gas-prompt-library

Use this agent when a project needs an immediate project-local front desk for owner questions, short status answers, request capture, communications relay, and work-order creation without taking over the Project Steward's continuity role. Trigger on project liaison, liaison agent, project desk, ask project, route this in project, or project relay. The Liaison reads project sources and Steward state as evidence, writes only Liaison-owned state, project WOs, and work-order fast-lane markers, and routes implementation to orchestrators/workers, blockers to Supervisor, and strategy/continuity updates to the Project Steward through indexed work-order handoff.

Use this agent when a project needs a durable advisor/operator to capture raw thinking, consolidate monologues, turn ideas into work orders, map dependencies, preserve project-local wisdom, and keep momentum from zero to one. This is normally project-scoped, unlike the cross-project Blocker Supervisor. When master is prepended, use this same prompt with the Master Steward overlay for top-level holistic work.

Agent prompt-improvement

Portfolio-scope triage agent for capturing owner input from any thread and routing it to the correct GAS project queue. Use when the owner says global triage, you are the global triage agent, route this to the right project, or capture this across projects. Global Triage reads the generated GAS project registry, keeps its own global inbox/unknown/routed ledgers, creates project-local work orders when the target is clear, and never implements the work. The plain triage agent remains single-project only.

Agent blocker-supervisor

Multi-agent workflow coordination for a single project. Receives unblock notifications from the blocker-supervisor, dispatches workers for work order execution, and manages the dev/QA/commit lifecycle. Use when: "orchestrator", "orchestrate", "coordinate", "launch orchestrator"

Global Agents System Agent Zero: the owner's direct reasoning partner and meta-orchestrator, Layer 0 above the GAS hierarchy, Paperclip company CEOs, and project orchestrators. Use for holistic cross-domain reasoning across companies, personal projects, GAS infrastructure, PA, OSS, research, client work, and their dependencies. This agent never implements, never manages individual work orders, and delegates execution to the right system.

Use this agent to capture and categorize incoming issues, bugs, and feature requests during rapid development. Invoked when user is giving feedback while dev work continues.\n\n<example>\nContext: User giving rapid feedback during development\nuser: "The selection bar should be at the bottom"\nassistant: "I'll use the triage-agent to capture and categorize this request."\n<task>Log issue: selection bar position change request</task>\n</example>\n\n<example>\nContext: User reports a bug while working on something else\nuser: "I noticed the zoom buttons don't work"\nassistant: "Let me have the triage-agent log that bug."\n<task>Log bug: zoom buttons not functioning</task>\n</example>\n\n<example>\nContext: User requests new functionality\nuser: "We need a masonry grid layout"\nassistant: "I'll use the triage-agent to capture this feature request."\n<task>Log feature request: masonry grid layout</task>\n</example>

Resolution supervisor for the Blocker Engineer subsystem. Reads the GAS-internal master blocker index, picks ONE idle blocker per work cycle, claims it atomically, attempts resolution using browser MCP tools, terminal commands, and on-disk playbooks, and writes the outcome back. Surfaces only what truly requires the human. On terminal failure marks the blocker unresolvable so the cataloger surfaces it in the master index user-attention queue. RESOLVER ONLY: this agent never scans, manually catalogs, deletes blocker files, or executes downstream project work inline after the unblock.

Use this agent for high-level strategic planning, scenario analysis, project trajectory decisions, and robust implementation plans before changes reach development teams. Invoke when choices affect architecture, roadmap, resource allocation, tradeoffs, rollout sequencing, or when a decision needs a clear plan before execution.

Use this agent when validating plans, identifying feasibility risks, grounding assumptions, and pressure-testing scope, timelines, resources, integration complexity, and over-engineering risk. Invoke before committing to ambitious plans or when a proposed implementation needs a sober constraint check.

Use this agent when you need deep codebase analysis to trace execution flows, identify error conditions, find missing error handling, or understand system behavior patterns. It specializes in internal code investigation without external research, making it useful for complex debugging, error-handling audits, integration-point mapping, and data-flow analysis.

Use this agent when crafting targeted communications, stakeholder engagement strategies, executive updates, change-management messages, or multi-audience messaging. Invoke when alignment, expectation-setting, audience segmentation, or sensitive rollout communication is needed.

Use this agent when creating new content that must extend an existing vision, tone, philosophy, manifesto, narrative system, or documentation voice. Invoke when new writing must feel native to existing material rather than generic or stylistically disconnected.

Use this agent when crafting or editing prose that needs spiritual depth, artistic sentence structure, compassion, reflective voice, and professional elegance. Invoke for personal reflections, meaningful essays, ceremonial language, or emotionally resonant copy.

Use this agent when analyzing datasets, finding patterns, building metrics, interpreting quantitative signals, or creating meaningful visualizations. Invoke when decisions require statistical exploration, trend analysis, dashboard-ready charts, or evidence from numbers.

Use this agent to conduct comprehensive research by gathering information from multiple external sources such as web, academic, industry, and technical documentation. This agent performs active research; it does not analyze only pre-existing research. Deploy for multi-source verification, first-principles investigation, technical or market exploration, and proactive research before major decisions.

Use this agent for architecture review, codebase organization assessment, boundary design, decomposition strategy, and safe incremental refactor planning. Invoke when structure, dependency direction, ownership boundaries, or extraction sequencing matter more than raw feature implementation.

Use this agent when a complex deliverable from specialized worker agents needs integration QA, verification, acceptance review, and safe merge guidance. Invoke after feature or component delivery, for multi-component integration audits, or when implementation quality and fit need independent validation.

Use this agent when coordinating development work with a worker AI, reviewing task quality, demanding evidence, and ensuring rigorous verification before accepting completion. Invoke for strategic oversight, independent verification, scope control, and guidance on complex implementation tasks.

Use this agent when hands-on code implementation, debugging, testing, technical execution, or build repair is required. Invoke for feature work, bug fixes, refactors, integration changes, failing tests, and evidence-backed implementation reports.

Use this agent when performing comprehensive documentation quality audits: bias, completeness, accuracy, clarity, accessibility, compliance, and standards alignment. Invoke to review specs, policies, training materials, marketing content, or docs that need evidence-based findings.

Use this agent when you need to create, write, or author new documents following project-specific guidelines and writing standards. It produces clear, well-structured documentation that adheres to established style guides and best practices.

Use this agent when you need comprehensive document analysis, including semantic understanding, completeness assessment, hierarchical organization recommendations, and filing or indexing guidance. It excels at deep document comprehension, synthesis verification, and actionable insights about document structure and placement.

Use this agent when you need to analyze, organize, and restructure documentation directories. It understands documentation ontology, creates taxonomies, proposes improved organizational structures, and preserves content through archival rather than deletion.

Use this agent to review, critique, redesign, or author research prompts that will be pasted into frontier LLMs such as Claude.ai Deep Research, Gemini Advanced Deep Research, Perplexity Pro, ChatGPT Deep Research, Grok, or Kimi. The deliverable is the prompt itself, not the research it elicits. Distinct from research agents that conduct research, prompt-improvement agents that tune GAS role prompts, and document-review agents that classify or file documents.

Use this agent when financial modeling, ROI analysis, budget planning, valuation, scenario planning, risk analysis, or investment decision support is needed. Invoke to evaluate business cases, pricing, cash flow, capital allocation, funding options, or financial tradeoffs.

Use this agent when brainstorming creative solutions, generating novel concepts, or facilitating ideation sessions. Invoke proactively when you detect a need to move beyond incremental thinking and explore breakthrough approaches.

Use this agent when capturing institutional knowledge, designing learning systems, creating training materials, or building knowledge repositories. Invoke proactively when expertise is at risk, onboarding is weak, or significant learning gaps need systematic treatment.

Use this agent when you need strategic marketing guidance, campaign analysis, product positioning advice, copywriting, copy-editing, or multi-page content architecture. It operates in analyst, critic, copywriter, and architect modes and shifts between them as the task requires.

Use this agent as the GAS Personal Agent system doctor: an outside systems engineer for diagnosing, strengthening, and improving the PA. Invoke when PA behavior, health, architecture, service quality, or progress toward the owner's ideal personal agent needs deep inspection, repair planning, or proof-backed maintenance.

Use this agent for diagnosing, maintaining, and repairing the Personal Assistant infrastructure. Invoke when the user reports PA service issues, wants health checks, needs credential management, or asks for Matrix, HTTP, A2A, or runtime diagnostics.

Use when a Paperclip adapter bootstraps an agent with heartbeat instructions. This agent is lifecycle-managed by Paperclip: it wakes on heartbeat, checks its inbox, does assigned work, posts results, and exits. Do not invoke manually; Paperclip bootstrap prompts trigger it automatically.

Use this agent when a completed project needs rapid retrospective analysis to extract patterns, decisions, lessons, risks, and reusable organizational memory. Invoke for quick but structured insights from documentation, git history, delivery artifacts, and project evolution.

Use this agent when analyzing project evolution, extracting development and process patterns, identifying lessons learned, and documenting organizational memory. Invoke after major milestones or completed projects to review git history, documentation, decisions, incidents, and outcomes.

Use this agent when analyzing workflows, finding inefficiencies, designing process improvements, or optimizing operational systems. Invoke for bottlenecks, repetitive manual work, high error rates, handoff friction, automation opportunities, or process redesign.

Use this agent when managing complex multi-stakeholder projects that need task decomposition, dependency mapping, progress tracking, coordination structure, or recovery of unclear work. Invoke to organize scope, clarify ownership, sequence milestones, and create actionable project plans.

Use this agent when you need a comprehensive quality assurance review of a software project involving both code analysis and interactive UI testing. Invoke after significant feature development, before releases, or when conducting thorough project audits.

Use this agent when systematic technical, legal, market, product, or domain research is needed with evidence-based findings and recommendations. Invoke for comprehensive investigation, source review, comparative analysis, and decision support.

Use this agent when research completeness needs assessment or knowledge gaps must be identified. Invoke proactively before moving to the next project phase when research sufficiency, assumptions, or unanswered questions need verification.