CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-debug

Bug diagnosis and fixing specialist - analyzes errors, identifies root causes, provides fixes, and writes regression tests. Use for bug, debug, error, crash, traceback, exception, and regression work.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

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.

A well-structured debugging protocol with explicit sequencing, validation checkpoints, and a feedback loop, plus concrete search commands and a guardrail checklist. The main gaps are mild abstraction overhead and some inlined content that duplicates what the referenced protocol files should carry.

Suggestions

Trim the SSL-primitive and resource-scope mapping tables, or move them into resources/execution-protocol.md, to reduce token overhead that doesn't directly aid debugging.

Expand the canonical workflow path beyond two `rg` examples into a small, copy-paste-ready reproduction→fix→verify command sequence for the common case.

De-duplicate the inlined scene/guardrail detail against resources/execution-protocol.md so SKILL.md stays a lean overview pointing one level deep.

DimensionReasoningScore

Conciseness

Dense and largely non-redundant with no over-explanation of basics, but some structural ceremony (SSL primitive mappings, resource-scope tables) adds tokens beyond the lean minimum.

4 / 5

Actionability

Provides concrete commands (`rg "<error-message-or-symbol>"`, Serena `find_symbol`/`search_for_pattern`) and a guardrail list, though much of the scene flow stays high-level rather than fully executable step-by-step.

4 / 5

Workflow Clarity

Clear sequenced Entry/Scenes/Transitions/Exit with an explicit VERIFY checkpoint, a fix-fails-verification feedback loop, and a guardrails checklist — covering validation, recovery, and checklist for a code-mutating task.

5 / 5

Progressive Disclosure

Well-organized headers with clearly signaled one-level references (resources/*.md, ../_shared/*.md); no bundle dirs exist, and some inlined protocol detail overlaps the referenced execution-protocol.md rather than being fully split out.

4 / 5

Total

17

/

20

Passed

Description

96%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, concise description that clearly states concrete capabilities and an explicit "Use for..." trigger clause with comprehensive natural keywords. The only slight weakness is minor overlap risk with QA/review skills, which is better handled by the body's "When NOT to use" section.

DimensionReasoningScore

Specificity

Names four concrete actions ("analyzes errors, identifies root causes, provides fixes, and writes regression tests"), giving comprehensive coverage of the debugging domain with no gaps.

5 / 5

Completeness

Explicitly answers both what (analyze/diagnose/fix/test) and when ("Use for bug, debug, error, crash, traceback, exception, and regression work"), matching the anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

Lists natural synonyms users actually say ("bug, debug, error, crash, traceback, exception, and regression"), covering the full vocabulary of the domain; no file extensions apply here.

5 / 5

Distinctiveness Conflict Risk

Debugging is a clear niche with distinct triggers, but there is minor overlap risk with general QA/code-review skills; not full anchor-5 minimal-conflict.

4 / 5

Total

19

/

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.