agentleFS
Sign inStart free
ArangoGutierrezArangoGutierrez/claude-toolkit/.claude/skills/eureka/SKILL.md

eureka

Skill4 starsChanged 3 months agoMITView on GitHub

Capture technical breakthroughs as structured documents. Triggered by "breakthrough", "key insight", "document discovery", or /eureka

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. Very specific:

    Optional: If insight implies a new convention, propose update to relevant rules/ file.

    line 44
  2. Distinctive:

    Don't capture routine debugging — that's /reflection

    line 47
  3. Distinctive:

    Don't capture well-documented knowledge

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Eureka — Breakthrough Capture

Capture technical breakthroughs worth remembering across projects.

Bar

"Would this surprise a senior engineer?" Routine solutions are not breakthroughs.

Process

  1. Prompt for details:
    • Problem: What were you trying to solve?
    • Insight: What was the non-obvious realization?
    • Implementation: How did you apply it?
    • Impact: What changed (quantify if possible)?

  2. Write structured document to docs/breakthroughs/YYYY-MM-DD-<slug>.md:

    # [Title]

**Date:** YYYY-MM-DD
**Tags:** [go, k8s, gpu, performance, ...]
**Project:** [name or "cross-project"]

## Problem
## Insight
## Implementation
## Impact

    (Interim location until cross-IDE memory architecture ships)

  3. Optional: If insight implies a new convention, propose update to relevant rules/ file.

Gotchas

  • Don't capture routine debugging — that's /reflection
  • The insight section must be specific enough to be actionable
  • Don't capture well-documented knowledge

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