CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lcx-contribute-bug-fix

Contribute a verified bug fix for LazyCodex, lazycodex-ai, omo-codex, bundled Codex skills, or upstream Codex CLI bugs. LazyCodex-owned defects get a fork PR against code-yeongyu/oh-my-openagent (base dev, source-tree paths under packages/omo-codex/plugin, with the changelog fragment); upstream Codex bugs get a fork PR against openai/codex. code-yeongyu/lazycodex is a generated distribution mirror and never gets a PR. Use when the user asks to fix a bug, contribute a bug fix, contribute to fix bug, open a PR for a bug, or debug and PR a LazyCodex/Codex defect.

Quality

90%

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.

An exceptionally actionable, well-sequenced operational skill with real validation feedback loops and verified bundle wiring. The main costs are token weight from repeated policy statements and a large inline shell library that belongs in a script file.

Suggestions

State the code-yeongyu/lazycodex no-PR rule once (e.g. in Required Outcome) and reference it elsewhere with 'never target the mirror (see above)' instead of restating the full rationale in four places.

Move the valid_source_checkout / recover_corrupt_source_checkout / sync_latest_source shell library into a bundled script (e.g. scripts/sync-sources.sh) and keep only the three sync_latest_source invocations plus one line on cache validation in the body.

Move the pointer issue template and the PR body template into a references/ file (or fold the template fully into create-pr-body.mjs output, which already produces it) so the body carries only the input JSON shape and the invocation.

DimensionReasoningScore

Conciseness

The body is operational rather than explanatory, but the mirror prohibition ('NEVER open a PR or push a branch against code-yeongyu/lazycodex') is repeated four times across sections, and a ~45-line shell library (valid_source_checkout / recover_corrupt_source_checkout / sync_latest_source) is inlined where a tighter summary or a bundle script would do.

3 / 5

Actionability

Everything is copy-paste ready: complete bash blocks for cloning, worktrees, label management, and PR creation; the exact JSON input shape for the PR body generator; the script invocation path; and full issue/PR templates.

5 / 5

Workflow Clarity

The 14-step workflow is clearly sequenced with explicit validation checkpoints (failing regression test before the fix, git status inspection before commit, checkout validation with quarantine-and-recover feedback for corrupt caches, post-fix QA) plus stop conditions and a gated destructive-cleanup step with a receipt.

5 / 5

Progressive Disclosure

Sections are well-organized and the single bundle reference (scripts/create-pr-body.mjs, invoked as '<skill-root>/scripts/create-pr-body.mjs') is clearly signaled and exists on disk. However, the long inline sync shell library and both full templates are content that could appropriately live in separate bundle files.

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 highly specific, complete description that states concrete per-repo deliverables and an explicit multi-phrase trigger clause. Its only weakness is that the generic trigger phrasing ('fix a bug', 'open a PR for a bug') could fire outside the LazyCodex/Codex niche.

Suggestions

Qualify the generic triggers, e.g. 'Use when the user asks to fix or PR a LazyCodex, omo-codex, or upstream Codex CLI defect' so 'fix a bug' alone does not match unrelated local bug-fix requests.

DimensionReasoningScore

Specificity

Names multiple concrete actions with full specifics — 'fork PR against code-yeongyu/oh-my-openagent (base dev, source-tree paths under packages/omo-codex/plugin, with the changelog fragment)', 'fork PR against openai/codex', and the explicit mirror exclusion 'never gets a PR' — giving comprehensive coverage of the skill's routing surface with no gaps.

5 / 5

Completeness

It explicitly answers both questions: the 'what' (contribute a verified bug fix, with per-repo deliverable routing) and the 'when' via a concrete 'Use when the user asks to...' clause with specific trigger phrases.

5 / 5

Trigger Term Quality

The trigger clause covers natural phrasings and their variants — 'fix a bug, contribute a bug fix, contribute to fix bug, open a PR for a bug, or debug and PR a LazyCodex/Codex defect' — which is comprehensive synonym coverage rather than just a few good keywords.

5 / 5

Distinctiveness Conflict Risk

The named projects (LazyCodex, omo-codex, Codex CLI) establish a clear niche, but unqualified triggers like 'fix a bug' or 'contribute a bug fix' are phrases users naturally say for any local bug fix, creating minor overlap risk with general fix tasks and the companion report-bug skill.

4 / 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/oh-my-openagent

Path

packages/omo-codex/plugin/components/lcx/skills/lcx-contribute-bug-fix/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.