CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-refactor

Restructure existing code while preserving observable behavior. Use for targeted technical debt or hotspot work with characterization tests.

59

Quality

68%

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 ./.agents/skills/oma-refactor/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-engineered process skill: the workflow is explicitly sequenced with validation checkpoints and error-recovery loops, and tooling guidance is concrete. Its main weaknesses are redundancy — the same guardrails restated across four sections — and references to resource files that are not present in the bundle.

Suggestions

Consolidate the repeated two-hats/behavior-mixing and Mikado rules into one authoritative section (e.g., Guardrails) and reference it from the workflow instead of restating it four times.

Ship the referenced resource files (resources/definition.md, resources/measurement.md, resources/governance.md) or inline their critical content — currently the git one-liners and tool registry they hold are unavailable.

Normalize the References section to consistent relative paths and add brief one-line descriptions for the shared core files, matching the treatment of the resources/ files.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (no padding with basic refactoring concepts), but the same rules repeat across four sections: "never mix behavior changes" appears in PREPARE (two-hats), Transitions, Guardrail 5, and the canonical workflow, while the Mikado procedure is restated in Scenes, Transitions, the failure table, and the workflow. This is 'mostly efficient but could be tightened' rather than the 'minor instances' of a 4.

3 / 5

Actionability

Concrete specifics are present: "uvx lizard / uvx radon", "jscodeshift / OpenRewrite / ast-grep / comby", "refactor:-typed commits", and explicit artifact paths, plus a directed per-transformation loop. It falls short of a 5 because key executable details (git forensics one-liners, tool registry) are deferred to resource files and no copy-paste command sequence exists for the verification step itself.

4 / 5

Workflow Clarity

The sequence is explicit (PREPARE → ACQUIRE → REASON → ACT → VERIFY → FINALIZE) with a hard validation checkpoint ("Re-run existing tests unchanged") and genuine feedback loops: the Mikado record-revert-recurse loop plus a Failure/Recovery table mapping each failure mode to a recovery. This matches the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.

5 / 5

Progressive Disclosure

References are clearly labeled, described, and one level deep (resources/definition.md, resources/measurement.md, resources/governance.md, plus shared core files). However, none of the referenced files exist in the bundle, and the References section mixes path styles with uneven formatting; some inlined process detail duplicates what the resource files would carry — 'good structure... minor organization gaps' rather than fully clean navigation.

4 / 5

Total

16

/

20

Passed

Description

62%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 serviceable description with a clear what and an explicit use-when clause, but it undersells the skill's breadth. It omits the primary trigger term "refactor" and the concrete transformation vocabulary (extract, move, rename, decompose) that would improve both specificity and trigger coverage.

Suggestions

Add the word "refactor" (and "clean up") to the description — they are the most common terms users say for this need, yet neither appears.

Enumerate the concrete transformations (extract, move, rename, decompose, de-duplicate) to raise specificity beyond the single 'restructure' action.

Broaden the 'Use for' clause to cover common triggers like modernizing legacy code or preparatory refactoring before a feature, not only technical debt and hotspot work.

DimensionReasoningScore

Specificity

The description states "Restructure existing code while preserving observable behavior" plus "characterization tests", naming the domain and 1-2 concrete actions, but never enumerates the actual transformations (extract, move, rename, decompose). It fits the 'names domain and 1-2 concrete actions, but not comprehensive' anchor rather than the 'several specific actions' anchor.

3 / 5

Completeness

It answers both parts: the what ("Restructure existing code while preserving observable behavior") and an explicit when ("Use for targeted technical debt or hotspot work with characterization tests"). The when clause is narrow — it omits common triggers like general clean-up or modernization requests — so it is not a 5, but the explicit 'Use for' phrasing keeps it above a 3.

4 / 5

Trigger Term Quality

Terms like "technical debt", "hotspot", "characterization tests", and "restructure" are natural user phrasing, but the most common trigger words a user would actually say — "refactor" and "clean up" — are absent. This matches 'some relevant keywords but missing common variations or synonyms' rather than 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

"Preserving observable behavior" and "characterization tests" carve out a clear refactoring niche that is unlikely to fire for debugging or feature work. There is minor overlap risk with adjacent code-quality/audit skills, matching 'mostly distinct; minor overlap risk with closely related skills'.

4 / 5

Total

14

/

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.

Validation — 16 / 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.