Individual skill

multi-dim-manager

Runs a parameter sweep over many rounds and keeps a hash-based audit trail. Snapshots the declared critical files before and after each round, records parameters, hashes, timestamps and status, and rolls any past round back non-destructively. Fires when a workflow repeats over a Cartesian parameter space or when rollback to an earlier round must stay possible.

skills/multi-dim-manager/SKILL.md

Read pinned source

Source commit b85519b411c909e451c618312fc8fc7edb68050b

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Local scripts
Last checked: Nov 4, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 10
Repository last updated: Nov 6, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-orchestration Repository topic
ai-agent Repository topic
ai-skills Repository topic
bibtex Repository topic
latex Repository topic
llm-agent Repository topic
research-automation-tools Repository topic
skill-orchestration Repository topic
operations Derived category
security Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

.gitignoreasset · 178 bytes
AUTHORS.mddoc · 98 bytes
CHANGELOG.mddoc · 2,762 bytes
CITATION.cffasset · 704 bytes
LICENSEasset · 1,068 bytes
README.mddoc · 1,610 bytes
README_zh.mddoc · 823 bytes
SKILL.mdcore · 3,269 bytes
SKILL.mdcore · 3,269 bytes
SKILL.mdcore · 3,269 bytes
config.example.yamlasset · 1,512 bytes
manifest.jsonasset · 424 bytes
pyproject.tomlasset · 468 bytes
requirements.txtdoc · 193 bytes
run.pyruns · 2,163 bytes
sample_plugin.pyruns · 1,648 bytes
scripts/__init__.pyruns · 324 bytes
scripts/aggregator.pyruns · 2,016 bytes
scripts/audit.pyruns · 3,813 bytes
scripts/common.pyruns · 446 bytes
scripts/config.pyruns · 3,342 bytes
scripts/errors.pyruns · 482 bytes
scripts/executor.pyruns · 4,348 bytes
scripts/param_space.pyruns · 4,268 bytes
scripts/report.pyruns · 1,948 bytes
scripts/rollback.pyruns · 2,257 bytes
scripts/run.pyruns · 10,054 bytes
scripts/snapshot.pyruns · 3,151 bytes
scripts/verify.pyruns · 2,380 bytes
tests/__init__.pyruns · 113 bytes
tests/conftest.pyruns · 2,670 bytes
tests/test_aggregator.pyruns · 1,480 bytes
tests/test_audit.pyruns · 1,752 bytes
tests/test_config.pyruns · 3,467 bytes
tests/test_executor.pyruns · 2,970 bytes
tests/test_param_space.pyruns · 2,710 bytes
tests/test_report.pyruns · 1,513 bytes
tests/test_rollback.pyruns · 2,470 bytes
tests/test_run_cli.pyruns · 9,150 bytes
tests/test_skill_docs.pyruns · 4,210 bytes
tests/test_snapshot.pyruns · 3,124 bytes
tests/test_verify.pyruns · 1,170 bytes

Read excerpt


# multi-dim-manager

Orchestrates repeated rounds: expands the parameter grid, snapshots declared
critical paths, records an auditable round log, and restores any past round.
It **never computes your domain result** — the per-round computation belongs to
your plugin.

- **Stage:** `workspace` · **Sandbox:** no · **Dependencies:** stdlib only (`PyYAML` only for `.yaml` configs; JSON configs need nothing)

## Quick Execution

Run this exact form — do not read the source tree:

```bash