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.

69

Quality

85%

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, actionable skill body with a clear sequenced workflow, explicit verification and recovery loops, and disciplined guardrails. Remaining weaknesses are moderate redundancy in meta sections and the References listing, and unverifiable/duplicated reference paths.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — no basic-concept explanations, with table-formatted actions, guardrails, and transitions instead of prose padding. It falls short of 'lean and efficient; every token earns its place' due to redundancy: the References section lists the same resource files twice (narrative lines plus a bullet list), the Dependencies and Tools sections overlap, and meta-scaffolding sections like 'Resource scope' and 'Control-flow features' add bookkeeping rather than instruction. It is well above 'noticeably verbose'.

4 / 5

Actionability

Concrete, executable guidance is present: the canonical workflow gives real commands (`rg "<error-message-or-symbol>"`, `rg --files`), Serena MCP calls are written as exact signatures (`find_symbol("functionName")`), and outputs/paths are specific (`.agents/results/bugs/`). Minor gaps remain — 'run the smallest reproduction command first' is generic with no example reproduction command, and the workflow snippet is thin compared to the level of detail elsewhere. This fits 'mostly executable guidance; concrete code or commands with minor gaps' rather than fully copy-paste-ready coverage.

4 / 5

Workflow Clarity

The PREPARE → ACQUIRE → REASON → ACT → VERIFY → FINALIZE scenes give a clear sequence with an explicit validation stage (VERIFY re-runs failing and related checks), feedback loops for error recovery ('If the first fix fails verification, return to root-cause analysis'; reproduction-failure fallback), and referenced checklists (resources/checklist.md, resources/debugging-checklist.md). This matches the top anchor including the feedback-loop requirement; score 4 would require missing checkpoints, and none are.

5 / 5

Progressive Disclosure

The body keeps the overview inline and points detailed material to one-level-deep, purpose-labeled references (execution steps, examples, checklist, error recovery, bug report template, etc.) — good structure overall. It is not the top anchor because the reference list is duplicated within the References section, and several referenced paths (resources/*.md, ../_shared/core/*.md) do not exist in the provided bundle and include cross-package references outside the skill directory, which adds navigation and verification gaps.

4 / 5

Total

17

/

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 description that clearly states capabilities and explicit trigger terms in third person without padding. The main improvement opportunity is broadening trigger coverage (stack trace, failing test, performance/slowdown terms).

DimensionReasoningScore

Specificity

The description lists four concrete, distinct actions — "analyzes errors, identifies root causes, provides fixes, and writes regression tests" — which comprehensively covers the bug-fixing domain from diagnosis to regression coverage. It matches the anchor for multiple specific concrete actions with comprehensive coverage; score 4 would require minor gaps, and none are evident.

5 / 5

Completeness

It explicitly answers both questions: what it does ("analyzes errors, identifies root causes, provides fixes, and writes regression tests") and when to use it ("Use for bug, debug, error, crash, traceback, exception, and regression work") with concrete trigger phrases. This directly matches the top anchor; the 'when' clause is explicit, so the cap of 3 for missing trigger guidance does not apply.

5 / 5

Trigger Term Quality

"Use for bug, debug, error, crash, traceback, exception, and regression work" gives good natural keyword coverage across the domain, but a few terms users would naturally say are missing (e.g., "stack trace" as distinct from "traceback", "failing test", "broken", "performance/slowdown" — performance issues are only mentioned in the body, not the description). This fits the 'good keyword coverage; a few natural terms missing' anchor rather than the comprehensive-with-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

Bug diagnosis and fixing is a distinct niche with dedicated triggers (crash, traceback, exception, regression), but there is minor overlap risk with closely related skills such as testing, code review, or general development skills — the body itself acknowledges routing ambiguity ("General code review -> use QA Agent"). This fits 'mostly distinct; minor overlap risk with closely related skills' rather than the minimal-conflict top anchor.

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.

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.