Skip to content
Back to skills

Msd Recovery Protocol

ASecurity

Assemble executable soft-mode recovery evidence for Minimum Stein Discrepancy Estimator proxy experiments.

  • 247 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 9, 2026
tools

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned September 9, 2026

npx -y skills add VectorSpaceLab/AREX-Skill --skill msd_recovery_protocol --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Msd Recovery Protocol?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Msd Recovery Protocol
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vectorspacelab-msd-recovery-protocol/badge)](https://www.skillsdirectory.com/skills/vectorspacelab-msd-recovery-protocol)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: msd_recovery_protocol
description: Assemble executable soft-mode recovery evidence for Minimum Stein Discrepancy Estimator proxy experiments.
---

# MSD Recovery Protocol

Use this skill when recovering Minimum Stein Discrepancy Estimators under bounded runtime. It coordinates the generated Stein-kernel, diffusion-design, and optimiser skills to produce validation-ready recovery artifacts without reading an original source repository.

## Inputs
- Attempt directory containing `module_plan.json`, module docs, generated skills, and `environment/runtime_handoff.json`.
- Recovery mode and target from the run manifest.
- Paths to generated skills that must be invoked or cross-checked.

## Outputs
- `recovery/experiment_plan.md` describing full and proxy options.
- `recovery/source_manifest.json` listing only allowed sources.
- `recovery/logs/generated_skill_invocations.json` with evidence for every core module.
- `recovery/logs/generated_data_item.json` and `recovery/logs/training_trace.json` for reduced proxy evidence.
- `recovery/recovery_result.json` and `recovery/experiment_validation.json`.

## Workflow
1. Confirm full reproduction blockers and soft-mode permission for a declared proxy.
2. Generate a deterministic Student-t location sample matching the module-plan target.
3. Call or import the generated diffusion-design skill to obtain Student-t diffusion diagnostics.
4. Call or import the Stein-kernel skill to evaluate DKSD losses.
5. Call or import the optimiser skill to minimise the empirical loss.
6. Save all logs and mechanism checks before running the recovery validator.

## Validation
Run the bundled `tests/test_msd_recovery_protocol.py` for source-manifest and mechanism-check helpers. The full recovery harness in the attempt directory should additionally run `validate_recovery_experiment.py`.

## Limitations
This skill accepts a declared reduced/proxy target only in soft mode. It must never label proxy evidence as full reproduction of the paper figures.

## Refinement cycle 3 note
A negative source-boundary check rejected an `original_repo` source; keep this check as a required recovery-protocol regression.

Files in this skill

  • SKILL.md2.1 KB
  • scripts/protocol_checks.py1.5 KB
  • tests/test_msd_recovery_protocol.py867 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.