メニュー
Systematic debugging of issues — use when a test fails, runtime error occurs, unexpected behavior is reported, or an awareness tick produces anomalous results
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
This 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.
| name | debugging |
| description | Systematic debugging of issues — use when a test fails, runtime error occurs, unexpected behavior is reported, or an awareness tick produces anomalous results |
| consumer | cc_background_task |
| phase | 6 |
| skill_type | workflow |
Systematically diagnose and resolve bugs, failures, or unexpected behavior in Genesis or its dependencies.
issue: <one-line description>
date: <YYYY-MM-DD>
root_cause: <what actually went wrong>
fix: <what was changed>
files_modified:
- <file path>
regression_risk: low | medium | high
lesson: <what to remember to prevent recurrence>
Trigger: Post-commit hook throws KeyError: 'HOME' in CI-like environment.
Expected output:
issue: Post-commit hook crashes when HOME not set in non-login sessions
date: 2026-04-06
root_cause: Hook script reads os.environ["HOME"] but non-login shells
(systemd, cron) strip HOME from environment
fix: Guard with os.environ.get("HOME", "/root") fallback + persist HOME
in /etc/environment during install
files_modified:
- .claude/hooks/genesis-hook
- scripts/install_guardian.sh
regression_risk: low
lesson: Never assume HOME exists — non-login shells strip it. Always
use get() with fallback for environment variables in hook scripts.
tests/ — Test suite for verificationsrc/genesis/learning/procedural/ — Procedure updates for recurring patterns