spike
Run a disposable experiment to resolve a specific feasibility question. Use for an explicit spike or when inspection cannot resolve an implementation-blocking uncertainty.
- Installs
- 80
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/petekp/claude-code-setup --skill spike- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads spike automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Spike
State the question, what result would change the decision, and a small experiment budget. Use inspection alone when it can answer the question. A request for a prototype or an estimate does not by itself authorize disposable code or a larger experiment.
Keep experiment code separate from the implementation. Use a temporary directory for self-contained checks. If real project imports are needed, use a task-owned, locally ignored scratch directory or an isolated worktree. Preserve unrelated work and the existing scope and approval boundaries.
Build only enough to measure the unknown. Do not mock the behavior being measured. Include realistic inputs and failure cases when they could change the answer; skip unrelated production polish. Do not use production credentials or mutate shared data without authorization.
Report the observed result, the evidence, its limits, and what it implies for the proposed implementation. A negative result is a valid outcome. Stop when the question is answered or the stated budget is exhausted; do not turn the experiment into an unrequested feature.
Record useful findings before removing task-created scratch code. Treat the implementation as separate work; do not silently promote experimental code. If the user asks to retain the prototype or measurement artifact, preserve it and clearly identify its limitations. Never remove someone else's files, branch, or worktree.
FAQ
What does the spike skill do?
Run a disposable experiment to resolve a specific feasibility question. Use for an explicit spike or when inspection cannot resolve an implementation-blocking uncertainty.
How do I install spike?
Run npx skills add https://github.com/petekp/claude-code-setup --skill spike in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/spike/ (personal) or .claude/skills/spike/ (project).
Which AI agents can use spike?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is spike safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains spike?
It is published by petekp in petekp/claude-code-setup. It has 80 recorded installs.
More from petekp/claude-code-setup
code-comments
petekp/claude-code-setup
Write, review, or remove code comments. Use when adding comments or doc comments, reviewing the comments in a diff, or cleaning up or removing comments.
deep-research
petekp/claude-code-setup
Investigate a question that requires sustained research across sources and produce cited findings. Use for deep research requests; skip ordinary lookups and single-document reviews.
exhaustive-systems-analysis
petekp/claude-code-setup
Open the skill to read its SKILL.md instructions.
typography
petekp/claude-code-setup
Apply professional typography principles to create readable, hierarchical, and aesthetically refined interfaces. Use when setting type scales, choosing fonts, adjusting spacing, designing text-heavy layouts, implementing dark mode typography, or when asked about readability, font pairing, line height, measure, typographic hierarchy, variable fonts, font loading, or OpenType features.
claude-code-audit
petekp/claude-code-setup
Forensic audit of the user's recent Claude Code sessions to surface step-change workflow improvements — not marginal ones. Use when the user asks to "audit my Claude Code sessions", "analyze how I use Claude Code", "find patterns in my usage", "improve my Claude Code workflow", "review my sessions", "find leverage in my setup", or wants to understand where their Claude Code setup is leaking time. Samples dozens of real transcripts, extracts quantitative signal via scripts, uses parallel subagents for deep reads, then synthesizes into a short prioritized report with drafted implementations (new skills, CLAUDE.md rules, hooks, settings diffs) that the user can install directly. Trigger even when the user doesn't say the word "audit" — if they're asking about improving or reviewing their Claude Code habits at scale, use this skill.
literate-guide
petekp/claude-code-setup
Create a narrative guide to a codebase or feature in the style of Knuth's Literate Programming — code and prose interwoven as a single essay, ordered for human understanding rather than compiler needs. Use when the user asks to 'explain this codebase as a story', 'write a literate guide', 'create a narrative walkthrough', 'tell the story of this code', 'Knuth-style documentation', 'weave a guide for this feature', or when they want deep, readable documentation that treats the program as literature. Also trigger when someone wants a document that a thoughtful reader could follow from start to finish and come away understanding both WHAT the code does and WHY every design choice was made.
Popular other skills
hyperframes-cli
heygen-com/hyperframes
The HyperFrames CLI by job - scaffold, check, look at frames, edit the timeline, preview, render locally or in the cloud, publish, project history - plus reading its JSON and recovering from build or render failures.
triage
mattpocock/skills
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
ask-matt
mattpocock/skills
Ask which skill or flow fits your situation. A router over the skills in this repo.
to-questionnaire
mattpocock/skills
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
loop-me
mattpocock/skills
Grill me about specs for the workflows I want to build, within this workspace.