القائمة
Process user feedback on AI memories: agreement promotes status, disagreement deletes, refinement revises claims. Translates natural user reactions into DeepMemory governance operations.
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
| name | user-feedback-handler |
| description | Process user feedback on AI memories: agreement promotes status, disagreement deletes, refinement revises claims. Translates natural user reactions into DeepMemory governance operations. |
| metadata | {"version":"1.0.0","category":"cognitive-memory","tags":["feedback","user-correction","memory-governance","deepmemory"]} |
This skill translates user feedback signals (thumbs up, corrections, disagreements) into DeepMemory governance operations. It closes the loop between AI observations and human ground truth.
DeepMemory MCP Server must be running. The system should track which
memories were surfaced in the current conversation so feedback can be
mapped to specific memory_id values.
Analyze the user's message to determine feedback type:
| Signal | Type | Confidence Boost |
|---|---|---|
| "yes", "correct", "exactly", "good", 👍 | agree | +0.15 |
| "no", "wrong", "that's not right", 👎 | disagree | N/A (delete) |
| "actually...", "not exactly, it's...", correction | refine | reset to 0.70 |
| "remember that...", "keep in mind..." | reinforce | +0.20 |
| "forget that", "ignore that", "never mind" | forget | N/A (delete) |
Determine which memory the feedback refers to:
If ambiguous, ask the user to clarify which observation they're responding to.
For agree feedback:
deepmemory_promote(
memory_id="mu_xxx",
status="provisional_consensus"
)
If already at provisional_consensus, promote to canonical.
For disagree feedback:
deepmemory_delete(
memory_id="mu_xxx",
reason="user_disagreement"
)
For refine feedback:
deepmemory_revise(
memory_id="mu_xxx",
operational_claim="the corrected claim from user",
confidence=0.70
)
For reinforce feedback:
deepmemory_revise(
memory_id="mu_xxx",
confidence=0.95
)
deepmemory_promote(
memory_id="mu_xxx",
status="canonical"
)
For forget feedback:
deepmemory_delete(
memory_id="mu_xxx",
reason="user_requested_removal"
)
Confirm the action briefly:
| Action | Response Template |
|---|---|
| Promoted | "Got it, I've noted that as confirmed." |
| Deleted | "Understood, I've removed that observation." |
| Revised | "Updated — I'll remember the corrected version." |
| Reinforced | "Marked as a strong preference." |
Context: AI previously recalled "user prefers uv for packaging" User: "对，一直用 uv"
Action: deepmemory_promote(memory_id, "canonical") — user explicitly confirmed
Context: AI recalled "project uses PostgreSQL" User: "不是 PostgreSQL，我们用的 SQLite"
Action: deepmemory_revise(memory_id, operational_claim="项目使用SQLite而非PostgreSQL", confidence=0.90)
Context: AI recalled "user wants tests before implementation" User: "不需要这个规则了，现在我们直接写代码"
Action: deepmemory_delete(memory_id, reason="user_changed_workflow")
refine, keep the
agreed part, update the corrected partdisagreeRun a multi-agent debate around contested memories. Multiple agents argue for/against a memory claim, then vote to determine its final social status. This is the "game theory enhances collective memory" engine — consensus emerges through structured argumentation, not just majority counting.
Before generating an AI reply, recall relevant memories from DeepMemory and search related code from FlashMemory, then inject both as augmented context. This is the memory-enhanced RAG pipeline — combining symbolic recall with vector search for richer, history-aware responses.
Run a periodic memory evolution cycle: decay stale observations, deprecate low-confidence memories, and prune excess per object. Call every 10 turns or on a daily schedule to keep the memory store healthy and relevant.
Extract symbolic order from conversations: identify key concepts as Signs, anchor them to ObjectRefs, and record interpretant claims via DeepMemory MCP. This is the "semiotics deconstructs semantics" engine — it turns natural language into structured, contestable memory units instead of opaque vectors.
FlashMemory CLI for cross-language code analysis and semantic search. Use this skill when you need to understand project architecture, locate implementations, or index large codebases using natural language queries. Make sure to use this skill whenever the user asks about the codebase structure, finding code, or searching files.
Build and maintain semantic vector indexes for large codebases using FlashMemory. Use this skill whenever you need to index a new project, re-index after making code changes, perform incremental file updates, or switch between vector engine backends. Make sure to use this whenever you modify code or pull new changes so the semantic search index stays up-to-date.