Run any Skill in Manus with one click

gsd-core

Stars8

Forks1

UpdatedFebruary 12, 2026 at 12:21

Core principles and patterns for the Get Shit Done (GSD) framework. Includes questioning, TDD, verification patterns, and UI brand guidelines.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

hq-opensource

hq-opensource/si-mapper

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

18 files

SKILL.md

readonly

name	gsd-core
description	Core principles and patterns for the Get Shit Done (GSD) framework. Includes questioning, TDD, verification patterns, and UI brand guidelines.

GSD Core Skill

This skill provides the foundational knowledge and patterns for executing the Get Shit Done (GSD) framework.

1. Deep Questioning

Project initialization is dream extraction. Be a thinking partner, not an interviewer.

Start open: Let the user dump their mental model.
Challenge vagueness: Never accept fuzzy answers.
Make abstract concrete: Ask for examples or walkthroughs.
Goal: Enough clarity to write a PROJECT.md that downstream phases can act on.

2. Test Driven Development (TDD)

Use TDD for business logic, API endpoints, and data transformations.

Cycle: RED (failing test) → GREEN (pass) → REFACTOR (cleanup).
Commit Pattern: test(XX-YY): add failing test, feat(XX-YY): implement feature, refactor(XX-YY): cleanup.
Focus: Design quality, not just coverage.

3. Verification Patterns

Existence ≠ Implementation. Check for:

Substantive: Real code, not stubs (TODOs, hardcoded values).
Wired: Proper imports and connections (Component → API → DB).
Functional: Actually works as expected.

4. UI Brand Guidelines

Maintain a premium, consistent look for all GSD-related output.

Banners: Use the ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ style.
Checkpoints: Use explicit boxes for user actions.
Next Up: Always provide a clear instruction for the next step.

5. Git Strategy

Commit outcomes, not process.

Atomic: One commit per task.
Metadata: Unified commits for plan completion.
Handoffs: WIP commits for session continuity.

6. Planning & State

The project's memory is stored in structured Markdown files in .planning/.

PROJECT.md: The permanent context (Core Value, Requirements, Constraints).
ROADMAP.md: The journey (Phases and Plans).
STATE.md: The living memory (Current position, Performance metrics, Session continuity).
PLAN.md: Executable tasks with automated/human checkpoints.
SUMMARY.md: Results, decisions, and tech debt tracking for each plan.

7. Subagents

Detailed agent definitions are located in resources/agents/:

planner.md: Creates executable phase plans.
plan-checker.md: Verifies plan quality before execution.
roadmapper.md: Creates project roadmaps and requirement mappings.
executor.md: Executes plans and manages commits.

More from this repository

same repository

adk-cheatsheet

hq-opensource/si-mapper

MUST READ before writing or modifying ADK agent code. ADK API quick reference for Python — agent types, tool definitions, orchestration patterns, callbacks, and state management. Includes an index of all ADK documentation pages. Do NOT use for creating new projects (use adk-scaffold).

2026-03-118

adk-deploy-guide

hq-opensource/si-mapper

MUST READ before deploying any ADK agent. ADK deployment guide — Agent Engine, Cloud Run, GKE, CI/CD pipelines, secrets, observability, and production workflows. Use when deploying agents to Google Cloud or troubleshooting deployments. Do NOT use for API code patterns (use adk-cheatsheet), evaluation (use adk-eval-guide), or project scaffolding (use adk-scaffold).

2026-03-118

adk-dev-guide

hq-opensource/si-mapper

ALWAYS ACTIVE — read at the start of any ADK agent development session. ADK development lifecycle and mandatory coding guidelines — spec-driven workflow, code preservation rules, model selection, and troubleshooting.

2026-03-118

adk-eval-guide

hq-opensource/si-mapper

MUST READ before running any ADK evaluation. ADK evaluation methodology — eval metrics, evalset schema, LLM-as-judge, tool trajectory scoring, and common failure causes. Use when evaluating agent quality, running adk eval, or debugging eval results. Do NOT use for API code patterns (use adk-cheatsheet), deployment (use adk-deploy-guide), or project scaffolding (use adk-scaffold).

2026-03-118

adk-observability-guide

hq-opensource/si-mapper

MUST READ before setting up observability for ADK agents or when analyzing production traffic, debugging agent behavior, or improving agent performance. ADK observability guide — Cloud Trace, prompt-response logging, BigQuery Agent Analytics, third-party integrations, and troubleshooting. Use when configuring monitoring, tracing, or logging for agents, or when understanding how a deployed agent handles real traffic.

2026-03-118

adk-scaffold

hq-opensource/si-mapper

MUST READ before creating or enhancing any ADK agent project. Use when the user wants to build a new agent (e.g. "build me a search agent") or enhance an existing project (e.g. "add CI/CD to my project", "add RAG").

2026-03-118

name	gsd-core
description	Core principles and patterns for the Get Shit Done (GSD) framework. Includes questioning, TDD, verification patterns, and UI brand guidelines.

GSD Core Skill

This skill provides the foundational knowledge and patterns for executing the Get Shit Done (GSD) framework.

1. Deep Questioning

Project initialization is dream extraction. Be a thinking partner, not an interviewer.

Start open: Let the user dump their mental model.
Challenge vagueness: Never accept fuzzy answers.
Make abstract concrete: Ask for examples or walkthroughs.
Goal: Enough clarity to write a PROJECT.md that downstream phases can act on.

2. Test Driven Development (TDD)

Use TDD for business logic, API endpoints, and data transformations.

Cycle: RED (failing test) → GREEN (pass) → REFACTOR (cleanup).
Commit Pattern: test(XX-YY): add failing test, feat(XX-YY): implement feature, refactor(XX-YY): cleanup.
Focus: Design quality, not just coverage.

3. Verification Patterns

Existence ≠ Implementation. Check for:

Substantive: Real code, not stubs (TODOs, hardcoded values).
Wired: Proper imports and connections (Component → API → DB).
Functional: Actually works as expected.

4. UI Brand Guidelines

Maintain a premium, consistent look for all GSD-related output.

Banners: Use the ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ style.
Checkpoints: Use explicit boxes for user actions.
Next Up: Always provide a clear instruction for the next step.

5. Git Strategy

Commit outcomes, not process.

Atomic: One commit per task.
Metadata: Unified commits for plan completion.
Handoffs: WIP commits for session continuity.

6. Planning & State

The project's memory is stored in structured Markdown files in .planning/.

PROJECT.md: The permanent context (Core Value, Requirements, Constraints).
ROADMAP.md: The journey (Phases and Plans).
STATE.md: The living memory (Current position, Performance metrics, Session continuity).
PLAN.md: Executable tasks with automated/human checkpoints.
SUMMARY.md: Results, decisions, and tech debt tracking for each plan.

7. Subagents

Detailed agent definitions are located in resources/agents/:

planner.md: Creates executable phase plans.
plan-checker.md: Verifies plan quality before execution.
roadmapper.md: Creates project roadmaps and requirement mappings.
executor.md: Executes plans and manages commits.