sb-ai-lab/sirin/agent

Claude Code and agent skill by sb-ai-lab/sirin

Trust tier 2
  • community
LLM review pending
Source check pending

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

Use when working in the SIRIN repository to implement, debug, review, or document hallucination and answerability detection code, including probing, judging, uncertainty estimation, feature processors, model adapters, Hydra configs, checkpoint compatibility, Streamlit UI presets, or SIRIN tests.

Install

npx vskill@latest install sb-ai-lab/sirin/agent

SKILL.md

SIRIN Framework

Use this as the entry point. Load only the reference file that matches the task.

First Checks

  • Work from the repo root and pin imports with PYTHONPATH=$PWD; the shared environment may otherwise import another checkout.
  • Prefer existing detector, processor, adapter, logger, splitter, and config patterns before adding anything new.
  • Treat vendored dependencies, config compatibility, and cache behavior as documented in ../reference/pitfalls.md.
  • When changing configs or public imports, update the matching shared reference doc.
  • Keep generated or captured artifacts out of commits unless they are intentional fixtures.

Reference Router

Common Workflows

Change Detection Behavior
  1. Identify the family: probing, judge, or uncertainty.
  2. Read the relevant imports/configs in ../reference/architecture.md and ../reference/configs.md.
  3. Trace the flow through adapter -> feature processor -> detector -> pipeline.
  4. Add one focused check for the behavior you changed.
  5. Run the narrowest relevant test command.
Touch Feature Extraction
  1. Read ../reference/feature-processing.md before choosing side, pooling_type, layers, or attn_implementation.
  2. Follow the cache and attention constraints documented there.
Touch Generation or API Adapters
  1. Keep standard sampling explicit: max_length maps to adapter max_tokens.
  2. Put provider-specific request extensions where ../reference/configs.md says they belong.
  3. Use an integration test only when endpoint shape matters.
Touch Checkpoint Loading
  1. Follow the checkpoint compatibility notes in ../reference/pitfalls.md.
  2. Keep legacy loading behavior covered by a focused test.

Minimum Verification

bash
PYTHONPATH=$PWD python -c "import sirin; print(sirin.__file__)"
PYTHONPATH=$PWD python -m pytest -q tests/ -m 'not integration'
PYTHONPATH=$PWD python -m ruff check <changed-python-files>

Set CUDA_VISIBLE_DEVICES as needed, then run PYTHONPATH=$PWD python -m pytest -q tests/ -m integration only for tests explicitly marked integration.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

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

Source

Popularity

Repository stars
61
Repository forks
3
7-day trend score
21

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/sb-ai-lab/sirin/agent/badge)](https://verified-skill.com/skills/sb-ai-lab/sirin/agent)

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