yyt-2378/automat/confidence-estimation

Claude Code and agent skill by yyt-2378/automat

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Add, run, or debug uncertainty and confidence estimation in the agent_qwen workflow. Use when integrating structure_recongnition/confidence_estimation.py, generating per-atom/lattice confidence reports, or adding confidence artifacts to agent_qwen harness outputs.

Install

npx vskill@latest install yyt-2378/automat/confidence-estimation

SKILL.md

Confidence Estimation

Use confidence_estimation_tool for uncertainty quantification in the agent_qwen workflow.

Runtime Surface

  • Wrapper: agent_qwen/runtime_skills.py::_run_confidence
  • Source implementation: structure_recongnition/confidence_estimation.py
  • Harness insertion point: after stem2cif_tool in classic workflow, after

direct_reconstruct_tool in direct workflow

Inputs

  • image_path: denoised STEM image, usually recon_png
  • elements: element symbols from user or template matching
  • pixel_size: default 0.10
  • output: JSON report path

Outputs

Return and preserve:

  • confidence_report
  • global_confidence
  • summary

Treat this as an analysis artifact, not as a model checkpoint.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
84
Repository forks
9
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/yyt-2378/automat/confidence-estimation/badge)](https://verified-skill.com/skills/yyt-2378/automat/confidence-estimation)

Something wrong with this skill or its page? Tell us.