AI Agent Workflow Collection

Forward Deployed Engineer delivery contract for AWS engagements, build-first artifacts, grounded cost estimates, Well-Architected review, evolution…

Code understanding tool selection.

Multi-AI adversarial fallback chain — three tiers: Codex CLI (primary), OpenCode/GLM5 (fallback), Claude subagent (last resort). Three modes: review (code review with pass/fail gate), challenge (adversarial — tries to break your code), consult (ask anything with session continuity). Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex".

End-to-end content creation and publishing. Takes a topic (or generates one), drafts in the user's voice, gets approval via Telegram, and publishes to Medium via browser automation. Invoke with "publish a post about X", "write and publish to Medium", "content-publish", or when an ego-dispatched session needs to create and distribute content.

Produce a professional, send-ready deliverable on the user's behalf — in the correct file format (never raw markdown), in the user's voice, structured to lead with the strongest material, and free of document-level AI tells. Runs a gated pipeline with a fresh-context verification policeman and a Stop-hook that won't let the session finish without a verified PASS. Use when producing a job take-home, client report, executive one-pager, slide deck, proposal, or anything going out under the user's name.

How to produce a demand forecast for a SKU, and when to delegate that to a subagent vs. compute it yourself. Load this for any task involving "forecast", "how much will we sell", "next month", promos, or seasonal SKUs.

Use 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.

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.

Turn any external program into a Genesis module via structured discovery, connection mapping, config generation, and verification.

Use when the user asks to "write a comment for this LinkedIn post", "help me respond to this post", "what should I comment on this", "craft a LinkedIn comment", or when Genesis identifies high-value posts in the user's network worth engaging with. Also triggered by "how should I engage on LinkedIn" or "help me be more visible on LinkedIn".

Use when the user asks to "plan my LinkedIn content", "create a content calendar", "what should I post about this week", "plan my posting schedule", or when Genesis proactively suggests a weekly content plan during surplus compute. Also triggered by "I need post ideas" or "I don't know what to write about".

Use when the user asks to "write a LinkedIn message", "draft a connection request", "help me reach out to someone on LinkedIn", "write an InMail", "message this person", or when the prospect-researcher skill identifies a high-value contact worth reaching out to. Also triggered by "how should I approach [person/company]" in a LinkedIn context.

Use when the user asks to "write a hook for my post", "give me opening lines", "help me start this LinkedIn post", "I need a better opener", or when the linkedin-post-writer skill needs strong opening options. Also triggered by "my posts aren't getting clicks" or "how do I get people to read my posts".

Use when the user asks to "write a LinkedIn post", "draft a post about", "help me post on LinkedIn", "create LinkedIn content", or when Genesis proactively generates post ideas during surplus compute. Also triggered by content calendar execution or when the user shares a topic they want to write about.

Resolve obstacles using fallback chains — use when an approach fails, a dependency is unavailable, an API returns errors, or a task is blocked and needs an alternative path…

Use when the user asks to "research this company", "look into this person", "find the best angle for reaching out to", "who should I contact at [company]", "what does [company] care about", or when preparing outreach to a specific target. Also triggered by "help me prepare for an interview with [company]" or "I want to apply to [company]". Combines lead-generation intelligence with LinkedIn-specific approach planning.

Shelve the current session — create a bookmark so you can find and resume it later with /unshelve.

Anti-detection behavioral rules for stealth browser…

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.

Daily triage accuracy calibration — use during scheduled calibration runs to verify triage classification accuracy against few-shot examples and adjust confidence…

Search for shelved sessions — find past bookmarked sessions by keyword or browse recent ones.

Apply the user's voice when writing or editing content. Activate when the user says "use the voice-master skill", "write this in my voice", "make this sound like me", or any equivalent instruction. Use for any content type: professional proposals, long-form writing, social posts, emails, or short-form copy. Do NOT activate for code, technical docs, or any output the user hasn't asked to be written in their voice.

Evaluate content for personal relevance to the user using the user…