CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-skill-creator

Create or update OMA skills in the SSL-lite human-readable format. Use when adding a new `.agents/skills/{skill-name}/SKILL.md`, converting an existing skill to the standardized Scheduling / Structural Flow / Logical Operations / References structure, or validating whether a skill has enough routing, execution, resource, and safety detail.

64

Quality

76%

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 ./benchmarks/runs/oma/.agents/skills/oma-skill-creator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 well-organized and broadly actionable with a clear multi-scene workflow and recovery guidance, but it is held back by repeated skill-type classification, a missing explicit retry loop, and references to bundle files that are not actually present.

Suggestions

Consolidate the command/workflow/judgment/reference-heavy classification into one canonical location and reference it from the other sections instead of restating it.

Add an explicit validate→fix→retry step to the Canonical workflow path (e.g. 'if validation fails, fix the reported issue and re-run step 6 before finalizing').

Either ship the referenced files (resources/ssl-lite-template.md, resources/validation-checklist.md, ../_shared/core/*.md) or remove/correct the References entries so navigation is not broken.

DimensionReasoningScore

Conciseness

The body is mostly efficient (tables, numbered steps, terse guardrails), but the command/workflow/judgment/reference-heavy classification is repeated roughly four times (Expected inputs, Control-flow features, Entry, Canonical workflow path) and the Guardrails section restates constraints already covered elsewhere.

3 / 5

Actionability

Provides concrete, executable guidance — named tools ("rg, find, awk, sed, git diff --check", "apply_patch"), specific paths, a numbered Canonical workflow path, and explicit guardrails — with only the minor gap that execution leans on a template file that is not present in the bundle.

4 / 5

Workflow Clarity

Clear sequencing via Entry, Scenes (PREPARE→FINALIZE), and a Canonical workflow path, plus a VERIFY scene and a Failure and recovery table; however the canonical path's validation step (step 6) does not spell out an explicit validate→fix→retry loop.

4 / 5

Progressive Disclosure

The in-body section structure (Scheduling / Structural Flow / Logical Operations / References) is clean, but the References section points to resources/ssl-lite-template.md, resources/validation-checklist.md, and ../_shared/core/*.md that do not exist in the bundle, so the signaled navigation is broken.

3 / 5

Total

14

/

20

Passed

Description

88%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 strong, well-structured description that explicitly covers both capability and trigger conditions with concrete, domain-specific language. The main residual risk is overlap with sibling skill-creation tools, which the description does not explicitly bound.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Create or update OMA skills", "adding a new .agents/skills/{skill-name}/SKILL.md", "converting an existing skill to the standardized ... structure", and "validating whether a skill has enough routing, execution, resource, and safety detail" — giving comprehensive coverage of the skill's domain.

5 / 5

Completeness

Clearly states what ("Create or update OMA skills in the SSL-lite human-readable format") and explicitly answers when via an "Use when ..." clause with three concrete trigger scenarios.

5 / 5

Trigger Term Quality

Good natural keyword coverage ("OMA skills", "SSL-lite", ".agents/skills/{skill-name}/SKILL.md", "Scheduling / Structural Flow / Logical Operations / References"), but a few natural phrases a user might say (e.g. "skill template", "skill authoring", "skill format") are only weakly represented.

4 / 5

Distinctiveness Conflict Risk

The niche (OMA skill authoring in SSL-lite format) and triggers (specific path and structure names) are distinct, but "creating a skill" plausibly overlaps with adjacent tooling (skill installer, plugin creator) and the description carries no explicit disambiguation.

4 / 5

Total

18

/

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
first-fluke/oh-my-agent
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.