lsp-index-engineer
Language Server Protocol specialist building unified code intelligence systems through LSP client orchestration and semantic indexing
37
22%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./specialized-lsp-index/skills/SKILL.mdQuality
Discovery
17%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description reads more like a job title or resume bullet point than a skill description. It relies on technical jargon without explaining concrete actions or providing trigger guidance for when Claude should select it. The absence of a 'Use when...' clause and natural user-facing keywords significantly weakens its utility for skill selection.
Suggestions
Add a 'Use when...' clause with natural trigger terms like 'language server', 'go to definition', 'find references', 'code navigation', 'autocomplete setup', or 'LSP configuration'.
Replace abstract phrases like 'unified code intelligence systems' and 'LSP client orchestration' with concrete actions such as 'configure language servers, enable go-to-definition, set up code completion, manage LSP server connections'.
Include file types or tool names users might mention, such as '.lsp', 'lspconfig', 'pyright', 'typescript-language-server', or specific editors/IDEs.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (LSP, code intelligence) and mentions some actions ('building unified code intelligence systems', 'LSP client orchestration', 'semantic indexing'), but these are more like abstract concepts than concrete user-facing actions. It doesn't list specific things like 'go-to-definition', 'find references', 'auto-complete', or 'diagnose errors'. | 2 / 3 |
Completeness | Provides a vague 'what' (building code intelligence systems through LSP) but completely lacks any 'when' clause or explicit trigger guidance. The absence of a 'Use when...' clause caps this at 2 per the rubric, and the weak 'what' further reduces it to 1. | 1 / 3 |
Trigger Term Quality | Uses highly technical jargon ('LSP client orchestration', 'semantic indexing', 'unified code intelligence systems') that users are unlikely to naturally say. Missing common terms like 'code navigation', 'go to definition', 'find references', 'autocomplete', 'language server', or 'code intelligence'. | 1 / 3 |
Distinctiveness Conflict Risk | The LSP focus gives it some distinctiveness from general coding skills, but 'code intelligence systems' is broad enough to overlap with skills related to code analysis, IDE features, or code search. The lack of specific triggers increases conflict risk. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a comprehensive persona/role-play prompt than an actionable skill document. It is extremely verbose, spending significant tokens on identity, personality, communication style, and aspirational metrics that don't help Claude execute tasks. While it contains some useful technical content (LSP lifecycle, graph schema, code examples), the signal-to-noise ratio is low and the lack of progressive disclosure makes it unwieldy.
Suggestions
Remove personality, identity, communication style, learning/memory, and success metrics sections entirely—these waste tokens without adding actionable guidance.
Split into SKILL.md (concise overview + quick start) with references to separate files for graph schema types, LSP orchestration patterns, and the navigation index format.
Add explicit validation checkpoints to the workflow, e.g., 'Verify LSP initialization succeeded by checking capabilities response' and 'Validate graph consistency after each phase before proceeding.'
Replace illustrative interface definitions with smaller, fully executable code snippets that can be directly used, or clearly mark them as schemas/templates.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Includes extensive personality/identity sections, communication style guidance, 'learning & memory' sections, and success metrics that Claude doesn't need. The TypeScript interface definitions and code examples, while detailed, are largely illustrative rather than actionable. Sections like '🧠 Your Identity & Memory' and '💭 Your Communication Style' are unnecessary padding. | 1 / 3 |
Actionability | Contains concrete TypeScript code examples and a bash setup section with specific commands, but much of the code is illustrative interface definitions and incomplete class implementations rather than fully executable, copy-paste-ready code. The GraphBuilder pipeline is pseudocode-level with unimplemented methods like `extractSymbols` and `resolveReferences`. | 2 / 3 |
Workflow Clarity | Steps 1-4 in the workflow section provide a reasonable sequence, but validation checkpoints are largely absent. For a system involving graph consistency, LSP lifecycle management, and real-time updates, there are no explicit verification steps or error recovery feedback loops. The 'Graph Consistency Requirements' section lists rules but doesn't integrate them into the workflow as validation gates. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. All content—architecture, code examples, protocol details, performance requirements, personality instructions—is crammed into a single document. Content like the full TypeScript interfaces, the JSONL format spec, and advanced capabilities could easily be split into referenced files. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- OpenRoster-ai/awesome-openroster
- Commit
09aef5d
- 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.