القائمة
Zero Framework Cognition Principles
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use the local pr-watch CLI/daemon to watch GitHub pull request activity, wait for PR changes, and fetch normalized event deltas without manually managing webhook forwarding or event subscriptions.
One lifecycle for Lambda repos: choose a bd task, start work, land the PR, and watch GitHub via Dumbwaiter MCP until it merges.
Default Python stack for Lambda: uv + Astral tools, typed code, schemas, and Hypothesis.
How to use bd (beads) for issue tracking, ready work, status updates, and comments in this repo.
Provider-agnostic wait-for-change skill that uses the Dumbwaiter MCP server to wait on PR events (GitHub first) via wait.start/status/cancel/await, with progress notifications and durable state.
Default TypeScript stack for Lambda: pnpm workspaces + Turbo, strict TS, and sensible DX helpers.
| name | zfc |
| description | Zero Framework Cognition Principles |
Core Architecture Principle: This application is pure orchestration that delegates ALL reasoning to external AI. We build a “thin, safe, deterministic shell” around AI reasoning with strong guardrails and observability.
IO and Plumbing • Read/write files, list directories, parse JSON, serialize/deserialize • Persist to stores, watch events, index documents
Structural Safety Checks • Schema validation, required fields verification • Path traversal prevention, timeout enforcement, cancellation handling
Policy Enforcement • Budget caps, rate limits, confidence thresholds • “Don’t run without approval” gates
Mechanical Transforms • Parameter substitution (e.g., ${param} replacement) • Compilation • Formatting and rendering AI-provided data
State Management • Lifecycle tracking, progress monitoring • Mission journaling, escalation policy execution
Typed Error Handling • Use SDK-provided error classes (instanceof checks) • Avoid message parsing
Local Intelligence/Reasoning
Ranking/Scoring/Selection • Any algorithm that chooses among alternatives based on heuristics or weights
Plan/Composition/Scheduling • Decisions about dependencies, ordering, parallelization, retry policies
Semantic Analysis • Inferring complexity, scope, file dependencies • Determining “what should be done next”
Heuristic Classification • Keyword-based routing • Fallback decision trees • Domain-specific rules
Quality Judgment • Opinionated validation beyond structural safety • Recommendations like “test-first recommended”
The Correct Flow
Gather Raw Context (IO only) • User intent, project files, constraints, mission state
Call AI for Decisions • Classification, selection, composition • Ordering, validation, next steps
Validate Structure • Schema conformance • Safety checks • Policy enforcement
Execute Mechanically • Run AI’s decisions without modification
