菜单
Trigger: enforce norms, learn norms, validate documentation placement, check adaptive rules, run norm enforcer, update learned norms. Autonomous norm enforcement and learning system with 5 self-healing layers.
"Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy."
"12-agent academic paper writing pipeline. 10 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見."
"Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow."
Adaptive Mode Mejorado - Orquestacin inteligente con DAG dinmico, feedback loops automticos y rollback inteligente. Coordina mltiples agentes con dependencias reales, permite ciclos de retroalimentacin (QA DEV QA) y ejecuta rollback automtico ante fallos crticos.
Vercel AI SDK 5 patterns: streaming, AI objects, tools, messages. Trigger: "AI SDK", "AI SDK 5", "streamText", "generateText", "AI provider".
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
| name | adaptive-orchestrator |
| description | Trigger: enforce norms, learn norms, validate documentation placement, check adaptive rules, run norm enforcer, update learned norms. Autonomous norm enforcement and learning system with 5 self-healing layers. |
| metadata | {"source":"GV-native"} |
Load on session start/close or when user triggers: "run autonomous stack", "backup now", "check drift", "run tests autonomous", "restore from backup". Auto-triggers from session lifecycle events.
scripts/adaptive/*.ps1 scripts| Event | System Run | Action |
|---|---|---|
| Session start | Backup Orchestrator | Restore if needed |
| Session start | Norm Enforcer | Validate docs, create dirs |
| Session start/close | Norm Learner | Query Engram, promote norms |
| Session close | Doc-Drift Detector | Compare timestamps, delegate |
| Session start/close | Testing Orchestrator | Detect project, run tests, auto-repair |
| Manual trigger | All 5 systems | Full autonomous stack |
auto-backup-orchestrator.ps1 -Action restore (start) or
-Action backup (close)auto-norm-enforcer.ps1 -Trigger <event> -AutoFix — creates missing dirs,
applies standardsauto-norm-learner.ps1 -Trigger <event> — extracts patterns from Engram,
promotes to rules/custom/auto-doc-drift-detector.ps1 -Trigger <event> — compares code vs doc
timestamps, auto-delegates fixesauto-testing-final.ps1 -Trigger <event> — detects project type
(Node/Go/Python), runs tests, auto-repairsReturn session state (Ready / Closed). Log results for Judgment Day review. Store encrypted backup
to .backups/. Report any escalation cases (3 retries exhausted).
scripts/adaptive/references/appendix.md