create-rule
Create Cursor rules for persistent AI guidance. Use when the user wants to create a rule, add coding standards, set up project conventions, configure…
Use when starting a new project, onboarding to an existing product, or auditing an existing folder structure against the standard. Scaffolds the 16-document set, folder structure, project memory and doc-sync config.
$ npx -y skills add coco-research/coco --skill project-docs --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/project-docsContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when starting a new project, onboarding to an existing product, or auditing an existing folder structure against the standard. Scaffolds the 16-document set, folder structure, project memory and doc-sync config.
name: project-docs description: "Use when starting a new project, onboarding to an existing product, or auditing an existing folder structure against the standard. Scaffolds the 16-document set, folder structure, project memory and doc-sync config." domain: pm
Every project needs the same core set of interconnected documents. This skill scaffolds a complete documentation ecosystem from day one so that:
Every project should have these **16 document types** organized in **6 categories**. Not every project needs all 16 — the skill asks which ones apply and only scaffolds what's needed. Documents 11-16 are generated on demand via dedicated slash commands in the `pm-ops` skill category.
These are authoritative — all other documents derive from them.
| # | Document | File Pattern | Purpose | Update Trigger | |---|----------|-------------|---------|----------------| | 1 | **PRD / Requirements** | `PRD/` or `Requirements/` | What we're building and why | Decisions, research findings, stakeholder feedback | | 2 | **Project Memory** | `CLAUDE.local.md` | AI context — architecture, decisions, recent changes | Every session (auto-maintained) |
Raw inputs that feed the root documents. These are append-only — never edited after creation.
| # | Document | File Pattern | Purpose | Update Trigger | |---|----------|-------------|---------|----------------| | 3 | **Meeting Notes** | `Meeting-Notes/YYYY-MM-DD-Name.md` | Decisions, action items, context from calls | After every meeting | | 4 | **Research** | `Research/Topic-Name.md` | Deep dives, competitive analysis, technical research | As needed | | 5 | **Source Documents** | `Source-Documents/` | Contracts, emails, vendor docs, screenshots | When received |
Generated from root + source documents. These go stale and need syncing.
| # | Document | File Pattern | Purpose | Update Trigger | |---|----------|-------------|---------|----------------| | 6 | **Presentation / Deck** | `Presentations/Name-vN.html` | Stakeholder-facing summary | PRD changes, new meetings, new decisions | | 7 | **PRD Presentation** | `PRD/PRD-Presentation.html` | Slide version of PRD for reviews | PRD changes | | 8 | **Architecture Map** | `Architecture/` | System diagrams, data flows, integration maps | Design decisions, technical research | | 9 | **ARB Review** | `ARB/` | Architecture Review Board presentation (Coco Inc 11-slide format) | Architecture changes, pre-go-live |
Generate with: `/arb-review` — auto-populates from PRD + architecture + project registry data.
Living documents that track ongoing state.
| # | Document | File Pattern | Purpose | Update Trigger | |---|----------|-------------|---------|----------------| | 10 | **Verification / Audit** | `Verification/` | Data verification, gap analysis, compliance checks | Before milestones | | 11 | **Stakeholder Directory** | `Data/Stakeholder-Directory.xlsx` | Contact list with roles, groups, ownership | New people mentioned in meetings | | 12 | **Change Log** | `Change-Log.md` | Running log of product/platform changes (config, users, modules) | After every change | | 13 | **NFR Tracker** | `.nfr-status.json` | Cross-cutting readiness dashboard — tracks status of all document types | Continuous |
Generate with: `/change-log` (init or append) and `/nfr-tracker` (audit readiness).
Required for production systems. Generated on demand as go-live approaches.
| # | Document | File Pattern | Purpose | Update Trigger | |---|----------|-------------|---------|----------------| | 14 | **DR Plan** | `Operations/DR-Plan.md` | Disaster Recovery — RTO/RPO targets, failover, manual fallbacks | Pre-go-live, annually | | 15 | **IRP** | `Operations/IRP.md` | Incident Response Plan — severity matrix, escalation, SOX implications | Pre-go-live, annually | | 16 | **Recovery Plan** | `Operations/Recovery-Plan.md` | Step-by-step restoration runbooks per failure scenario | After DR + IRP created |
Generate with: `/dr-plan` → `/irp` → `/recovery-plan` (in dependency order).
Templates for stakeholder announcements. Generated on demand.
| Document | File Pattern | Purpose | Generate With | |----------|-------------|---------|---------------| | **Stakeholder Comms** | `Comms/Stakeholder-Comms.html` | Pre-filled templates: go-live, status, onboarding, incident, SteerCo | `/stakeholder-comms` |
Meeting Notes ──┬──→ PRD ──────────→ PRD Presentation
│ │
Research ───────┤ ├──→ Main Presentation
│ │
Source Docs ────┘ ├──→ Architecture Map
│
├──→ /arb-review (ARB presentation)
│
├──→ /dr-plan ────→ /recovery-plan
│
├──→ /irp ────────→ /recovery-plan
│
├──→ /change-log (append mode)
│
└──→ /stakeholder-comms
/nfr-tracker ──────→ Reads ACoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an engineering department: a routed advisory board, 226 skills, 386 commands, persistent state. Local. Open-core — MIT core; Super Intelligence is proprietary, own-use.
Repo: coco-research/coco
Create Cursor rules for persistent AI guidance. Use when the user wants to create a rule, add coding standards, set up project conventions, configure…
Guides users through creating effective Agent Skills for Cursor. Use when the user wants to create, write, or author a new skill, or asks about skill…
Create custom subagents for specialized AI tasks. Use when the user wants to create a new type of subagent, set up task-specific agents, configure code…
Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use…
Modify Cursor/VSCode user settings in settings.json. Use when the user wants to change editor settings, preferences, configuration, themes, font size, tab…
Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning. Use when setting up agent training, instrumenting agents…