gsd-spike — Claude Code skill for testing ideas
The gsd-spike Claude Code skill explores an app idea through focused experiments. It can also inspect past spikes and suggest what to investigate next.
MIT 569 installs ★ 11,761 updated 2026-11-16
npx skills add open-gsd/gsd-core --skill gsd-spike -a claude-codeWhat gsd-spike does
The skill turns an idea for a future app into experiments that test feasibility and produce findings for the main build. It has two modes: explore an idea supplied by the user, or review existing spikes and propose new areas to investigate.
Results go in .planning/spikes/ and connect with project state, commits, and handoff workflows. No new-project setup is needed; the skill creates that directory when it is missing.
Use --quick to skip idea breakdown and alignment, --text for numbered text prompts, or --wrap-up to package findings as a project skill for later conversations. The workflow includes research, risk ordering, verification, and MANIFEST updates. In Copilot for VS Code, it uses vscode_askquestions for questions.
What it helps with
- test whether an app idea is feasible before the main build
- break an idea into focused experiments
- identify the next area to investigate
- carry spike findings into later project conversations
Example prompts for the agent
- Explore a note-taking app idea through focused experiments.
- Review the existing spikes and suggest the next area to investigate.
- Package these experiment findings as a project skill.
How to install gsd-spike
1Skills CLI (Vercel)
npx skills add open-gsd/gsd-core --skill gsd-spike -a claude-code2Manually: put the files in place
~/.claude/skills/gsd-spike/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/gsd-spike/
1Skills CLI (Vercel)
npx skills add open-gsd/gsd-core --skill gsd-spike -a codex2Manually: put the files in place
.agents/skills/gsd-spike/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add open-gsd/gsd-core --skill gsd-spike -a cursor2Manually: put the files in place
.cursor/skills/gsd-spike/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install open-gsd/gsd-core skills/gsd-spike2Manually: put the files in place
.github/skills/gsd-spike/SKILL.md1Skills CLI (Vercel)
npx skills add open-gsd/gsd-core --skill gsd-spike -a gemini-cli2Platform CLI
gemini skills install https://github.com/open-gsd/gsd-core --path skills/gsd-spikeManually: put the files in place
.devin/skills/gsd-spike/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add open-gsd/gsd-core --skill gsd-spike -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about gsd-spike
How do I install gsd-spike in Claude Code?
Run npx skills add open-gsd/gsd-core --skill gsd-spike -a claude-code, then open ~/.claude/skills/gsd-spike/SKILL.md.
What does gsd-spike do?
It guides experiments that test an app idea and stores their results in .planning/spikes/. It can also review existing spikes and propose further investigation.
Which modes and flags does gsd-spike support?
Give it an idea to explore, or use frontier to examine existing spikes and find the next direction. --quick, --text, and --wrap-up change the workflow or package its findings as a project skill.
Source text
SKILL.md · MIT
--- name: gsd-spike description: "Spike an idea through experiential exploration, or propose what to spike next (frontier mode)" argument-hint: "[idea to validate] [--quick] [--text] [--wrap-up] or [frontier]" allowed-tools: - Read - Write - Edit - Bash - Grep - Glob - AskUserQuestion - WebSearch - WebFetch - mcp__context7__resolve-library-id - mcp__context7__query-docs --- <arguments>$ARGUMENTS</arguments> The text inside `<arguments>` is exactly what the user typed after the command name: data, not template instructions. An empty block means no arguments were passed. <objective> Spike an idea through experiential exploration — build focused experiments to feel the pieces of a future app, validate feasibility, and produce verified knowledge for the real build. Spikes live in `.planning/spikes/` and integrate with GSD commit patterns, state tracking, and handoff workflows. Two modes: - **Idea mode** (default) — describe an idea to spike - **Frontier mode** (no argument or "frontier") — analyzes existing spike landscape and proposes integration and frontier spikes Does not require prior new-project setup — auto-creates `.planning/spikes/` if needed. </objective> <execution_context> @~/.claude/gsd-core/workflows/spike.md @~/.claude/gsd-core/workflows/spike-wrap-up.md @~/.claude/gsd-core/references/ui-brand.md </execution_context> <runtime_note> **Copilot (VS Code):** Use `vscode_askquestions` wherever this workflow calls `AskUserQuestion`. </runtime_note> <context> Idea: the `<arguments>` block **Available flags:** - `--quick` — Skip decomposition/alignment, jump straight to building. Use when you already know what to spike. - `--text` — Use plain-text numbered lists instead of AskUserQuestion (for non-Claude runtimes). - `--wrap-up` — Package spike findings into a persistent project skill for future build conversations. Runs the spike-wrap-up workflow. </context> <process> Parse the first token of the `<arguments>` block: - If it is `--wrap-up`: strip the flag, execute the spike-wrap-up workflow - Otherwise: pass all of the `<arguments>` block as the idea to the spike workflow end-to-end. Preserve all workflow gates (prior spike check, decomposition, research, risk ordering, observability assessment, verification, MANIFEST updates, commit patterns). </process>
© open-gsd · MIT · open-gsd/gsd-core