Menu
Deep analysis and debugging with Opus. Systematically investigate problems, identify root causes, and recommend fixes with evidence.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Mark a logical phase completion in haivemind. More formal than /snapshot — used at step/phase boundaries in multi-phase work. Creates a named, resumable point that /continue can restore from. Triggered by /checkpoint, "checkpoint this", "mark this as a checkpoint", or at phase boundaries in long-running tasks.
Run the Qwen Code CLI as a one-shot bounded executor in a plan/do/verify loop. A frontier model (or you) plans the next bounded step and verifies the result; qwen-do makes a local model do exactly that one step, smoke-test first, then stop. Use when you want a cheap local model to do grunt coding while a smarter orchestrator keeps it on rails.
Scan git commits for PII, credentials, API keys, and passwords before they are pushed. Automatically gates commits via a pre-commit hook. Use when installing PII scanning on a repo, manually scanning a file or diff for credentials, or when a commit is blocked by the hook and remediation is needed. Triggers on "scan for PII", "check for credentials", "install PII guard", "pii hook", or when a commit is blocked by a PII check.
Runs a full CORE-EEAT 80-item content quality audit, scoring content across 8 dimensions with weighted scoring by content type. Produces a detailed report with per-item scores, dimension analysis, and a prioritized action plan.
PR review skill. Two modes: /pr [link] = internal thoughts only, what to look for, what to test — NO GitHub action ever. /pr-comment [link] "make it so #1" = draft a GitHub PR comment in <USER_NAME>s voice, present for approval, post only on explicit "go". Passphrase + "go" are both required before any GitHub write. Without both gates, nothing leaves the building.
Deep reflection and optimization with Opus. Two modes — /self-reflect analyzes completed work, extracts root causes, and stores lessons. /optimize analyzes a process or system, determines the right model and approach, then executes improvements. Use when reflecting on what happened, extracting lessons, optimizing workflows, or improving approaches. Triggers on "self-reflect", "reflect on", "optimize", "what went wrong", "what can we improve", "lessons learned".
| name | diagnose |
| description | Deep analysis and debugging with Opus. Systematically investigate problems, identify root causes, and recommend fixes with evidence. |
| category | debugging |
| runtimes | ["claude"] |
| pii_safe | true |
When user invokes /diagnose [problem description], perform deep investigation using Opus.
Switch to Opus for deep analytical thinking:
session_status model=opus
Gather evidence before forming hypotheses:
Analyze systematically:
Create diagnosis report:
## Diagnosis: [Problem Summary]
**Created:** [ISO timestamp]
**Model:** Opus
**Severity:** Critical | High | Medium | Low
### Symptoms
- [What's happening]
### Expected Behavior
- [What should happen]
### Investigation
1. [What I checked] → [What I found]
2. [What I checked] → [What I found]
### Root Cause
[The actual cause, with evidence]
### Recommended Fix
1. [Specific action]
2. [Specific action]
### Prevention
- [How to prevent recurrence]
Store diagnosis in haivemind:
mcporter call haivemind.store_memory \
content="DIAGNOSIS [channel-id] [ISO-timestamp] problem=[summary]: [diagnosis]" \
category="operations"
Present findings clearly:
Switch back to Sonnet after presenting findings:
session_status model=sonnet
Offer next steps:
/plan the fix?"/do it now?"Read <LOCAL_PATH>/dev/<PROJECT_NAME>.md — check Common Mistakes and Gotchas sections. The answer may already be documented from a previous incident.
When running as a sub-agent (session key contains "subagent"):
You MUST post diagnosis results back to the originating channel before completing.
See full pattern: <LOCAL_PATH>/dev/skills/subagent-result-posting/SKILL.md
Requester session: agent:main:[channel]:channel:[id] → platform + channel IDRequester channel: [channel] → platform namemessage action=send channel=[platform] target=[channel-id] message="🔍 **Diagnosis Complete**\n\n[findings summary]"
<LOCAL_PATH>/dev/tmp/results/diagnose-[timestamp].md/plan the fix?" or "Should I /do it now?"/plan for complex fixes, /do for simple ones/assess to verify the fix?"