القائمة
Socratic interview skill that clarifies requirements before any major build task and produces an immutable seed spec with acceptance criteria and ontology.
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
Local-only multi-agent orchestrator with token optimization, 6-signal composite routing, and persistent memory. Routes all tasks through local executor bridges (Claude Code, Hermes, Gemini, Codex) with DAG dependencies, auto-episode creation, and cognitive profiles.
Zouroboros self-healing watchdog that monitors scheduled agent models and automatically switches failing agents to backup models, restoring originals when they recover.
Hybrid SQLite + Vector persona memory system for Zo Computer. Episodic memory with temporal queries, graph-boosted search, BFS path finding, knowledge gap analysis, auto-capture pipeline, and per-workload model routing. Default generation workloads use OpenAI `gpt-4o-mini`; embeddings use OpenAI `text-embedding-3-small`.
Security governance gate for AI agent skills, backed by NVIDIA SkillSpector. Statically scans a skill (local path, directory, zip, or Git URL) for 65 vulnerability patterns across 16 categories (prompt injection, data exfiltration, privilege escalation, supply chain, excessive agency, tool/MCP misuse, dangerous code via AST, YARA signatures) and returns a 0-100 risk score with a SAFE / REVIEW / DO_NOT_INSTALL recommendation. Use BEFORE adopting any third-party skill, and for the periodic baseline scan of the Skills/ directory.
Detector for model classifier SOFT-blocks — refusals, filtered-to-empty, truncated-with-disclaimer, content-policy flags — that masquerade as successful empty output to existing infrastructure (agent-model-healer only catches HARD failures: HTTP 4xx/5xx, timeouts, genuine empties). Classifies an output as soft_block / genuine_empty / ok using a per-provider signal catalog, then routes a per-domain fallback (security → broader-tolerance model, bio/chem → human review, distillation → refuse-by-design, never routed around). Every block + fallback is appended to an audit ledger. A quarterly system-card-diff agent flags expanded classifier scope so the catalog stays current.
Rendered-output verification station for the swarm post-flight eval. After a maker subagent produces a visual deliverable (UI/route/site), the station captures a full-page screenshot via agent-browser, then an independent verifier model (not equal to author, per aiewf P0-2) reads the screenshot against seed acceptance criteria + project DESIGN.md tokens + prior screenshots. Match marks the task complete; mismatch emits a structured visual diff for the maker's next iteration. The verifier is the exit condition, not the maker. Recurring visual failure modes graduate to instincts.yaml via the extract-patterns gate (ZOU-452).
| name | spec-first-interview |
| description | Socratic interview skill that clarifies requirements before any major build task and produces an immutable seed spec with acceptance criteria and ontology. |
| compatibility | Created for Zo Computer |
| metadata | {"author":"marlandoj.zo.computer","origin":"https://github.com/Q00/ouroboros"} |
Before telling AI what to build, define what should be built.
# Run the interview
bun Skills/spec-first-interview/scripts/interview.ts --topic "Build a webhook retry system"
# Generate a seed spec from interview notes
bun Skills/spec-first-interview/scripts/interview.ts seed --from /path/to/interview-notes.md
# Score ambiguity of a request
bun Skills/spec-first-interview/scripts/interview.ts score --request "Make the site faster"
Adopt the Socratic Interviewer role (see references/socratic-interviewer.md).
ambiguity = 1 - (goal × 0.40 + constraints × 0.30 + success × 0.30)
Rules during interview:
Once ambiguity ≤ 0.2, adopt the Seed Architect role (see references/seed-architect.md).
Extract from the interview:
| Component | Description |
|---|---|
| Goal | Clear, specific primary objective |
| Constraints | Hard limitations (pipe-separated) |
| Acceptance Criteria | Measurable success conditions (pipe-separated) |
| Ontology | Domain model — name, description, fields (name:type:description) |
| Evaluation Principles | Quality dimensions with weights (name:description:weight) |
| Exit Conditions | When to stop (name:description:criteria) |
Save the seed to the workspace as a YAML file:
# seed-{id}.yaml
id: seed-{uuid}
created: {iso_date}
goal: "Build a CLI task management tool in Python"
constraints:
- "Python 3.14+"
- "No external database"
- "Must work offline"
acceptance_criteria:
- "Tasks can be created with title and priority"
- "Tasks can be listed, filtered by status"
- "Tasks persist to local JSON file"
ontology:
name: task
description: "A unit of work to be tracked"
fields:
- name: id
type: string
description: "Unique identifier"
- name: title
type: string
description: "Human-readable task name"
- name: status
type: string
description: "Current state: pending | done"
evaluation_principles:
- name: correctness
description: "Does it do what was asked?"
weight: 0.4
- name: simplicity
description: "Is the implementation minimal?"
weight: 0.3
- name: usability
description: "Is the CLI intuitive?"
weight: 0.3
exit_conditions:
- name: all_ac_met
description: "All acceptance criteria satisfied"
criteria: "AC compliance = 100%"
For complex or high-stakes work, run the Ontologist lens (see references/ontologist.md) on the seed:
three-stage-eval skill)