Hub Liaison
On any Telegram HUB-Q reply ALWAYS write the pi hub bridge answer file — even when the thread shows cancel/closed/timeout notes; the bridge classifies late answers itself. Use when a Telegram message replies to or contains a [HUB-Q:<qid>] marker.
Browser Testing With Devtools
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
Planning And Task Breakdown
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
Orchestration Verification
Defines the Verification Contract that keeps a multi-agent run honest — dispatcher-owned acceptance assertions, a parity/touchpoint inventory for "behave like X" requests, structured upward returns, and a requirement-regression reset. Use when orchestrating specialists through a dispatcher (agent-hub), when a "make X behave like Y" change risks shipping the exemplar while its siblings are missed,…
Designing Agents
Designs and writes a focused artifact another agent runs — an agent persona in agents/, a workflow skill in skills/, or a pi session harness in .pi/harnesses/. Use when authoring a reviewer or specialist persona, a repeatable process skill, or a pi extension that reshapes a session — or when rewriting one that is under-specified, overlapping, or being ignored.
Security And Hardening
Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.
Idea Refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or "stress-test my plan".
Context Engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
Bowser
Headless browser automation using Playwright CLI. Use when you need headless browsing, parallel browser sessions, UI testing, screenshots, web scraping, or browser automation that can run in the background. Keywords - playwright, headless, browser, test, screenshot, scrape, parallel.
Using Agent Skills
Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.
Compound Learning
Captures a finished session's lessons into the project's own rules and docs — extracts candidate lessons from session evidence, dedupes them against the existing rule tree, and lands them as minimal diffs on existing files. Use when a session ends with user corrections, recurring review findings, or debugging root causes worth keeping, when the user says "compound" or "capture the lessons", or as…
Guided Workspace Setup
Guides installation of agent-fleet artifacts into a target workspace. Use when onboarding a project to agent-fleet, when installing skills, commands, prompts, personas, or pi extensions for a chosen coding agent, or when a workspace needs its setup files configured.
Incremental Implementation
Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
Interview Me
Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch your…
Spec Driven Development
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.
Hub Conductor
Conducts local pi hub-team peers from Hermes through coms-cli list/send --await, while preserving no-herdr and pool-scope damage-control boundaries.
Peer Coms
Makes Claude Code a first-class peer in the local coms agent pool — discover pi colleagues, ask or delegate to them mid-task, and answer their inbound questions. Use when running inside a bridged herdr pane (a coms-claude-bridge is attached), when a task would benefit from asking a running pi peer (researcher, documenter, an orchestrator hub), or when a message prefixed "[coms message from …]" ar…
Git Workflow And Versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump, tagging, or writing a changelog.