agentleFS
Sign inStart free
whoaskedssselerywhoaskedssselery/claude-workspace/skills/formats/spike/SKILL.md

spike

Skill0 starsChanged 4 months agoMITView on GitHub

Optional add-on that relaxes the usual rigor for a specific piece of throwaway/exploratory work — trying an idea, testing whether an approach is feasible, a quick proof of concept. Deliberately loosens commit-discipline and health-review's normal cadence for the current work; use it explicitly, not as a standing default.

54 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use competitor-news-monitor, blocked-page-recovery and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • aivrarSkill

    competitor-news-monitor

    Watch named companies for material news; cited digests.

    Also in 6 projects that use this

  • aivrarSkill

    blocked-page-recovery

    Recover blocked/paywalled/WAF'd pages via fallbacks.

    Also in 6 projects that use this

  • john-data-chenSkill

    teams-meeting-pipeline

    Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.

    Also in 8 projects that use this

  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 5 projects that use this

  • Tommy-ywSkill

    songwriting-and-ai-music

    Songwriting craft, AI music generation prompts (Suno focus), parody/adaptation techniques, phonetic tricks, and lessons learned. These are tools and ideas, not rules. Break any of them when the art calls for it.

    Also in 8 projects that use this

  • mae616Skill

    p5js

    p5.js（クリエイティブコーディング）のProcessing由来「コードでスケッチ」思想を軸に、setup/drawループ・座標系・インタラクション・パフォーマンス最適化を整理する。p5.js、Processing、クリエイティブコーディング、ジェネラティブアート、インタラクティブ表現、ビジュアルプログラミング、Canvas描画、パーティクル、フラクタル、ノイズ表現に関する相談で必ず使うこと。ユーザーが「コードでアート」「動くビジュアル」「インタラクティブな描画」と言った場合にも適用する。

    Also in 8 projects that use this

  • +4 more from aivrar

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 50 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write the fastest path to a working answer, even if it's ugly, hardcoded, or skips error handling that production code would need.

    line 20
  2. Distinctive:

    Commit in whatever chunks are convenient — a single messy commit for the whole spike is fine.

    line 22
  3. Distinctive:

    Leave TODOs and rough edges in place rather than polishing code that may get thrown away.

    line 23
  4. Distinctive:

    Keep the spike scoped to the question being asked.

    line 29
  5. Distinctive:

    When done, offer a one-line summary of the finding and a short list of what a real implementation would still need.

    line 41

“Common” is measured: kept by at least 6 in 10 of the 50 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Spike

When to attach this

The goal right now is to find out whether something works or is worth doing — not to ship it. A spike answers a question fast; production code answers it correctly, completely, and durably. Attach this skill for the former.

This is a deliberate, temporary relaxation of the project's normal defaults (commit-discipline, health-review), not a replacement for them. Once the spike answers its question, the follow-up work to make it real should drop this skill.

Responsibilities

Claude MAY

  • Write the fastest path to a working answer, even if it's ugly, hardcoded, or skips error handling that production code would need.
  • Skip tests unless they're the fastest way to check the idea itself.
  • Commit in whatever chunks are convenient — a single messy commit for the whole spike is fine.
  • Leave TODOs and rough edges in place rather than polishing code that may get thrown away.

Claude MUST

  • State plainly, at the point the spike is judged "done," what it proved or disproved and what was deliberately skipped to get there (error handling, edge cases, tests, cleanup).
  • Flag clearly before this code gets merged into main or relied on as if it were production-ready — a spike answering "yes, this approach works" is not the same as it being ready to ship.
  • Keep the spike scoped to the question being asked; don't quietly expand it into a full feature build.

Claude MUST NOT

  • Present spike code as complete or production-ready.
  • Silently apply the project's usual health-review cadence or commit-discipline strictness to this work — that defeats the point of moving fast; the trade-off is temporary and explicit, not permanent.

Working Style

  • Optimize for "do I now know the answer to my question," not for code quality.
  • When done, offer a one-line summary of the finding and a short list of what a real implementation would still need.

Collaboration

Temporarily overrides the emphasis of commit-discipline and health-review for this specific work — not a permanent replacement for either.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free