agentleFS
Sign inStart free
kobaltgitkobaltgit/StatCraft/.agents/skills/capsulecraft/SKILL.md

capsulecraft

Skill53 starsChanged 4 days agoApache-2.0View on GitHub

Read, query, and update the CapsuleCraft project knowledge base and tasks for StatCraft.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every module, subsystem, architecture decision, task, and design document is stored as an honest, self-contained RFC 5322 (.eml) capsule …

    line 9
  2. Very specific:

    When exploring the architecture, public APIs, or subsystems of StatCraft.

    line 13
  3. Very specific:

    When checking technical debt, open tasks, and TODOs (tasks_todo.eml).

    line 14
  4. Distinctive:

    When planning new features or cross-module refactorings.

    line 15
  5. Distinctive:

    When saving architectural decisions or agent run artifacts.

    line 16
  6. Very specific:

    If the CapsuleCraft MCP server is running (capsulecraft), use these tools:

    line 19
  7. Distinctive:

    If MCP is not active, you can read the knowledge base directly from the filesystem:

    line 27

≈ “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

CapsuleCraft Knowledge Base Skill for StatCraft

This project is indexed into a local CapsuleCraft knowledge base located in .capsule/. Every module, subsystem, architecture decision, task, and design document is stored as an honest, self-contained RFC 5322 (.eml) capsule with full provenance.

When to use this skill

  • When exploring the architecture, public APIs, or subsystems of StatCraft.
  • When checking technical debt, open tasks, and TODOs (tasks_todo.eml).
  • When planning new features or cross-module refactorings.
  • When saving architectural decisions or agent run artifacts.

Available MCP Tools

If the CapsuleCraft MCP server is running (capsulecraft), use these tools:

  • project_overview: Retrieve the structural overview of modules, subsystems, and metrics.
  • capsule_search: Full-text BM25 search across capsules and code comments.
  • capsule_read: Read a capsule by its Message-ID or file name.
  • capsule_create: Create a new capsule documenting a feature, RFC, or bug analysis.
  • capsule_tasks: List and filter codebase tasks and TODOs.

Direct Capsule Access (Without MCP)

If MCP is not active, you can read the knowledge base directly from the filesystem:

  • Root overview: .capsule/index.eml
  • Subsystems: .capsule/subsystem_*.eml
  • Module capsules: .capsule/module_*.eml
  • Tasks: .capsule/tasks_todo.eml

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