced workflow, explicit validation checkpoints, and a strong troubleshooting table. Its main weaknesses are minor redundancy across sections and the absence of a complete worked example of a generated SKILL.md, which its own template recommends.

Suggestions

Add one complete worked example of a finished SKILL.md (frontmatter + body) to satisfy the 'Examples' section the skill itself recommends and to lift actionability toward 5.

De-duplicate the repeated guidance (e.g. the 'err wide not narrow' rule and the global-vs-project distinction appear in both their own sections and the Iron Rules) to tighten conciseness.

Consider splitting the troubleshooting table and openloaf.json/colorIndex reference detail into a short references file to practice the progressive disclosure the skill preaches.

DimensionReasoningScore

Conciseness

The ~207-line body is lean (well under its own 500-line ideal) and avoids explaining concepts Claude already knows, but several ideas are restated across sections (the 'err wide not narrow' rule and the global-vs-project distinction each appear in multiple places), keeping it just below the 'every token earns its place' bar.

4 / 5

Actionability

Guidance is concrete and specific for an instruction-only skill (exact paths, a real openloaf.json template with a colorIndex palette, Glob conflict-check commands, a symptom/cause/fix troubleshooting table), but it recommends an 'Examples' section for new skills without itself providing one complete worked SKILL.md example, which is a minor gap.

4 / 5

Workflow Clarity

A clear five-step creation sequence is paired with an explicit validation gate (conflict-check via Glob before saving, with overwrite/rename/cancel on conflict) and an explicit verify-and-iterate feedback loop plus a troubleshooting table, matching the 'clear sequence with explicit validation steps; feedback loops for error recovery; checklists' anchor.

5 / 5

Progressive Disclosure

The skill is self-contained and well-sectioned with clear headers and no nested references, which is appropriate given no bundle files exist; it sits at 'good structure; most content appropriately placed' rather than 5 because at 200+ lines it remains a single-file monolith with no one-level-deep reference split despite its own advice to split when content grows.

4 / 5

Total

17

/

20

Passed

Description

100%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 exemplary: it pairs concrete capabilities with an extensive list of natural trigger phrasings (including synonyms and colloquial variants), explicitly marks the when-condition, and draws a clear 'Not for' boundary against built-in skills. It is somewhat long, but the length is dense with genuinely useful trigger terms rather than fluff. Voice is appropriately third-person/imperative throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('create, edit, improve, or debug', 'understand the skill format', 'troubleshoot triggering issues', 'solidify a conversation workflow into a reusable capability') with comprehensive coverage of the skill-authoring domain, matching the 'lists multiple specific concrete actions; comprehensive coverage' anchor.

5 / 5

Completeness

Explicitly answers both what ('create, edit, improve, or debug an OpenLoaf custom Skill') and when ('Triggers when the user wants to...' plus concrete trigger phrases and 'Any create / modify / tune request touching a SKILL.md'), matching the 'clearly and explicitly answers both what AND when with concrete trigger phrases' anchor.

5 / 5

Trigger Term Quality

Includes an extensive, natural set of phrasings users would actually say ('help me create a skill', 'tweak this skill', 'why isn't this skill triggering', 'turn what we just did into a skill') with synonyms and colloquial variants, matching the 'comprehensive coverage of natural terms including synonyms' anchor.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (OpenLoaf custom Skill authoring under .openloaf/skills/) with distinct triggers and an explicit 'Not for: modifying built-in skills' boundary that minimizes conflict risk, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

20

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
itsablabla/openloaf-web
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.