collab-audit
This skill should be used when the user types /collab-audit or requests AI collaboration diagnosis. Analyzes conversation history, artifacts, and work patterns to generate a 14-section AI Collaboration Audit. Behavioral analysis and feedback are bundled by design — separating them causes users to skip one, defeating the purpose. Saves to ~/.claude/collab-audits/YYYY-MM-DD.md. Compare mode: /collab-audit compare (diffs latest 2 audits). Triggers: '/collab-audit', '/collab-audit compare', 'AI 협업 진단해줘', '협업 진단', '행동 패턴 분석', '나 어떤 사람이야', 'AI collaboration audit', 'work pattern analysis', 'compare audits'. Requires minimum 2 sessions or 100+ messages. Do NOT use self-report surveys — observation-only.
AlexZio00 · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add AlexZio00/sovereign-skills --skill collab-audit技能说明
skill_type: analysis tools: Read, Write, Bash triggers:
- "/collab-audit"
- "AI 협업 진단"
- "협업 분석"
- "AI 협업 진단해줘" name: collab-audit description: "This skill should be used when the user types /collab-audit or requests AI collaboration diagnosis. Analyzes conversation history, artifacts, and work patterns to generate a 14-section AI Collaboration Audit. Behavioral analysis and feedback are bundled by design — separating them causes users to skip one, defeating the purpose. Saves to ~/.claude/collab-audits/YYYY-MM-DD.md. Compare mode: /collab-audit compare (diffs latest 2 audits). Triggers: '/collab-audit', '/collab-audit compare', 'AI 협업 진단해줘', '협업 진단', '행동 패턴 분석', '나 어떤 사람이야', 'AI collaboration audit', 'work pattern analysis', 'compare audits'. Requires minimum 2 sessions or 100+ messages. Do NOT use self-report surveys — observation-only." user_invocable: true not_for:
- "Single feedback -> direct conversation"
- "Auditing a skill's own quality/structure — this audits collaboration patterns, not skill content" see_also:
- skill: project-check
relation: "collab-audit=user collaboration patterns, project-check=project health"
depends_on:
skills: []
agents: []
files:
- "scripts/session_hygiene_scan.py" concurrency_profile: sequential
/collab-audit — AI Collaboration Audit
Purpose
Analyzes conversation history, artifacts, and work patterns to generate behavioral and psychological insights. Based on direct behavioral observation during actual work rather than self-report surveys. More accurate than survey-based methods.
Dominant Variable
Whether the analysis infers reasons behind observed patterns, not just lists facts (facts alone ≠ success)
Trigger
/collab-audit- "AI 협업 진단"
- "협업 분석"
- "AI 협업 진단해줘"
Discard If
- Fewer than 2 observed sessions AND fewer than 100 messages — insufficient sample to extract patterns
- Simple code review request → use code-reviewer instead
- Only quantitative session metrics needed → use project-check instead
Key Assumptions
- 2+ observed sessions + 100+ messages — if broken: Discard If triggers.
- Access to memory/session-handoff-LATEST.md — if broken: handoff pattern analysis unavailable, skip that dimension.
Mode Detection (execute first)
- Input contains
/collab-audit compareor "compare" → Compare mode (separate section below) - Otherwise → Audit mode (14-section analysis)
Input Validation (Step 0 — execute first)
Minimum conditions — one of:
- 2+ sessions
- 100+ messages
- Single-session high-density exception → refer to Invariant 4 criteria. If exception met, mark
⚠ Single-session analysis — pattern confidence limitedthen proceed.
Deterministic gate (preferred): if session-meta JSON files are available (one per session, with fields such as message_count, artifact_count, originator, first_message, cwd), run scripts/session_hygiene_scan.py --meta-dir <DIR> and read meets_minimum / single_session_exception straight from its JSON output — do not re-derive these booleans by eyeballing the transcripts. Fall back to manual counting only when no such metadata directory exists (e.g. a single live conversation with no file access).
If all unmet:
"Insufficient data — minimum 2 sessions or 100 messages required. Currently [N] messages, [M] artifacts observed."
Output and stop immediately. Reject even "prediction-based" requests.
Workflow
Step 0.5: Tone Detection (determine delivery intensity)
Determines delivery intensity for Section 11 blind spots only. Other sections are factual, so tone variance is minimal.
Read signals from conversation patterns:
- High ratio of short, direct messages / "facts only" / speed-first requests → Direct (maintain current default)
- High emotion expression frequency / preference for long explanations / feedback-receptive signals → Calibrated (same blind spot content, but provide context before delivery)
Mark result 1 line before Section 11: [Delivery intensity: Direct / Calibrated]
Mid-session re-assessment: If conversation tone shifts noticeably (emotion spike, request method change, defensive responses appear), re-assess right before Section 11 output. Initial assessment does not lock in the entire session.
Important: Changing delivery intensity does not change blind spot content (accuracy). Only adjusts temperature.
Step 0.6: Source Hygiene Filter (deterministic-first measurement)
When multiple observation sources exist (e.g. session JSONLs), determine — before analysis — whether each source is an organic user session or an automation byproduct. A qualitative caveat alone (the old Step 1 approach) is not enough; automated sessions can be mistaken for user behavior.
Deterministic gate: run scripts/session_hygiene_scan.py --meta-dir <DIR> against the directory of session-meta JSON files. The script classifies every session into one of three states — include (organic) / uncertain (cannot confirm either way) / exclude (confidently auto-derived) — and returns included_count, excluded_count, uncertain_count, meets_minimum, and single_session_exception in one JSON object — read those fields directly rather than re-judging exclusion by eye.
Detection criteria the script applies:
- Confident exclude: session metadata contains auto-derivation markers such as
subagent/thread_spawn/agent_nickname; OR cwd matches a naming convention specific to paired/multi-arm experiment harnesses (e.g.pair-run,arm-a/arm-b,ab-test); ORoriginatoris an SDK/bot/exec-type process with no direct user-input signal (natural conversational opening message) present. - Uncertain (needs review, not auto-folded either way): cwd contains only a generic automation-adjacent word (currently:
pipeline) with no other automation marker — a real user project named e.g.data-pipeline-toolmust not be silently misclassified as an