agentleFS
ubie-ossubie-oss/claude-code-plugin/.claude/skills/implement-claude-extensions/SKILL.md

implement-claude-extensions

Skill1 starsChanged 9 months agoApache-2.0View on GitHub

Choose and implement the right Claude extension type by comparing hooks, skills, sub-agents, agent teams, and plugin packaging patterns.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    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:

    Use this umbrella skill to choose the correct extension type and route implementation to the appropriate component skill.

    line 8
  2. Distinctive:

    Core Principle: Start simple. Use the decision framework to score task complexity (0-10) and match to the simplest component type that …

    line 10
  3. Distinctive:

    Validate choice: Ask "Can this be done more simply?"

    line 37
  4. Distinctive:

    Apply lifecycle checks: Follow design → implement → evaluate → verify

    line 41

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Implement Claude Extensions

Use this umbrella skill to choose the correct extension type and route implementation to the appropriate component skill.

Core Principle: Start simple. Use the decision framework to score task complexity (0-10) and match to the simplest component type that meets requirements.

Complexity-Based Selection

ScoreComponent TypeWhen to Use
1-3Simple SkillSingle deterministic task, no branching logic
4-6Workflow SkillMulti-step with some conditional logic
7-8Sub-AgentModel-driven decisions, flexible approach needed
9-10Agent TeamMultiple specialized domains, complex coordination

See references/decision-framework.md for detailed scoring guide.

Comparison

Extension TypeBest ForPrimary ArtifactsComponent Skill
HooksEvent-driven automation/guardrailshooks/hooks.json, hook scripts../implement-hooks/SKILL.md
Agent SkillsReusable task playbooksskills/<name>/SKILL.md../implement-agent-skills/SKILL.md
Sub-AgentsSpecialized delegated rolesagents/*.md../implement-sub-agents/SKILL.md
Agent TeamsCoordinated multi-agent executionteam config + coordination docs../implement-agent-teams/SKILL.md
PluginsPackaging/distribution + wiring.claude-plugin/plugin.json../implement-plugin/SKILL.md

Workflow

  1. Assess complexity: Score task complexity using decision framework (0-10)
  2. Start simple: Choose simplest component type that meets requirements
  3. Validate choice: Ask "Can this be done more simply?"
  4. Identify constraints: Determine specific requirements and boundaries
  5. Plan evaluations: Define 20-50 test cases for validation
  6. Route implementation: Hand off to appropriate component skill
  7. Apply lifecycle checks: Follow design → implement → evaluate → verify

Progressive Disclosure

Best Practices (Anthropic Guidelines)

  • START HERE - Complexity scoring & decision framework: references/decision-framework.md
  • Context management patterns: references/context-management.md
  • Evaluation strategy: references/evaluation-strategy.md

Component Selection

  • Extension comparison details: references/extension-types.md
  • Decision guide: references/when-to-use.md
  • Cross-component patterns: references/cross-component-patterns.md
  • Lifecycle from design to verification: references/extension-lifecycle.md

Component Skills

  • ../implement-hooks/SKILL.md
  • ../implement-agent-skills/SKILL.md
  • ../implement-sub-agents/SKILL.md
  • ../implement-agent-teams/SKILL.md
  • ../implement-plugin/SKILL.md

Sources

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.