ianphil

This skill should be used when the user asks to "plan a feature", "create feature plan", "start planning", "new feature", or wants comprehensive planning with analysis, spec, research, design, and TDD task breakdown.

Generate structured, hallucination-proof code walkthroughs using Showboat. Use when the user asks to "walk me through this code", "explain this codebase", "create a walkthrough", "document how this works", "give me a tour of this repo", or wants a readable narrative document that explains code with real verified snippets. Also triggers on "showboat", "linear walkthrough", or "code documentation". Not for quick code questions — this produces a full markdown document.

Reverse-engineer software into product-level specifications and capability maps. Use when analyzing an OSS project, existing product, repo, docs, demos, or API surface to extract operator value, system capabilities, observable behavior, user flows, constraints, and non-goals — without implementation details. Triggers on "understand what this software does", "write a product spec from code", "extract requirements from this repo", "what does this project do as a product", "reverse-engineer this", "analyze this system", "describe this from the outside in", or any request to study software as a product rather than as an implementation.

This skill should be used when the user asks to "implement in parallel", "run phases concurrently", "parallel implement", "implement-agents phase X phase Y", or wants to orchestrate multiple agents running /implement simultaneously.

This skill should be used when the user asks to "consolidate notes", "summarize ainotes", "clean up notes", "ainotes", or wants to consolidate accumulated agent observations into a compact summary.

This skill should be used when the user asks to "commit changes", "push my code", "commit and push", "save my work", or wants to stage all changes and push to remote.

This skill should be used when the user asks to "load feature context", "resume feature work", "prime feature N", "continue feature N", or wants to load all planning artifacts for a specific feature number.

This skill should be used when the user asks to "prime the project", "load context", "get oriented", "what is this project", or wants to understand the codebase structure before starting work.

Install, remove, and manage extensions and skills from third-party Genesis packages. Use when the user asks to install a package from another repo, list installed packages, remove a third-party package, or check for updates from a specific package source.

Pull new extensions and skills from the genesis template registry. Use when user asks to "check for updates", "upgrade", "get latest extensions", or "sync from genesis".

Send messages to other agents — local or remote. The agent directory and communication layer. Use when the user asks to "talk to", "contact", "message", "reach", "send a message to", "ping", or "call" another agent by name. Also triggers on "list agents", "who can I talk to", or "add a contact".

Pull new extensions and skills from the genesis template registry. Use when user asks to "check for updates", "upgrade", "get latest extensions", or "sync from genesis".

Bootstrap a new AI agent mind. Use when user asks to "create a new mind", "new agent", "spawn a mind", "bootstrap another agent", or wants to set up a new agent persona. Supports repo-level and user-level minds.

Reference for building and debugging Copilot CLI extensions. Use when working on anything in .github/extensions/, creating extension tools, or troubleshooting extension lifecycle and SDK behavior.

Fleet library for sharing skills, extensions, and prompts between agents. Use when the user asks to "share a skill", "share a prompt", "fleet library", "library setup", "library add", "library use", "library sync", "library list", "library push", "library invite", or wants to distribute skills, extensions, or prompts laterally across a private agent fleet.

This skill should be used when the user asks to "load feature context", "resume feature work", "prime feature N", "continue feature N", or wants to load all planning artifacts for a specific feature number.

This skill should be used when the user asks to "plan a feature", "create feature plan", "start planning", "new feature", or wants comprehensive planning with analysis, spec, research, design, and TDD task breakdown.

This skill should be used when the user asks to "close feature", "archive feature", "complete feature N", "move feature to completed", or wants to move a finished feature to the _completed/ directory.

This skill should be used when the user asks to "commit changes", "push my code", "commit and push", "save my work", or wants to stage all changes and push to remote.

This skill should be used when the user asks to "implement in parallel", "run phases concurrently", "parallel implement", "implement-agents phase X phase Y", or wants to orchestrate multiple agents running /implement simultaneously.

This skill should be used when the user asks to "prime the project", "load context", "get oriented", "what is this project", or wants to understand the codebase structure before starting work.

Dispatch a Chamber release build to either the insiders channel (Azure blob, Windows + macOS, invite-only testers) or the stable channel (public GitHub Releases, Windows + macOS). Use this skill whenever the user asks to release, cut, publish, promote, ship a build, push to insiders, send to testers, go public, or make a new version available — even if they don't explicitly name a channel. This skill picks the channel, runs pre-flight checks, handles stable remote feature-flag graduation when needed, dispatches the matching workflow via `gh`, and reports back. It may open mechanical release/policy PRs but never merges anything without explicit user approval.

Connect and coordinate with Chamber A2A relay agents. Use this whenever the user mentions A2A, a2a-client, relay agents, Switchboard relay, connecting to the relay, listing agents, sending an agent a message, reading inbound messages, or replying to an inbound A2A message. Prefer the direct `a2a_*` tools; do not use shell commands as markers or wrappers for A2A actions.

Batch workflow for Chamber issue slates. Use this when the user asks to work through a group of GitHub issues by label, priority, milestone, or explicit issue list. It triages the slate, groups issues into small PRs/stacks, creates a roadmap and todos, then executes each item with a TDD mini-plan and the Chamber ship skill.

End-to-end shipping workflow for the Chamber repo. Use this when the user asks to ship, prepare, open, finalize, land, or create a PR. It rebases on the target base, applies version/changelog defaults, links closing issues, runs smoke tests, optionally reviews with Uncle Bob, and creates the PR via `gh`. Supports issue-slate autopilot defaults for batched work.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Use this for LlmAgent work: agent loop changes, AgentSession/harness APIs, AgentLoopOptions/API design, tools, events, context budget, option forwarding, or any task that mentions the agent package. It forces a harness-first public-surface decision, prefers portable SDK context streaming for ergonomic agent behavior, keeps raw Responses as an explicit escape hatch, and picks unit/fake/live agent tests before implementation.

Batch workflow for llm-svc issue slates. Use this when the user asks to work through a group of GitHub issues by label, priority, milestone, or explicit issue list. It triages the slate, groups issues into small independent PRs, creates a roadmap and todos, then executes each item with a TDD mini-plan.

Use this when adding or reviewing fake/live integration tests in this repo, especially for SDK, service, or agent behavior. It creates paired .Int coverage: fake tests for deterministic happy, negative, edge, and error cases; live Smoke tests for small real-upstream happy-path compatibility.

Use this for LlmSdk work: SDK issues, SDK client changes, Core/Proxy behavior, Infrastructure adapters, model/auth/routing/translation changes, or any task that mentions the SDK layer. It forces an SDK layer decision first, keeps agent/service consumers separate, and picks the owning SDK tests before implementation.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Generates a comprehensive daily report covering ADO work items, Teams chats, calendar, email, local mind next-actions, and inbox notes. Run this each morning to get a scannable summary of everything you need to know to start your day. Use when user asks for "daily report", "morning briefing", or "what's on my plate today".

Bootstrap a new AI agent mind. Use when user asks to "create a new mind", "new agent", "spawn a mind", "bootstrap another agent", or wants to set up a new agent persona. Supports repo-level and user-level minds.

Reverse-engineer software into product-level specifications and capability maps. Use when analyzing an OSS project, existing product, repo, docs, demos, or API surface to extract operator value, system capabilities, observable behavior, user flows, constraints, and non-goals — without implementation details. Triggers on "understand what this software does", "write a product spec from code", "extract requirements from this repo", "what does this project do as a product", "reverse-engineer this", "analyze this system", "describe this from the outside in", or any request to study software as a product rather than as an implementation.

Pull new extensions and skills from the genesis template registry. Use when user asks to "check for updates", "upgrade", "get latest extensions", or "sync from genesis".

Create, validate, run, inspect, and schedule Chamber automation scripts. Use this skill whenever the user asks for cron jobs, recurring work, scheduled tasks, reminders, daily/weekly/monthly checks, background automations, unattended workflows, or anything that should run later or repeat inside a Chamber mind. This is the Chamber-specific companion to the ttasks skill; use ttasks for generic task graph patterns and this skill for Chamber cron and automation-runtime rules.

Create, inspect, fix, and manage Chamber Lens views. Use this skill whenever the user mentions Lens, lenses, Chamber views, dashboards, panels, reports, forms, command centers, app-like screens, self-modifying UI, or says a Lens icon/view is missing. Always use this skill before creating or editing files under .github/lens.

TypeScript task runner and workflow engine using @ianphil/ttasks-ts. Use this skill whenever you need to run, chain, or orchestrate TypeScript operations — even if the user hasn't mentioned ttasks. Reach for it when they want to: run a shell command and track the result, chain steps where later ones depend on earlier ones ('do X then Y then Z'), run tasks in parallel and merge results, ensure cleanup always runs even after a failure, persist step results to disk so they survive a crash, include an LLM prompt or agent step inside a workflow, or find out exactly which step in a pipeline broke. Also triggers on: build pipeline, automate steps, retry on failure, parallel tasks, workflow with dependencies, 'if one step fails skip the rest', task queue in TypeScript. DO NOT USE FOR: non-TypeScript projects, throwaway one-liners that don't need tracking.

This skill should be used when the user asks to "commit changes", "push my code", "commit and push", "save my work", or wants to stage all changes and push to remote.

Generates a comprehensive daily report covering ADO work items, Teams chats, calendar, email, local mind next-actions, and inbox notes. Run this each morning to get a scannable summary of everything you need to know to start your day. Use when user asks for "daily report", "morning briefing", or "what's on my plate today".

This skill should be used when the user asks to "commit changes", "push my code", "commit and push", "save my work", or wants to stage all changes and push to remote.

Generates a comprehensive daily report covering ADO work items, Teams chats, calendar, email, local mind next-actions, and inbox notes. Run this each morning to get a scannable summary of everything you need to know to start your day. Use when user asks for "daily report", "morning briefing", or "what's on my plate today".

Search the notes mind using QMD hybrid search. Use when looking up notes, finding related documents, searching for decisions, people, initiatives, or any mind content. Triggers on search, find, look up, "what do I know about", "where is", recall.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

TypeScript task runner and workflow engine using @ianphil/ttasks-ts. Use this skill whenever you need to run, chain, or orchestrate TypeScript operations — even if the user hasn't mentioned ttasks. Reach for it when they want to: run a shell command and track the result, chain steps where later ones depend on earlier ones ('do X then Y then Z'), run tasks in parallel and merge results, ensure cleanup always runs even after a failure, persist step results to disk so they survive a crash, include an LLM prompt or agent step inside a workflow, or find out exactly which step in a pipeline broke. Also triggers on: build pipeline, automate steps, retry on failure, parallel tasks, workflow with dependencies, 'if one step fails skip the rest', task queue in TypeScript. DO NOT USE FOR: non-TypeScript projects, throwaway one-liners that don't need tracking.

Reverse-engineer software into product-level specifications and capability maps. Use when analyzing an OSS project, existing product, repo, docs, demos, or API surface to extract operator value, system capabilities, observable behavior, user flows, constraints, and non-goals — without implementation details. Triggers on "understand what this software does", "write a product spec from code", "extract requirements from this repo", "what does this project do as a product", "reverse-engineer this", "analyze this system", "describe this from the outside in", or any request to study software as a product rather than as an implementation.