CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

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

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.

A highly actionable, well-sequenced workflow with excellent validation and fallback coverage, undermined by repetition (the routing rule and label/footer rules each restated several times) and by keeping everything — a long shell script and two full templates — inlined in a single large file. Splitting the sync script and templates into bundle files and deduplicating the routing rules would raise both conciseness and progressive disclosure.

Suggestions

Move the source-sync shell block (valid_source_checkout / recover_corrupt_source_checkout / sync_latest_source) into a scripts/sync-sources.sh bundle file and invoke it from the workflow step, reducing SKILL.md by ~40 lines.

State the 'never file a PR against code-yeongyu/lazycodex' rule once (e.g., in the routing bullet or Stop Conditions) instead of four times, and consolidate the label/footer requirements into the 'Required Label And Footer' section only.

Move the issue body and PR body templates into references/ (e.g., references/issue-template.md and references/pr-template.md) with clearly signaled links, so the main workflow file remains an overview.

DimensionReasoningScore

Conciseness

The body is mostly earned — executable `gh` commands, complete templates, no explanation of concepts Claude already knows — but it is noticeably padded through repetition: the 'never file a PR against code-yeongyu/lazycodex' rule appears in four places (intro bullets, step 11, PR template section, Stop Conditions), and the label/footer requirement is restated three times. The ~44-line source-sync shell block could also be tightened or externalized. This fits anchor 3 ('mostly efficient but includes some unnecessary explanation or could be tightened') better than anchor 4, which requires only minor trimming, but better than anchor 2, since nothing teaches material Claude already knows.

3 / 5

Actionability

Guidance is fully executable end-to-end: a copy-paste-ready source-sync script with corruption recovery and branch detection, exact `gh issue list/create/comment/edit` and `gh pr create` commands, complete issue and PR body templates, label-creation with a graceful fallback, and explicit browser/computer-use fallbacks. Nothing is pseudocode; placeholders like "<clear title>" are appropriate template slots. This matches the anchor-5 'fully executable, copy-paste ready commands covering common cases'.

5 / 5

Workflow Clarity

The 11-step workflow is clearly sequenced with explicit validation checkpoints for an outward-facing (issue/PR creation) operation: checkout validation with quarantine-and-retry feedback loops, duplicate search before creating, explicit repo/title/body verification before browser submission, and a 'do not file' checklist in Stop Conditions. The destructive/batch cap of 3 does not apply because verification steps are present throughout; this matches anchor 5 (clear sequence, explicit validation, error-recovery loops, checklist).

5 / 5

Progressive Disclosure

There are no bundle files (no references/, scripts/, or assets/), so everything lives in a ~250-line SKILL.md. Section headers are clear and well-ordered, but content that clearly belongs in separate files is inlined: the ~44-line source-sync shell block would sit naturally in scripts/ and the issue/PR body templates in a references/ file. This fits anchor 3 ('some structure ... content that should be separate is inline') rather than anchor 2 (structure here is good, not minimal) or anchor 4 (no external split at all for a 250-line skill).

3 / 5

Total

16

/

20

Passed

Description

100%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.

An exemplary description: one sentence delivers a concrete 'what' (create a source-backed bug issue or PR in the owning repo) and an explicit 'when' with natural trigger verbs and full product synonyms. It is dense but not padded, and the niche is sharply distinct.

DimensionReasoningScore

Specificity

"Create a high-signal bug issue or PR in the repo that owns the defect" names the concrete artifacts, and the description enumerates the substantive deliverables — "source-backed root cause, reproduction steps, fix guidance, and GitHub routing" — giving comprehensive, concrete coverage of the skill's actions within its niche. It does not fit anchor 4 because no meaningful action category of this skill (create issue/PR, route to owning repo, deliver root cause/repro/fix guidance) is left out.

5 / 5

Completeness

The 'what' is explicit ("Create a high-signal bug issue or PR in the repo that owns the defect") and the 'when' is explicit with concrete trigger phrases ("Use this whenever the user asks to report, file, open, or triage a ... bug"). Both halves are clearly and directly answered, matching the anchor-5 example structure exactly; anchor 4 would require the 'when' to be less explicit than it is.

5 / 5

Trigger Term Quality

"report, file, open, or triage" gives four natural verb triggers, and "LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI" covers the full synonym set a user would actually name. This matches the anchor-5 pattern of comprehensive natural terms including synonyms rather than the anchor-4 'a few natural terms missing'.

5 / 5

Distinctiveness Conflict Risk

The description is scoped to a clear niche — bug reporting for named repos/products (LazyCodex / upstream Codex CLI) with GitHub routing — so it would not plausibly trigger for an unrelated skill. Product names and repo-level routing give it a distinct trigger surface with minimal overlap risk, matching anchor 5 rather than anchor 4's 'minor overlap risk with closely related skills'.

5 / 5

Total

20

/

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/oh-my-openagent
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.