CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lcx-report-bug

Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and GitHub routing.

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

The canonical home for this skill is lcx-report-bug in code-yeongyu/oh-my-openagent

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 highly actionable and the workflow is exceptionally well-sequenced with validation, recovery, and stop-condition checkpoints for an outward-facing GitHub operation. Its weaknesses are token efficiency — the mirror-repo PR prohibition is repeated five times — and the absence of any bundle structure, with a 45-line script and full templates inlined in a single long file.

Suggestions

Move the source-sync bash (valid_source_checkout, recover_corrupt_source_checkout, sync_latest_source) into a scripts/ file and invoke it from the workflow step, cutting ~45 lines from SKILL.md.

Extract the issue and PR body templates into references/ files (e.g. references/issue-template.md, references/pr-template.md) and reference them one level deep from the workflow.

State the "never PR or push a branch against code-yeongyu/lazycodex; fixes go to code-yeongyu/oh-my-openagent (base dev)" rule once in the routing section and once in Stop Conditions, removing the three intermediate restatements.

DimensionReasoningScore

Conciseness

The body is mostly tight operational instruction with no concept over-explanation, but the "never PR against code-yeongyu/lazycodex" rule is restated five times (intro routing, step 11, PR template intro, GitHub Creation Path, Stop Conditions) and a ~45-line source-sync script plus two full templates are inlined. This matches 'mostly efficient but could be tightened' rather than the minor-trimming bar for 4.

3 / 5

Actionability

Fully executable guidance throughout: complete bash for checkout validation/quarantine and re-sync, copy-paste `gh issue create`/`gh pr create`/label commands, and complete fill-in issue and PR templates, with a gh → Browser Use → Computer Use fallback chain. Placeholders ("<clear title>") are clearly marked and the $EDITOR case is explicitly handled with a file-tool fallback.

5 / 5

Workflow Clarity

An 11-step sequenced workflow with explicit validation checkpoints (valid_source_checkout before routing, duplicate/lead-PR search before creating, visual confirmation before browser submit), error-recovery loops (corrupt-cache quarantine, gh-clone fallback, re-sync on every run), and a Stop Conditions checklist — matching the top anchor. Not 4: checkpoints are explicit and feedback loops are present for every fragile operation.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and all ~254 lines live inline: the long source-sync script and the issue/PR templates are content that clearly belongs in scripts/ or references/ files. Section headers give real structure, so this sits at 'some structure but content that should be separate is inline' rather than the minimal-structure anchor 2 or the mostly-appropriate-placement anchor 4.

3 / 5

Total

16

/

20

Passed

Description

95%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: it states the concrete deliverable (a high-signal, source-backed bug issue or PR routed to the owning repo) and gives an explicit, synonym-rich 'Use this whenever' trigger clause covering the product names users would mention. Only minor headroom on breadth of stated actions.

DimensionReasoningScore

Specificity

Quotes several concrete capabilities — "Create a high-signal bug issue or PR", "source-backed root cause, reproduction steps, fix guidance, and GitHub routing" — matching the anchor for several specific actions with minor gaps. It is not 5 because the action set reduces to creating an issue/PR plus routing, rather than comprehensive coverage of distinct actions.

4 / 5

Completeness

Explicitly answers both: what ("Create a high-signal bug issue or PR... source-backed root cause, reproduction steps, fix guidance, and GitHub routing") and when ("Use this whenever the user asks to report, file, open, or triage...") with concrete trigger phrases. Anchor 5 fits; anchor 4's weaker 'when' does not.

5 / 5

Trigger Term Quality

"report, file, open, or triage" plus "LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug" gives comprehensive natural-verb and product-name synonym coverage a user would actually say. Not 4: no common variation of the request is missing.

5 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche (LazyCodex/Codex bug reporting and repo routing) with distinct product-name triggers, so overlap with other skills is minimal. Not 4: there is no closely related skill surface it would accidentally trigger on.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

code-yeongyu/lazycodex

Path

plugins/omo/components/lcx/skills/lcx-report-bug/SKILL.md

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.