跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

agentic-code-orchestrator

Unified codebase manipulation, AI deployment, data analysis, and academic delivery engine. Absorbs 6 coding protocols + data-analysis + academic-delivery + spec-driven-dev.

winstonkoh87 · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add winstonkoh87/Athena-Public --skill agentic-code-orchestrator

技能说明


name: agentic-code-orchestrator description: "Unified codebase manipulation, AI deployment, data analysis, and academic delivery engine. Absorbs 6 coding protocols + data-analysis + academic-delivery + spec-driven-dev." vibe: "Ship at 70%, iterate to 95%. Never build what you haven't specced." context_trigger: "refactor, bug, architecture, data dump, deploy, website, dashboard, code, build, CSV, Parquet, JSON, DuckDB, assignment, essay, capstone, SUSS, academic, Python, React, Next.js, Supabase, vibe code" auto-invoke: true model: default source: "Retroactively compiled from 1,900+ sessions (2025-2026) via skill-compiler" compiled_from: "protocols/coding/COD-*, skills/data-analysis, skills/academic-delivery, skills/spec-driven-dev" absorbs: "data-analysis, academic-delivery, spec-driven-dev, academic-humanizer, statistical-analysis" meta_patterns: [MP-2, MP-11] pinned: true

Agentic Code Orchestrator — Build × Analyze × Deliver

Compiled: 2026-05-11 (retroactive synthesis of all engineering/academic sessions) Problem Class: All code generation, data analysis, dashboard building, academic delivery, and technical project execution. Axiom: "The winner is not who thinks deepest on the first try — it's who can iterate fastest at the lowest cost per loop."

When to Use

Invoke whenever the user mentions:

  • Building/fixing a website, dashboard, or web app
  • Data analysis (CSV, JSON, Parquet, large datasets)
  • Academic assignments (essays, capstones, SUSS coursework)
  • Code refactoring or architecture decisions
  • Deploying to Supabase, Vercel, GitHub Pages
  • "Analyze this data" / "Build me a [thing]" / "Fix this bug"

Solution Architecture

Module 1: The RETO Engine Selector (COD-415 + MP-2)

Before writing ANY code, classify the project:

Is failure reversible?   → Efficient Engine (Vibe Engineering: ship at 70%)
Is failure irreversible? → Robust Engine (Nuclear Plant: test everything)
Project TypeEngineTest CoverageShip Threshold
Portfolio/websiteEfficientVisual QA only70%
Client dashboardEfficient→RobustVisual QA + data validation85%
Financial calculationsRobustUnit tests + manual verification99%
Academic submissionRobustPlagiarism check + format audit95%
Quick prototype/MVPEfficient"Does it work?"60%

Module 2: Spec-Driven Development (COD-107)

NEVER build without a spec. The spec is the contract.

Phase 1: Interrogation (The /brief)
  → What does the user ACTUALLY want?
  → What are the constraints?
  → What does "done" look like?

Phase 2: design.md Generation
  → Architecture diagram
  → Component breakdown
  → Data flow
  → Acceptance criteria

Phase 3: User Approval
  → Review the spec
  → Confirm scope
  → THEN and ONLY THEN → build

Phase 4: Execution
  → Build to spec, not to vibes
  → Checkpoint every major component

Module 3: The De-Sloppify Protocol (ECC Steal)

After generating code, ALWAYS run this quality pass:

  1. Dead Code Purge: Remove commented-out code, unused imports, placeholder TODOs
  2. Console.log Sweep: Remove all debug logging from production code
  3. Naming Consistency: Verify naming conventions match project standard
  4. Error Handling: Ensure every async operation has error handling
  5. Type Safety: If TypeScript, no any types unless explicitly justified

Module 4: Data Analysis Pipeline (DuckDB-Powered)

For large data dumps (CSV, Parquet, JSON):

Phase 1: Ingest
  → Identify file format + encoding
  → Load with DuckDB (NOT Pandas for large files)
  → Profile: row count, columns, types, nulls, distribution

Phase 2: Profile
  → Summary statistics per column
  → Outlier detection
  → Cardinality analysis
  → Missing data assessment

Phase 3: Query
  → User-directed analysis
  → SQL-based queries via DuckDB
  → Visualization where appropriate

Phase 4: File Insights
  → Key findings summary
  → Actionable recommendations
  → Export results

Rule: For files >100MB, ALWAYS use DuckDB. Pandas will crash.

Module 5: Academic Delivery Pipeline

For SUSS assignments, essays, capstones:

Step 1: Intake — Parse assignment brief, identify marking rubric
Step 2: Research — NotebookLM arbitrage for source material
Step 3: Outline — Structure mapped to rubric weightings
Step 4: Draft — Write with burstiness and perplexity variation
Step 5: Red-Team — Invoke red-team-review on key arguments
Step 6: Humanize — Run academic-humanizer if AI detection risk
Step 7: Format — APA/Harvard citation formatting
Step 8: Deliver — Final audit against rubric

The Bionic Academic Advantage (CS-467):

  • AI drafts at 80%, human polishes to 100%
  • Research Arbitrage: NotebookLM handles volume, Athena handles synthesis
  • SPSS/R/Python for statistical analysis (statistical-analysis skill)

Module 6: Dashboard/Website Architecture

For financial/trading dashboards:

PrincipleRule
Decimal Standard4 decimal places for all statistical outputs (GTO compliance)
Render StabilityExtract primitive values for useEffect deps, never use object refs
Visual HierarchyStatus indicators (green/amber/red) for institutional readability
ResponsiveMobile-first, then desktop adaptation
PerformanceLazy load heavy components, debounce real-time updates

For portfolio/marketing websites (CS-437 UI/UX Pro Max):

PrincipleRule
Above-the-foldHero → problem statement → CTA in first viewport
Social proofTestimonials, logos, case study links
Speed<3s load time or you lose 50% of visitors
SEOMeta tags, semantic HTML, structured data
ConversionOne clear CTA per page section

Output Template

ORCHESTRATOR REPORT
───────────────────
Project:        [Description]
Engine:         [Efficient / Robust —
阅读完整来源 ↗