AI Agent Workflow Collection

Use when generating multiple slide images at scale, creating AI slide decks, or iterating on presentation visuals with generate-image CLI.

Migrate docs from bd (beads) to br (beadsrust). Use when updating AGENTS.md, converting bd commands, "bd sync" → "br sync --flush-only", or beads migration.

Use when user asks about calendar, schedule, wants to create/view events, mentions meetings, appointments, or availability. Covers gcal CLI.

Use when working with clawdbot, configuring messaging bindings, WhatsApp/iMessage/Telegram channels, or managing agent identities and routing.

Use when you discover a stray config file; move into dotfiles, symlink back, and commit.

Use when creating or relocating project documentation files for human readers (guides, implementation notes, reference pages); not for AI agent memory or skill files. For agent knowledge routing, see memory-placement.

Use when drafting email replies for Michael, generating outbound emails, or applying his email communication patterns and style.

Use when adding or updating environment variables or secrets. Covers global secrets (~/.env.zsh), project-specific secrets (.env.local), and documentation patterns (.env.example).

Use when in an everything-loop session, when system message shows "Everything Loop iteration", when continuing autonomous development work.

Use when about to run "git stash", encountering modified files you didn't create, or working with git operations that require a clean working tree.

Turn a broad or open-ended goal into a checkable definition of done, track it, and autonomously pursue it until that "done" verifies. Use this whenever the user signals PERSISTENT PURSUIT toward an outcome: "keep going until X", "don't stop until Y", "iterate until it passes", "work on this until it's actually done", or any broad goal that clearly wants sustained work toward a stopping condition rather than a single one-off action. The "until X" becomes the falsifiable success criterion and the loop's exit condition. Also use it when the user wants to set up, sharpen, or track a goal of that kind, or asks where such a goal stands. Do NOT use it for a concrete one-off task that should just be done, for repo CI fitness gates (that is the agentops goals skill, GOALS.yaml / ao), or when the user explicitly typed the built-in /goal command.

Process raw Todoist inbox items into a structured knowledge system using GTD (actions → Todoist) and PARA (reference → Obsidian). Use when batch-processing inbox captures, triaging voice notes and links, filing raw ideas into Obsidian with MOC suggestions, or running an inbox-to-knowledge-system pipeline. Handles enrichment (URL fetching, voice interpretation), clustering related items, generating Obsidian reference notes, filing Todoist actions, and producing a triage report. Self-improving via prompt-self-improvement protocol.

End-to-end define-to-ship delivery loop with DAG orchestration and stage gates. Use when the user wants to turn high-level product goals into detailed stories (risks, decisions, acceptance checks), execute with subagents, run independent dual reviews, and progress tasks only when explicit gate criteria pass.

Use when performing batch operations on many similar items (files, migrations, refactors). Do 2-3 items manually first to discover patterns, then write a comprehensive subagent prompt for parallel execution.

Use when user says 'remember this', when deciding where to store learnings or context, when about to edit CLAUDE.md or create a skill, or when routing any persistent information. Determines the correct storage destination among CLAUDE.md, auto-memory, rules, skills, and local overrides.

Log, analyze, and prevent recurring mistakes. Use when: (1) a mistake or near-miss occurs (self-detected or user-detected), (2) session start/end review of recent patterns, (3) user asks to review or analyze mistakes, (4) after any corrective action to verify the fix was logged. Covers logging JSONL events, running RCA, promoting/demoting guardrails, and testing prevention.

Produces a finished motivational audio clip, a spoken voiceover mixed over a music bed. Use for wake-up, hype, or pump-up tracks, or narration that needs music underneath. For speech with no music use tts.

Use when interacting with Notion PPV system, creating projects, updating goals, doing quarterly reviews, or working with PPV databases.

Use when automating macOS apps, clicking UI elements, taking screenshots, or controlling applications via peekaboo CLI with vision-based detection.

Speeds up piagentrust development and verification workflows. Use when editing providers, tools, sessions, extensions, installer/uninstaller logic, or triaging regressions in this repo.

Use when about to kill a process on a port, when a port is busy and you need to free it, or when suspecting a dev server is still running.

Use when summarizing a session; append a human-readable entry and reference any updated guides.

Use when the user asks to save session context, identify the current session or thread, create a resumable handoff, or prepare a Todoist/note summary that must include the working directory and session id. Works across Codex and Claude Code by detecting runtime-specific session identifiers and normalizing them into one summary.

Use when creating Next.js projects with shadcn/ui, scaffolding new apps with Radix components, or setting up React apps with the Nova theme.