AGENT SKILL

r-language-server-toolkit

Scaffold, configure, and inspect R language server protocol runtimes, C-level graphics devices (jgd), and session watchers for R execution environments. Do not use for generic web scraping or Python-only analytics.

License 许可
MIT
最近更新
2026-11-15
Stars
★ 0
Forks
0

01 前言 Front Matter

name
r-language-server-toolkit
description
Scaffold, configure, and inspect R language server protocol runtimes, C-level graphics devices (jgd), and session watchers for R execution environments. Do not use for generic web scraping or Python-only analytics.

02 资源文件 3

03 SKILL.md 正文

R Language Server Toolkit: Ecosystem Architecture & Integration

The r-language-server-toolkit skill provides structured domain capabilities for orchestrating R development tooling, integrating the Microsoft Language Server Protocol (LSP 3.17) via languageserver, real-time zero-dependency plot streaming via the C-level jgd graphics engine, and non-invasive R user-space session introspection from vscode-R.

See CARD.md for the companion summary card, stage progression table, and invariants checklist. Consult config.default.yaml for baseline operational budgets and timeout thresholds.


The Three Foundational Pillars

1. LSP 3.17 Protocol Compliance & Asynchronous Diagnostics

Orchestrating bidirectional JSON-RPC communication over standard I/O and TCP transports. Employs version-gated document caching (update_document_index) and debounced background lint passes (diagnostics_generation) to evaluate syntax trees and lintr rules without causing editor keystroke latency.

2. Headless Zero-Dependency Plot Streaming

Intercepting R C-level GEdevice primitives (lines, polylines, polygons, circles, rasters, and text) through function table callbacks in device.c. Converts drawing commands directly into structured JSON streams pushed across OS-native named pipes or WebSockets to HTML5 Canvas / SVG frontends without headful GUI windowing locks.

3. Non-Invasive Session Reflection

Observing active R runtime state (loaded packages, workspace symbols, active devices, working directories) through user-space task callbacks (.vsc.attach). Encapsulates observation logic within an isolated environment namespace (.vsc) to prevent symbol contamination of the user's .GlobalEnv.


Operational Workflow

[R Process / Console]
         │ (addTaskCallback)
         ▼
[.vsc.attach() Reflection] ──► [Atomic JSON Queue] ──► [Session Inspection API]
         │
         ▼ (GEdevice C hooks)
[jgd Graphics Engine] ───────► [Named Pipe / TCP] ───► [Canvas / SVG Webview]
         │
         ▼ (JSON-RPC over stdio)
[languageserver Engine] ────► [LSP 3.17 Client] ─────► [Diagnostics & Completions]
  1. Session Inspection:
    • Query runtime working directory, loaded namespaces, and exported workspace symbols.
    • Verify environment cleanliness to ensure user namespaces remain unpolluted.
  2. Diagnostics Normalization:
    • Parse LSP diagnostic payloads and map R 1-indexed line/column positions into 0-indexed UTF-16 code units.
    • Classify diagnostic severity (Error = 1, Warning = 2, Information = 3, Hint = 4).
  3. Plot Event Streaming:
    • Capture plot resize, redraw, and display-list packets from jgd.
    • Forward serialized graphics events to frontend consumers without blocking the R compute thread.

Anti-Patterns

  • Synchronous Keystroke Linting — Triggering full AST parsing and lintr execution synchronously on every edit event rather than debouncing.
  • Disk Polling for Graphics Updates — Watching temporary disk directories for static PNG files instead of streaming primitives over named pipes.
  • GlobalEnv Mutation for State Tracking — Injecting helper variables directly into the user's .GlobalEnv rather than isolated environments.
  • Unchecked Request Superseding — Failing to cancel active formatting or completion requests when a new document edit arrives.
  • Monolithic LSP-Bound Syntax — Coupling text syntax highlighting to language server initialization, causing unstyled text during server cold-starts.

04 同仓库更多 Skills

SpectreDeath
SpectreDeath/Brain-Harness

ui-behavior-primitive-architect

Architect, audit, and verify zero-dependency headless UI behavior primitives, WebMCP agent bridges, WAI-ARIA/SSR/RTL tri-modal checks, and framework expert routing. Do not use for static CSS theme styling or backend database migrations.

★ 0
SpectreDeath
SpectreDeath/Brain-Harness

trustgraph-ontology-governor

Govern knowledge graphs, SHACL-AF triple policies, OntologyRAG subclass validation, PROV-O dual named graphs, and Laya entropy decision scoring. Do not use for relational SQL queries or generic web scraping.

★ 0
SpectreDeath
SpectreDeath/Brain-Harness

shim-harness-governor

Govern universal CLI agent loops, 4-tier tool permissions, ancestor-symlink workspace sandboxes, deterministic-first command routing, collision-safe MCP namespacing, and layered skill loading. Do not use for static UI styling or external SQL analytics.

★ 0
SpectreDeath
SpectreDeath/Brain-Harness

graphiti-zep-memory-governor

Govern bi-temporal knowledge graphs with Graphiti future-edge clamping, MinHash/LSH entity dedup, RRF/MMR reranking, and Zep typed ontologies. Do not use for static SQL joins or generic web crawling.

★ 0
SpectreDeath
SpectreDeath/Brain-Harness

agora-mcp-workbench-architect

Architect, audit, and orchestrate Agora Workbench MCP servers, loopback sidecars, unified state graphs, gateway/dispatcher connectors, and policy-enforced data lakes. Do not use for static frontend CSS styling or non-MCP desktop GUI automation.

★ 0
SpectreDeath
SpectreDeath/Brain-Harness

skill-eval-assurance-runner

Evaluate and assure agent skills using small-N Wilson confidence intervals, unbiased pass^k reliability, deterministic trajectory graders, preflight boundary honesty, and sealed digest verification. Do not use for subjective prose review or unconstrained production deployment.

★ 0