CtrlK
BlogDocsLog inGet started
Tessl Logo

lcx-doctor

Diagnose LazyCodex and Codex CLI installation health against the latest sources. Use whenever the user asks for a doctor or health check, says LazyCodex, lazycodex-ai, omo-codex, or Codex behaves oddly after an install, update, or config change, suspects a stale, drifted, or broken setup, or wants the local install audited and compared with the latest LazyCodex and Codex code.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

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.

A highly actionable, well-sequenced diagnostic skill with executable code, strong validation checkpoints, and a concrete report template. The main gaps are conciseness (long inline body) and progressive disclosure (no reference files for a complex skill).

Suggestions

Extract the bash source-sync block into a script under scripts/ (e.g. scripts/sync_sources.sh) and invoke it from the body, shrinking the inline payload while keeping the workflow executable.

Move the Doctor Report Template into a references/ file and link to it, so SKILL.md stays a lean overview of the workflow.

Tighten the repeated caveats in the Stop Conditions and step 3 lists into a single consolidated checklist to reduce token weight.

DimensionReasoningScore

Conciseness

The body is dense, high-signal, and free of basic-concept padding, but it is long (~120 lines) with a sizable bash sync block and repeated caveats that could be tightened without losing clarity, so it sits at the 'mostly efficient' level rather than fully lean.

2 / 3

Actionability

It provides fully executable, copy-paste-ready bash (the sync_latest_source functions) plus specific commands throughout (gh repo clone, find .../plugin.json, codex --version, gh release view, gh issue list) and a concrete report template.

3 / 3

Workflow Clarity

The 8-step Required Workflow is clearly sequenced with explicit validation checkpoints (validate cached checkouts before reuse, verify manifest-declared payload, re-sync on every run) and feedback loops (recover_corrupt_source_checkout, re-validate), plus Stop Conditions for risky decisions.

3 / 3

Progressive Disclosure

Content is well-organized into clear sections (Required Workflow, Doctor Report Template, Follow-up Routing, Stop Conditions) with only one-level-deep external skill references, but the entire complex skill is inline with a large bash block and report template that, for a skill this size, could be split into reference files.

2 / 3

Total

10

/

12

Passed

Description

90%

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 with explicit what/when structure, rich natural trigger terms, and a clearly distinct niche. The only weakness is that the stated actions lean abstract rather than enumerating concrete operations.

Suggestions

Replace abstract verbs like "Diagnose ... health" and "audited" with more concrete operations, e.g. "check installed vs latest versions, verify config.toml and plugin wiring, probe the runtime, and report PASS/WARN/FAIL with evidence."

Lead with the most specific concrete actions first so the capability is unambiguous at a glance.

DimensionReasoningScore

Specificity

The description names the domain and several actions ("Diagnose LazyCodex and Codex CLI installation health", "audited and compared with the latest LazyCodex and Codex code"), but the actions are somewhat abstract ("health", "audit") rather than the multiple concrete, distinct operations the top anchor calls for.

2 / 3

Completeness

It explicitly answers what ("Diagnose LazyCodex and Codex CLI installation health against the latest sources") and when via an explicit "Use whenever..." trigger clause, matching the top anchor.

3 / 3

Trigger Term Quality

It covers a broad set of natural terms users would actually say: "doctor or health check", "LazyCodex", "lazycodex-ai", "omo-codex", and "Codex behaves oddly after an install, update, or config change".

3 / 3

Distinctiveness Conflict Risk

The LazyCodex/Codex install-doctor niche is narrow with distinctive triggers, making it unlikely to fire for the wrong skill.

3 / 3

Total

11

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

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.