CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/omo-codex/plugin/components/lcx/skills/lcx-contribute-bug-fix/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 contribution workflow with strong validation gates and a correctly used bundled PR-body generator. Its weaknesses are length and duplication — the inline shell source-sync library and the redundant PR body template inflate the body and belong in the bundle rather than SKILL.md.

Suggestions

Move the valid_source_checkout / recover_corrupt_source_checkout / sync_latest_source shell functions into a bundled script (e.g. scripts/sync-sources.sh) and invoke it in one line from the workflow to cut ~45 lines from the body.

Delete the 'PR Body Template' section or reduce it to one line pointing at scripts/create-pr-body.mjs — the script already emits that exact structure, so the duplication costs tokens and risks drift if the script changes.

Tighten step 3's prose (routing rules are already stated in the opening section) and resolve the '<skill-root>' placeholder into a concrete relative path so the script invocation is copy-paste ready.

DimensionReasoningScore

Conciseness

The body is dense and command-first with no concept explanations Claude already knows, but it runs ~270 lines and repeats itself: the 'PR Body Template' section duplicates the exact structure the bundled create-pr-body.mjs emits, and a ~45-line shell library (valid_source_checkout, recover_corrupt_source_checkout, sync_latest_source) is inlined. Mostly efficient but could be tightened — matches anchor 3 rather than 4.

3 / 5

Actionability

Guidance is overwhelmingly executable: complete bash blocks for clone/worktree/branch, commit, label handling, fork-and-PR and issue creation, plus a concrete JSON input shape for the real bundled script. Not a 5: placeholders like '<short-slug>' and '<skill-root>' require the reader to resolve paths, and the non-gh git fallbacks are only sketched once.

4 / 5

Workflow Clarity

Thirteen explicitly numbered steps with validation checkpoints throughout: reproduce before fixing, a failing regression test confirmed to fail for the right reason, post-fix verification, 'Inspect the status first so the delivered diff cannot be empty or stale', corrupt-checkout quarantine before reuse, and a Stop Conditions section with error-recovery guidance. This is the anchor-5 pattern (validate → fix → retry, explicit gating).

5 / 5

Progressive Disclosure

The single bundled file (scripts/create-pr-body.mjs) is real, correctly referenced, and one level deep — but scored against the actual bundle, the body inlines a ~45-line shell sync library and a full duplicate PR-body template that clearly belong in a bundled script/reference file. Structure exists (clear section headers) but content that should be separate is inline, matching anchor 3.

3 / 5

Total

15

/

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 concrete deliverables per target repository, encodes the critical PR-vs-issue routing rule, and closes with an explicit multi-phrase 'Use when' trigger clause. The only weaknesses are unenumerated workflow steps in the 'what' and slightly generic core trigger phrases that could overlap with general bug-fix requests.

DimensionReasoningScore

Specificity

Concrete actions are named — 'Opens a fork PR only for upstream openai/codex', 'LazyCodex-owned defects become a verified-fix issue on code-yeongyu/lazycodex' — with explicit target enumeration. Not a 5: the description stops at routing/delivery and does not mention the debug-reproduce-verify workflow that is the skill's core.

4 / 5

Completeness

Both questions are answered explicitly: the 'what' ('Contribute a verified bug fix... fork PR... verified-fix issue') and the 'when' via a dedicated 'Use when...' clause listing concrete trigger phrases. This matches the anchor-5 example structure directly.

5 / 5

Trigger Term Quality

'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 and their variants well. Not a 5: it misses common synonyms such as 'submit a patch', 'upstream a fix', or 'send a PR'.

4 / 5

Distinctiveness Conflict Risk

The niche is clear — repo-specific routing between 'openai/codex' and 'code-yeongyu/lazycodex' distinguishes it from generic skills. Not a 5: bare triggers like 'fix a bug' or 'open a PR for a bug' could also fire for an ordinary bug-fix request outside the LazyCodex/Codex scope, giving minor overlap risk with sibling contribution skills.

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
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.