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. Opens a fork PR only for upstream openai/codex; LazyCodex-owned defects become a verified-fix issue on code-yeongyu/lazycodex (never a PR — that repo is a generated distribution mirror). 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.

68

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 highly actionable, well-sequenced workflow: every step has executable commands, validation checkpoints, and failure-recovery paths, and the destructive operations (branch push, issue/PR creation, worktree cleanup) are guarded by explicit stop conditions. The main cost is token weight — the defensive source-sync scaffolding and the PR template that duplicates the generator script inflate the body without adding proportionate guidance.

Suggestions

Move the sync_latest_source/valid_source_checkout/recover_corrupt_source_checkout bash from step 3 into a bundled script (e.g. scripts/sync-sources.sh) and invoke it in one line, cutting ~40 lines of git plumbing Claude can rederive if needed.

Drop or compress the "PR Body Template" section: scripts/create-pr-body.mjs already generates that exact structure, so showing the JSON input shape plus one sentence pointing to the generated output format is sufficient.

Extract the Verified-Fix Issue Template into a references/ file referenced by path, so the main workflow stays scannable and the template is loaded only at delivery time.

DimensionReasoningScore

Conciseness

The body is mostly lean executable bash with little concept explanation, but the ~45-line sync_latest_source/valid_source_checkout defensive scaffolding in step 3 is git plumbing Claude could rederive, and the "PR Body Template" section duplicates the structure that scripts/create-pr-body.mjs already generates. Mostly efficient with some content that could be tightened — the 3 anchor.

3 / 5

Actionability

Fully executable throughout: exact gh/git commands with fallbacks, copy-paste-ready templates for both targets, and the PR body generator is a real bundled script with its JSON input shape and CLI invocation shown. Placeholders like <short-slug> are conventional and unambiguous.

5 / 5

Workflow Clarity

Thirteen sequenced steps with explicit validation checkpoints (failing regression test written before production changes, confirmation the failure is the bug not a fixture, git status inspected before commit, regression + adjacent tests + real-surface QA after) and error-recovery loops (corrupt-checkout quarantine, label-management fallback, gh-clone fallback). Stop conditions and a cleanup receipt close the loop — matches the 5 anchor.

5 / 5

Progressive Disclosure

Clear sections and a real, well-signaled one-level-deep reference to scripts/create-pr-body.mjs (verified to exist with matching input shape). Minor gaps: the long source-sync bash block and the two full deliverable templates are inlined in SKILL.md and would sit better in bundled scripts/references, keeping the overview leaner.

4 / 5

Total

17

/

20

Passed

Description

83%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 a concrete what with explicit repository routing and deliverables, and closes with a genuine "Use when..." clause listing natural user phrasings. Its only weaknesses are a trigger term set that misses a few synonyms and a broad "fix a bug" trigger that could overlap with ordinary debugging requests.

DimensionReasoningScore

Specificity

Names several concrete actions with named repos: "Contribute a verified bug fix", "Opens a fork PR only for upstream openai/codex", "LazyCodex-owned defects become a verified-fix issue on code-yeongyu/lazycodex". Falls just under the 5 anchor because the actual fix-development and verification workflow is only implied by the word "verified" rather than stated.

4 / 5

Completeness

Explicitly answers what (verified bug fix delivered as a fork PR for openai/codex or a verified-fix issue on code-yeongyu/lazycodex, never a PR there) and when ("Use when the user asks to fix a bug, contribute a bug fix, ... open a PR for a bug"), with concrete trigger phrases matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

"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" covers natural phrasings well, including the ungrammatical-but-real "contribute to fix bug". A few common synonyms like "patch", "resolve", or "bugfix" are missing, so it fits the 4 anchor (good coverage, a few natural terms missing) rather than 5.

4 / 5

Distinctiveness Conflict Risk

Named repositories and delivery-specific triggers (fork PR, verified-fix issue) carve a clear niche distinct from general debugging or bug-reporting skills. "Fix a bug" is broad enough that a user asking to fix a local bug in their own code could trigger this skill, which is minor overlap with closely related skills — the 4 anchor.

4 / 5

Total

17

/

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.