smartsnap-agents

Shift agent verification from post-hoc external judgment to proactive in-situ self-evidence curation. Agents generate atomic evidence tuples during execution, guided by 3C principles (Completeness, Co

SKILL.md

GitHub

Overview

SmartSnap enables agents to prove their success rather than waiting for external verification.

Core Technique

3C Evidence Principles:

evidence = agent.gather_evidence(
    completeness=include_all_pivotal_actions,
    conciseness=minimize_redundancy,
    creativity=generate_additional_proof_actions
)

Evidence Definition: Atomic (action, observation) tuples—objective facts.

When to Use

Use when: Agent verification critical, reducing cognitive load, dense learning signals.

References

  • Proactive evidence gathering
  • Atomic evidence definition
  • Structured verifier feedback

Related in other

limits-colimits

Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context polluti...

by parcadei
3,392

ddttom-allaboutv2-claude-skills-block-collection-and-party

The Block Collection and Block Party are repositories for existing AEM blocks, build tools, code snippets, integration p...

by mattnigh
20

nodnarbnitram-claude-code-extensions-claude-skills-esphome-confi

This skill should be used when the user asks to "create an esphome config", "set up an esp32 device", "configure esphome...

by mattnigh
20