菜单
Show everything Claudia knows with provenance tracing and entity counts. Triggers on "what do you know?", "show memories", "memory audit", "what do you remember about". See also: `memory-health` for system-level stats and data quality; `diagnose` for connectivity troubleshooting.
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
Iteratively improve a local artifact (draft, document, page) by running a hill-climbing loop. The user names the artifact, the evaluator, and the budget. Claudia edits the artifact, scores it, keeps it if better or reverts if worse, repeats. Use when user says "iterate on this", "loop on this until it's better", "run experiments on this draft", "auto-research this", "make this better and don't stop until it's good". Workspace-scoped, never touches live files, no external actions during the loop.
Propose a personalized team of specialized agents based on the user's profile, goals, and how they actually work. Runs the proposal through an independent Checker, gates on the user's approval, and applies with rollback. Use when the user says "build my team", "set up my agents", "what agents should I have", "design my team", "/build-team", or asks Claudia to tailor her team to their work. See also: `hire-agent` for proactive single-agent suggestions; `structure-generator` for folder scaffolding; `capability-suggester` for command-level additions.
End-of-session reflection generating persistent learnings about user preferences, communication patterns, and cross-session insights. Activates when wrapping up a session, or when user says "let's wrap up", "end the session", "time to reflect", or "meditate". Also extracts judgment rules from decisions made during the session. See also: `weekly-review` and `growth-check` for time-based reflection cadences.
Launch the Brain Monitor TUI, a real-time terminal dashboard for watching Claudia's memory system. Triggers on "brain monitor", "show dashboard", "memory dashboard", "terminal brain". See also: `brain` for a 3D graph view in the browser.
Launch the Brain Visualizer, a real-time 3D view of memory and relationships. Triggers on "show your brain", "visualize memory", "open the brain", "memory graph". See also: `brain-monitor` for a terminal dashboard alternative.
Process meeting notes or transcript to extract decisions, commitments, and insights. Use when user shares transcript or says "capture this meeting", "here are my notes from the call". See also: `meeting-prep` for pre-call briefings; `follow-up-draft` for post-meeting emails.
| name | memory-audit |
| description | Show everything Claudia knows with provenance tracing and entity counts. Triggers on "what do you know?", "show memories", "memory audit", "what do you remember about". See also: `memory-health` for system-level stats and data quality; `diagnose` for connectivity troubleshooting. |
Show what Claudia knows. Verify claims trace to sources. Surface gaps.
/memory-audit -- Full system audit/memory-audit [entity name] -- Audit everything about a specific person, project, or entityWhen run without arguments, produce a system-level overview of everything in memory.
Query the memory system for aggregate counts:
claudia memory entities search --query "*" --project-dir "$PWD"
claudia memory recall "*" --compact --limit 1 --project-dir "$PWD"
claudia memory document search --project-dir "$PWD"
Parse the JSON output from each command to get counts.
Display:
## Memory Audit - [Date]
| Category | Count |
|----------------|-------|
| Entities | N |
| Memories | N |
| Commitments | N |
| Documents | N |
| Relationships | N |
claudia memory entities search --types "person" --limit 10 --project-dir "$PWD"
For each person:
claudia memory about "[person name]" --project-dir "$PWD"
Display as a table:
### People
| Name | Memories | Last Mentioned | Key Fact |
|------|----------|----------------|----------|
| ... | ... | ... | ... |
Same pattern with types=["project"]:
claudia memory entities search --types "project" --limit 10 --project-dir "$PWD"
claudia memory session context --project-dir "$PWD"
Pick the 3 most recent high-importance memories and trace them:
claudia memory recall "*" --compact --limit 3 --project-dir "$PWD"
For each result, run:
claudia memory provenance trace --memory-id "[id]" --project-dir "$PWD"
Display:
### Provenance Check (3 recent memories)
**Memory:** "[content snippet]"
- Source: [episode/document/user_input]
- Document: [filename] (if linked)
- Entities: [linked entities]
- Verified: [yes/no/pending]
When run with an entity name (e.g., /memory-audit Sarah Chen):
claudia memory about "[entity name]" --project-dir "$PWD"
Display:
## Audit: [Entity Name]
**Type:** person/project/organization
**Description:** [from entity record]
**Importance:** [score]
**First seen:** [created_at]
**Last mentioned:** [updated_at]
From the claudia memory about JSON response, group memories:
### Facts (N)
- [content] (importance: X, created: date)
### Commitments (N)
- [content] (importance: X, created: date)
### Observations (N)
- [content] (importance: X, created: date)
### Relationships (N)
- [relationship_type] with [other_entity] (strength: X)
claudia memory document search --entity "[entity name]" --project-dir "$PWD"
Display:
### Documents (N)
- [filename] ([source_type], [date]) - [summary snippet]
For each commitment or high-importance memory (importance > 0.7):
claudia memory provenance trace --memory-id "[memory ID]" --project-dir "$PWD"
Display:
### Provenance
**"[memory content]"** (commitment, importance: 0.9)
|- Source: session_summary (episode 42)
|- Episode: "Discussed Q2 goals with Sarah..."
|- Document: meeting-sarah-q2.md (transcript)
|- Verified: yes (2026-01-15)