pedrogrande

Create VS Code custom agents (.agent.md files) that define specialized AI personas with scoped tools, model preferences, handoffs, and hooks. Use when creating a new custom agent, configuring tool restrictions for a role, setting up agent handoffs for multi-step workflows, adding agent-scoped hooks, or deciding between agents vs prompt files vs skills.

Guide for the Project Initiation Manager when conducting the brief conversation. Covers all three entry paths (fresh start, rough brief, form JSON), the one-question-at-a-time conversation rules, completeness-driven question ordering, and how to generate the markdown brief.

Show pending tasks for a TaskFlow agent role. Lists what work is waiting and which project/feature each task belongs to. Use this to find out what an agent needs to do next.

Add TaskFlow to an existing project. Scans the workspace, detects existing agents/skills/MCP servers, and guides the user through creating a brief that captures what's already built.

Start a new TaskFlow project. Prompts for a project brief (file path or inline text), then hands off to the Project Initiation Manager to build and validate the brief before the Dev Manager configures the team. Use this to kick off a new development cycle.

Check for and apply pending TaskFlow schema migrations after pulling a new release.

Guide for the product_manager agent when writing feature records and definitions of done in step 3. Auto-loaded when a step-3 task is in progress.

How to use vscode/askQuestions and vscode/memory tools correctly. Load this skill whenever you need to ask the user structured questions or persist working state across turns.

Strategic guidance for the ask_user tool (UserFeedbackTools) — when to pause and ask the user structured questions, how to design options, anti-patterns to avoid, and how to behave after the run resumes. Load this skill before calling ask_user whenever you need to clarify intent, resolve a trade-off, or collect a preference that genuinely shapes your next action.

Execute an AgentOS implementation plan to completion — create/edit files, register agents, add evals, validate, smoke-test, update AGENTS.md, write a report. Use when a plan exists and you want it built. Covers Agno conventions and AGENTS.md update mapping.

Plan implementations of new agents, teams, workflows, and capabilities for AgentOS (Agno + Postgres + pgvector). Use when architecting or scoping before coding. Covers agent shape, DB isolation, guardrails, evals, promotion.

Governing delivery rules, energy calibration, pattern portfolio, self-check protocol, and priority matrix for the ThinkingPartner behaviours. Load this skill whenever any behaviour trigger fires — it provides the rules that govern every response, plus the two always-on behaviours (Energy Calibration, Pattern Portfolio). Other ThinkingPartner skills (contextual, expansions, examples) load alongside this one.

Delegate calendar tasks to the CalendarAgent via AgentOS MCP. The thinking partner does not have direct calendar tools — it calls the calendar agent when the user needs to view, search, create, update, or delete events.

Interact with Google Drive scoped to the collab001 project folder. List, search, read, upload, and download files — all operations are restricted to the collab001 folder. Uses a service account that has been granted access to the folder.

Generate ideal (best-case) outcomes for a stakeholder group — the ceiling when everything has gone perfectly to plan, not the floor of what's acceptable. Use this skill when the user asks for ideal outcomes, best-case outcomes, or the best-case scenario for a stakeholder group, or when generating outcomes and the user wants the ceiling not the floor. Also use when the user has asked for ideal outcomes and the response is drifting toward acceptable or realistic outcomes.

Surface patterns, recurring themes, and connections across the user's thinking. Identify when ideas in one area relate to another, and highlight challenges that keep coming back.

Full 8-part Agno Agent Design Template. Load when filling out, presenting, or reviewing the agent design template.

Current EdgeAI infrastructure reference — databases, agents, tools, services, and environment variables. Load when referring to existing infrastructure or making compatibility decisions.

7-phase agent design process — DISCOVER, SCOPE, SPECIFY, REVIEW & APPROVE, GENERATE, VALIDATE, PERSIST. Load when designing a new agent or continuing an in-progress design.

Plain-language analogies for technical design choices. Load when explaining storage, memory, model, vector DB, architecture, guardrails, or human-in-the-loop to non-technical users.

Show pending tasks for a TaskFlow agent role. Lists what work is waiting and which project/feature each task belongs to. Use this to find out what an agent needs to do next.

Start a new TaskFlow project. Prompts for a project brief (file path or inline text), creates the project record, and seeds the pipeline for the product manager. Use this to kick off a new development cycle.

Guide for the product_manager agent when writing feature records and definitions of done in step 3. Auto-loaded when a step-3 task is in progress.

Decomposes a requirement into tasks and inserts them into the DevFlow database, auto-spawning reviews for qualifying task types.

Reads a project brief from the workspace and ingests it into the DevFlow database — creating a project row and deriving requirements.

Surfaces all pending reviews and guides the reviewer agent through approving or rejecting each one.

Design and implement Agent Skills following best practices for VS Code and any Agent Skills-compatible agent. Use this skill when the user wants to create a new skill, improve an existing skill, review a skill for quality, or learn skill authoring best practices. Covers scoping decisions, instruction patterns, progressive disclosure, description optimization, and evaluation workflows.

Design and write VS Code custom agent files (.agent.md) following the minimum-sufficient-context spec: scoped tools, structured instructions, hard-enforcement hooks, and handoffs. Use this skill when creating a new custom agent, reviewing an existing .agent.md for quality, deciding an agent's tool set, writing agent body instructions, adding PreToolUse or PostToolUse hooks to an agent, designing an orchestrator-with-subagents team, or adapting the reference spec to a specific project. Covers frontmatter fields, body section ordering, hook input/output contracts, model fallback chains, and the orchestrator/subagent/handoff patterns.

Full 8-part Agno Agent Design Template. Load when filling out, presenting, or reviewing the agent design template.

Write succinct agent notes to minimise context. Use when: reporting on work done, summarising completed tasks, reviewing another agent's output, flagging what was good, what needs fixing, what is incomplete. Triggers: report, summarise work, note findings, review agent output, what was good, what needs improving.