lsp-maintain

Diagnose and align Kode LSP behavior with the reference CLI (plugin-based .lsp.json, stdio-only, no install menus). Use when LSP results are missing, LSP is disabled, or you need to configure plugin LSP servers without telling the user to run menu-style install commands.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 instruction-only skill with a clear sequenced workflow and verification step. The main gap is the absence of a concrete .lsp.json example and an explicit retry-on-verification-failure loop.

Suggestions

Add a minimal concrete .lsp.json record example under 'Notes for LSP server config authoring' so the guidance is copy-paste ready rather than abstract.

Add an explicit feedback loop in Step 4 (e.g. 'If servers are not resolved or the LSP call fails, return to Step 2/3 and re-check the config source') to strengthen verification.

Optionally include one example of a manifest lspServers inline record vs. relative file path to remove ambiguity in Step 2.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with no padding about what LSP or plugins are; every line (Non-negotiables, the 'LSP enabled' definition, Steps, Notes) earns its place; matches the top anchor.	5 / 5
Actionability	Provides concrete executable commands ('Run /lsp via SlashCommand', 'Use SlashCommand to manage plugins (/plugin ...)', 'Use Edit to update the plugin's .lsp.json') with minor gaps; not a 5 because there is no concrete example of a .lsp.json record or manifest lspServers entry, and not a 3 because the guidance is concrete rather than pseudocode.	4 / 5
Workflow Clarity	Clear 4-step sequence with an explicit Verify step (re-run /lsp, attempt an LSP tool call) as a checkpoint; not a 5 because there is no explicit feedback loop if verification fails, and not a 3 because the sequence and main checkpoint are clearly present.	4 / 5
Progressive Disclosure	A simple, under-50-line skill with no need for external references, organized into well-labeled sections (Non-negotiables, What 'LSP enabled' means, Steps 1-4, Notes); per the simple-skills note this matches the top anchor.	5 / 5
	Total	18 / 20 Passed

Description

87%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 that clearly states both what the skill does and when to use it, with concrete trigger phrases and a distinct niche. Minor opportunity to broaden trigger synonyms and add a couple more action verbs.

Dimension	Reasoning	Score
Specificity	Names several specific actions ('Diagnose and align', 'configure plugin LSP servers') with concrete mechanisms (plugin-based .lsp.json, stdio-only), which lists several specific actions with only minor coverage gaps; not a 3 because it goes beyond 1-2 actions, and not a 5 because coverage is not fully comprehensive.	4 / 5
Completeness	Explicitly answers both what ('Diagnose and align Kode LSP behavior with the reference CLI...') and when ('Use when LSP results are missing, LSP is disabled, or you need to configure plugin LSP servers...') with concrete trigger phrases; matches the top anchor exactly.	5 / 5
Trigger Term Quality	Includes natural user phrases ('LSP results are missing', 'LSP is disabled', 'configure plugin LSP servers') with good keyword coverage; not a 5 because some common synonyms (e.g. 'language server not working') are absent, and not a 3 because coverage is clearly better than 'some relevant keywords'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Kode LSP maintenance, plugin-based .lsp.json, stdio-only) with distinct triggers and minimal overlap with other skills; matches the top anchor.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: shareAI-lab/Kode-CLI
Path: packages/builtin-skills/skills/lsp-maintain/SKILL.md
Commit: c7f6fcc

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.