메뉴
Extract learned patterns from session - invoked automatically by finishing-a-development-branch or manually anytime
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
The Evaluate-Loop coordinator for soe. Runs the BRAINSTORM → PLAN → EVALUATE_PLAN → EXECUTE → EVALUATE_EXEC → (FIX↺ | COMPLETE) state machine for a track: dispatches leaf agents, dispatches workers into isolated worktrees and applies their validated returns serially, and is the SOLE writer of .soe/tracks/{id}/state.json. Resumes crash-safely from committed state and bounds its fix/plan loops. Use when: 'run the loop', 'orchestrate', 'run the track', 'evaluate-loop', 'drive the track to completion'.
Session-model-led multi-model tiering. Use in ANY conversation (ambient) or in the pipeline to decide which model tier does which slice of work, and to delegate to the right model-pinned agent (strategist/deep-reasoner/fast-worker). The session model you selected IS the orchestrator; it self-selects its topology from its own model identity.
Use when the orchestrator needs to delegate an implementation task to an isolated worker — dispatches each worker as a Task-tool subagent in its own git worktree, awaits its return as the completion signal, and applies results serially as the sole state.json writer behind a validated context firewall
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Use at run start to discover what reviewers/analyzers/generators any installed plugin provides and route work by ROLE. Builds a role→provider map via lib/capability-scan.js so the loop prefers the best-matching installed specialist (a Go reviewer, a Flutter reviewer, AgentShield, ...) and falls back to soe-core's generic (soe:code-reviewer, soe:security-reviewer, soe:architect, ...) when none is installed. soe-core is self-sufficient and NEVER hard-depends on packs.
SOC 직업 분류 기준
| name | extract-patterns |
| description | Extract learned patterns from session - invoked automatically by finishing-a-development-branch or manually anytime |
Wraps ECC's continuous-learning-v2 system to extract and save useful patterns from development sessions.
Auto-invoked by: finishing-a-development-branch skill Can be invoked: Manually anytime to save learning Purpose: Build institutional knowledge over time
Announce at start: "I'm using the extract-patterns skill to learn from this session."
Use /soe:learn command to extract patterns:
/soe:learn
This analyzes the current session for:
The learning system will show patterns with confidence scores.
Review criteria:
Patterns are automatically saved to the instinct system.
View saved patterns:
/soe:instinct-status
For mature patterns (high confidence, multiple uses):
/soe:evolve
This clusters related patterns into reusable skills.
Auto-Invoked:
finishing-a-development-branch:
1. Verify tests pass
2. Sync documentation
3. Extract patterns (THIS SKILL) ← Auto-invoked
4. Generate changelist
5. Present options
Manual Invocation:
Any time during development:
- "Can you extract patterns from what we just did?"
- Skill invoked
- Patterns saved for future
To disable auto-invocation in finishing workflow:
See: docs/integration/OPT-OUT.md
Export patterns to file:
/soe:instinct-export
Import patterns from file:
/soe:instinct-import
Useful for:
| Command | Purpose |
|---|---|
/soe:learn | Extract patterns from session |
/soe:instinct-status | View saved patterns |
/soe:instinct-export | Export to file |
/soe:instinct-import | Import from file |
/soe:evolve | Cluster patterns into skills |
Remember: This builds institutional knowledge. The more you use it, the smarter the system becomes.