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.

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%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with a well-sequenced, validation-rich workflow and a real referenced script. Its weakness is conciseness and progressive disclosure: much of the bash and both delivery templates are inline, where moving templates/workflow details into reference files would keep SKILL.md a leaner overview.

Suggestions

Move the 'Verified-Fix Issue Template' and 'PR Body Template' sections into reference files (e.g. references/issue-template.md, references/pr-body-template.md) and link to them from the body, so SKILL.md stays a lean overview.

Extract the long 'sync_latest_source' clone/recovery bash block into a scripts/ helper or a references/ file, keeping only the invocation and the validation contract inline.

Trim repeated worktree/clone patterns across steps 3-4 and 10-12 into a single documented helper to reduce token weight without losing actionability.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence and is mostly efficient, but it is lengthy (multi-page inline bash with two long templates) and could be tightened or split; some blocks repeat patterns already established. Not a 3 because verbosity is present; not a 1 because it does not explain basic concepts Claude knows.

2 / 3

Actionability

Provides fully executable bash snippets (clone/worktree/branch/commit), a real referenced script (scripts/create-pr-body.mjs) with its expected JSON input shape, and concrete issue/PR templates. Guidance is copy-paste ready rather than abstract.

3 / 3

Workflow Clarity

A clearly sequenced 13-step workflow with explicit validation checkpoints: corrupt-checkout recovery via valid_source_checkout, a failing-before/passing-after regression test, 'git status --short' before commit, and a Stop Conditions section. Error-recovery feedback loops are present for a destructive/batch context.

3 / 3

Progressive Disclosure

There is a real one-level bundle file (scripts/create-pr-body.mjs) referenced from the body, and references/ and assets/ are empty, but large sections (the Verified-Fix Issue Template and PR Body Template, plus the full clone workflow) live inline in SKILL.md rather than being split into reference files. Structure exists but content that should be separate is inline.

2 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, complete, and distinct: it names the concrete deliverables, the routing rules, and a clear set of natural 'Use when' triggers. It avoids fluff and stays in third person throughout.

DimensionReasoningScore

Specificity

Lists concrete actions: 'Contribute a verified bug fix', 'Opens a fork PR only for upstream openai/codex', and 'verified-fix issue on code-yeongyu/lazycodex (never a PR)'. It names the deliverable types and routing explicitly rather than vague abstraction.

3 / 3

Completeness

Explicitly answers 'what' (verified bug fix delivered as fork PR or verified-fix issue) and 'when' via the 'Use when the user asks to...' clause, satisfying both halves with explicit triggers.

3 / 3

Trigger Term Quality

Covers natural phrasings a user would say — 'fix a bug', 'contribute a bug fix', 'open a PR for a bug', and 'debug and PR a LazyCodex/Codex defect' — giving good coverage of how the need is actually voiced.

3 / 3

Distinctiveness Conflict Risk

The niche is clearly bounded (bug-fix contribution with explicit PR-vs-issue routing by repo) and unlikely to trigger for unrelated skills; the trigger terms are specific to contributing/debugging a defect.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
code-yeongyu/lazycodex
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.