agentleFS
link7373link7373/agentic-sales-marketing/.claude/skills/experiment/SKILL.md

experiment

Skill1 starsChanged 3 months agoMITView on GitHub

Design, run, and call disciplined experiments — offer variants, message angles, channel tests, price points — one variable at a time with pre-committed decision rules. Run when a question is worth answering with data.

29 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use eval, cost 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.
  • qtzx06Skill

    eval

    Evaluate trained YOLO model accuracy with mAP metrics and per-class error analysis. Identifies failure cases for targeted improvement. Use after training.

    Also in 5 projects that use this

  • maxvaegaSkill

    cost

    Estimate what Claude Cowork / Claude Code conversations would cost if run on the pay-per-token Claude API instead of the subscription. Reports token counts and cache-aware API cost in USD and EUR, for the current conversation or for the whole history (cost per conversation). Trigger when the user asks things like "how much would this conversation cost on the API", "API cost of my Cowork conversations", "token usage / token count", "cost per conversation", "/cost", or wants to compare subscription vs API pricing.

    Also in 3 projects that use this

  • dirienSkill

    decide

    Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.

    Also in 3 projects that use this

  • javatarzSkill

    wiki

    Access and manage the local GitHub Wiki clone. Use this skill when you need to read wiki content (architecture, design docs, guides), update wiki documentation, check wiki status, or push wiki changes. The wiki contains high-level system design and architectural documentation.

    Also in 3 projects that use this

  • HeshamFSSkill

    loop

    Run a command or check on a recurring interval

    Also in 3 projects that use this

  • VercelSkill

    workflow

    Creates durable, resumable workflows using Vercel's Workflow SDK. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of "workflow", "durable functions", "resumable", "workflow sdk", "queue", "event", "push", "subscribe", or step-based orchestration.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 1

    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:

    Pick the highest-leverage question: Test big levers before small ones: offer > headline > audience > channel > button color.

    line 14

“Common” is measured: kept by at least 6 in 10 of the 27 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

/experiment — Test, Don't Argue

Inputs: the question to test (from scorecard findings, a stalled metric, or a strategy assumption), knowledge/experiments/ history (don't rerun settled questions), knowledge/strategy.md. Agents: growth-analyst leads; copywriter/funnel-builder/campaign-manager build variants; tools-operator configures splits. Method: knowledge/methods/funnel-and-measurement.md (experiment sections).

Steps

  1. Pick the highest-leverage question. Test big levers before small ones: offer > headline > audience > channel > button color. At low traffic, favor bold variants (a different angle, not a synonym swap) — subtle differences need volume this business may not have yet.
  2. Write the brief. templates/experiment-brief.md: hypothesis with reasoning, ONE variable, primary metric, minimum sample/duration, and the decision rule — all committed before launch.
  3. Build the variants. Meaningfully different on the one variable, identical elsewhere. Compliance and voice checks apply to variants too.
  4. Configure the split. Tool-native A/B where the platform supports it (email subject splits, page-builder tests); else sequential testing with matched conditions, honestly labeled as weaker evidence.
  5. Run without peeking-to-stop. Monitor for breakage, not for early winners; stopping early on noise is how false lessons get learned. Approval gates apply if variants involve spend/outbound/publishing beyond existing approvals.
  6. Call it by the rule. Adopt / reject / inconclusive. Inconclusive with thin volume → either rerun bigger or accept the default and move on; say which and why.
  7. Bank the learning. The result updates the relevant knowledge file (offer, positioning notes, channel plan) so the lesson persists beyond the experiment log — plus one dated line in the relevant method file's "What we've learned here" section, citing the experiment slug.

Before you start

  1. Required inputs: knowledge/strategy.md approved; knowledge/experiments/ history checked — don't rerun settled questions.
  2. Scan knowledge/decision-log.md for the domain being tested — an experiment that would contradict a recorded decision needs that decision explicitly reopened first.
  3. Gate check: variants involving spend/outbound/publishing beyond existing approvals get gated before launch, not after.

If things go wrong

  • Traffic too low to reach minimum sample in reasonable time → don't run it; recommend a bolder variant or a cheaper evidence source (5 customer conversations beat an underpowered A/B test).
  • The split tool breaks mid-run → stop, assess contamination honestly; a contaminated test is called inconclusive, not salvaged.
  • Result is inconvenient for a recorded decision → report it straight and propose a superseding entry; never bury.

Outputs

A called experiment with its evidence and the adopted change (if any) rolled into the knowledge base. Experiment files: knowledge/experiments/YYYY-MM-<slug>.md. Close with the report per templates/skill-report.md.

Writeback

knowledge/experiments/YYYY-MM-<slug>.md; adopted changes to their home files (knowledge/offer.md, knowledge/channel-plan.md, …); learning line to the relevant knowledge/methods/*.md; the decision to knowledge/decision-log.md.

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.