一键导入
uni-store-lesson
Store a lesson learned from a failure, gate rejection, or unexpected issue. Use after bugfixes and gate failures to prevent recurrence.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Store a lesson learned from a failure, gate rejection, or unexpected issue. Use after bugfixes and gate failures to prevent recurrence.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Version bump, changelog generation, tag, and push to trigger the release pipeline.
Manage a goal's capability map in Unimatrix — the behaviorally-proven units that must exist for a goal to be delivered. Decompose goals into capabilities, track delivery status, and report what's left. Status advances to proven ONLY on attached behavioral evidence.
Unimatrix Zero — vision guide mode. Strategic advisor for product evolution, feature ordering, vision alignment, security posture, and codebase health. Conversational. Does not modify application code or run delivery protocols.
Post-merge retrospective — extracts patterns, procedures, and lessons from shipped features into Unimatrix. Use after a feature PR is merged.
Store an architectural decision record in Unimatrix. ADRs live in Unimatrix only — no ADR files. Use after each design decision.
Ad-hoc independent product-lens review via uni-zero-reviewer. Use for re-reviews after rework or reviews outside protocol runs. Advisory only — human makes the call.
| name | uni-store-lesson |
| description | Store a lesson learned from a failure, gate rejection, or unexpected issue. Use after bugfixes and gate failures to prevent recurrence. |
Stores a lesson learned in Unimatrix. Lessons capture what went wrong, why, and the takeaway. They surface in future briefings and searches to prevent the same failure from recurring.
Use after: gate failures, bug diagnoses, unexpected issues, rework cycles.
mcp__unimatrix__context_search({
"query": "{what went wrong}",
"category": "lesson-learned",
"k": 3
})
If a matching lesson already exists, go to Step 2b (supersede) instead of creating a duplicate.
mcp__unimatrix__context_store({
"title": "{concise description of what went wrong}",
"content": "{structured lesson content}",
"topic": "{feature-id or crate}",
"category": "lesson-learned",
"tags": ["{domain}", "{failure-type}"],
"agent_id": "{your role name, e.g. uni-architect}"
})
mcp__unimatrix__context_correct({
"original_id": 1234, // integer — never quote it
"content": "{updated lesson with new evidence or broader scope}",
"reason": "Updated: {what new evidence or context was added}"
})
This deprecates the old lesson and creates a corrected version with a supersession chain. Future searches return the latest version.
If a lesson is simply wrong or no longer applies (e.g., the underlying code was redesigned):
mcp__unimatrix__context_deprecate({"id": 1234, "reason": "{why it no longer applies}"}) // id is an integer — never quote it
Structure as: What happened -> Root cause -> Takeaway (200-500 chars):
Gate 3b rejected: confidence calculation used f32 intermediate values
despite f64 pipeline decision (ADR-003). Root cause: rust-dev didn't
read ADR before implementing. Takeaway: MANDATORY ADR read step in
rust-dev pseudocode consumption is not optional — validator should
check ADR compliance explicitly.
NOT a full incident report. NOT a narrative. Just the facts that prevent recurrence.
| Tag type | Examples |
|---|---|
| Failure type | gate-failure, bug, rework, regression, scope-fail |
| Gate | gate-3a, gate-3b, gate-3c |
| Domain | confidence, storage, mcp, testing |
| Severity | minor, major, critical |
| Agent | When |
|---|---|
| uni-bug-investigator | After diagnosing root cause — store the generalizable pattern |
| uni-validator | After gate failure — store what the gate caught and why |
| Coordinator | After rework cycle — store what caused the rework |
| Retrospective agents | After analyzing session data — store systemic issues |
Generalizable — applies beyond this one incident. "Off-by-one in loop" is not a lesson. "Boundary conditions at table scan limits not covered by unit tests" is.
Actionable — the takeaway prevents recurrence. "Be more careful" is not actionable. "Add boundary condition tests for every table scan method" is.
Concise — 200-500 chars. If it needs more, it's probably a procedure or a pattern, not a lesson.