CtrlK
BlogDocsLog inGet started
Tessl Logo

lsp

Use when Codex needs language-server diagnostics, definitions, references, symbols, or rename safety checks in the current workspace.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 lean, well-structured tool-reference skill that is highly token-efficient and self-contained. It could improve actionability with concrete call examples and make its validation workflow explicit.

Suggestions

Add one or two example tool invocations with argument values (e.g., a diagnostics or goto_definition call) so usage is copy-paste ready rather than implied from the parameter list.

Frame the rename safety flow as an explicit sequence: validate with lsp.prepare_rename, then apply lsp.rename, re-running diagnostics afterward.

Make the post-edit verification loop explicit (edit → lsp.diagnostics with severity:"error" → fix → re-check) instead of leaving it as a scattered tip.

DimensionReasoningScore

Conciseness

Lean and efficient at ~35 lines: a tight tool list with one-line descriptions, a single config example, and two tactical tips, with no padding or explanation of concepts Claude already knows.

5 / 5

Actionability

Gives concrete tool names with required parameters and a copy-paste config block, but is reference-style — it lacks example invocations showing actual tool calls with argument values, leaving a minor gap.

4 / 5

Workflow Clarity

Encodes sequence and checkpoints as prose tips (status-first recovery, post-edit diagnostics verification, prepare_rename before rename), but these are scattered rather than an explicit numbered feedback loop, and the validate→apply loop for rename is hinted not framed.

4 / 5

Progressive Disclosure

Under 50 lines, self-contained with no bundle files, and organized into clear Tools and Config sections — meeting the simple-skill exception where well-organized sections alone earn a 5.

5 / 5

Total

18

/

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, specific description with concrete capabilities and an explicit trigger clause. Its main weakness is merged what/when phrasing and the absence of common synonyms/acronyms a user might actually say.

Suggestions

Lead with a concise what-statement before the trigger clause (e.g., "Provides language-server diagnostics, definitions, references, symbols, and rename support.") to separate what from when.

Add common synonyms/acronics users say — "LSP", "go to definition", "find usages/references" — to broaden trigger coverage.

Frame the when in terms of user utterances (e.g., "Use when the user asks to find references, go to a definition, check diagnostics, or rename a symbol").

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "diagnostics, definitions, references, symbols, or rename safety checks" — giving comprehensive coverage of LSP capabilities with no real gaps.

5 / 5

Completeness

Has an explicit "Use when..." trigger and answers "what" via the capability list, but the what and when are merged into one clause and the triggers are capability-named rather than user-utterance-named, so it stops short of the fully separated, explicit-trigger anchor.

4 / 5

Trigger Term Quality

Terms like diagnostics, definitions, references, symbols, and rename are natural developer language, but common synonyms/acronyms such as "LSP", "go to definition", and "find usages" are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (language-server operations in Codex) with distinct, specific triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.