メニュー
Daily triage accuracy calibration — use during scheduled calibration runs to verify triage classification accuracy against few-shot examples and adjust confidence thresholds
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | triage-calibration |
| description | Daily triage accuracy calibration — use during scheduled calibration runs to verify triage classification accuracy against few-shot examples and adjust confidence thresholds |
| consumer | daily_calibration |
| phase | 6 |
| skill_type | hybrid |
Review recent triage decisions against actual outcomes. Adjust signal weights and depth thresholds to improve classification accuracy over time.
date: <YYYY-MM-DD>
period: <start> to <end>
total_ticks: <n>
accuracy: <percentage>
over_triage_rate: <percentage>
under_triage_rate: <percentage>
systematic_errors:
- signal: <signal name>
bias: over | under
magnitude: <how far off>
recommendations:
- <proposed adjustment>
src/genesis/learning/triage/ — Triage pipelinesrc/genesis/awareness/ — Awareness loop and depth classificationsrc/genesis/learning/signals/ — Signal collectorsThis skill should be used when developing, debugging, refactoring, or building Genesis itself — tasks like "fix this in Genesis", "add a new MCP tool", "wire up the runtime", "Genesis won't start", "create a worktree", "debug the bridge", or "add a capability". Applies to any task modifying files under src/, .claude/, or tests/. Do NOT load for Genesis-as-tool work ("summarize this", "write a LinkedIn post", "research X") or general questions unrelated to Genesis internals.
Foundational voice authority and AI humanizer — writes content in the user's authentic voice with built-in AI detection, and supports stealth / anti- attribution writing (forum personas, anonymous posts, "write as not-me"). Use when asked to write/draft/generate content, invoke /voice, /write-as-me, or /humanize, run voice calibration, check "does this sound like me?", "make this sound human" / "de-AI this", "write a forum post as [persona]", or run AI detection ("does this sound like AI?", "check for AI patterns", "anti-slop check"). Do NOT use this skill for code, technical docs, or any output the user has not asked to be written in their voice — code styling defers to the separate code-voice skill.
Forward Deployed Engineer delivery contract for AWS engagements, build-first artifacts, grounded cost estimates, Well-Architected review, evolution roadmap
This skill should be used before answering "does Genesis have X", "does Genesis lack X", auditing Genesis capabilities, comparing Genesis to an external system, or reviewing/summarizing the architecture. It routes to the canonical judgment-layer subsystem map so audits start from the map, not from a cold grep. Also fires after changing a subsystem's capabilities, to keep the map current.
First-run onboarding — guides new users through Genesis setup on their first CC session. Configures user profile, essential API keys, Telegram, GitHub backup, and service verification. Triggered automatically when ~/.genesis/setup-complete is absent. Re-runnable by asking Genesis to "run setup" or "reconfigure [section]".
Apply when Genesis writes as itself — outreach, public content, community posts, emails, DMs. Not for writing in the user's voice (that's voice-master). Activate when Genesis is the author, not the ghostwriter.