agentleFS
Sign inStart free
search-atlas-groupsearch-atlas-group/amm-founding-circle/skills/case-study-engine/SKILL.md

case-study-engine

Skill0 starsChanged 5 months agoMITView on GitHub

Discover evidence-backed case-study candidates and draft collateral for human approval without inferring causation.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search supplied redacted results for meaningful, repeatable outcomes.

    line 36
  2. Very specific:

    Create a candidate record using templates/candidate.example.md.

    line 37
  3. Distinctive:

    Do not infer causation from before/after change alone.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Case-study engine

Purpose

Find repeatable client outcomes, assemble the evidence, and draft a case study that marketing or sales can use after approval. This is not a report generator; it is an evidence and permission workflow.

Required evidence

  • Baseline and comparison period.
  • Observed change and exact source.
  • Intervention or scope delivered.
  • Attribution limits and plausible alternatives.
  • Client identity and permission status.
  • Reviewer and publication decision.

Method

  1. Search supplied redacted results for meaningful, repeatable outcomes.
  2. Create a candidate record using templates/candidate.example.md.
  3. Separate observed facts from interpretation.
  4. Draft a proof story using report-writer or html-reports only after the evidence record is reviewable.
  5. Route client naming, publication, outbound sharing, and sales use to a named human approver.

Guardrails

Do not infer causation from before/after change alone. Do not expose a client, publish, or send collateral automatically. Missing evidence remains unknown.

Evidence: transcript JSON i segments 459–468.

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