multi-dim-manager
Skill10 starsChanged 6 days agoMITView on GitHub
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.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- JiamingShi-JsPhys/agent-skillstheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- JiamingShi-JsPhys/agent-skills★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/chelate-shell.mdcCursor rule
- 3d-modelerSkill
- ai-trace-removerSkill
- bibtex-normalizerSkill
- capstone-labmateSkill
- conflict-detectorSkill
- data-profilerSkill
- document-evolution-trackerSkill
- formula-validatorSkill
- fulltext-extractorSkill
- latex-exporterSkill
- literature-retrieverSkill
- longitudinal-analysisSkill
- ml-auditorSkill
- quantitative-validatorSkill
- reference-auditorSkill
- sci-visualizerSkill
- security-guardSkill
- task-organizerSkill
- video-trackerSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
Run this exact form — do not read the source tree:
- Very specific: line 35
Always dryrun first: it prints the full round plan with no side effect.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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 (PyYAMLonly for.yamlconfigs; JSON configs need nothing)
Quick Execution
Run this exact form — do not read the source tree:
python run.py --root <WS> --action dryrun -- --config config.example.yaml- Always
dryrunfirst: it prints the full round plan with no side effect. --configis a workspace-relative or absolute config file (JSON or YAML).- The gate lands in
<WS>/process/gates/multi-dim-manager_<ts>.json.
When to use
- A workflow repeats over a grid of parameters (rounds, seeds, conditions).
- Per-round snapshots of declared critical files must exist before and after each round.
- A full audit trail — parameters, hashes, timestamps, status — must be reproducible.
- The user must be able to roll back to any past round without destroying the live state.
When NOT to use
- A single run with no parameter space — a plain script is enough.
- You want the manager to compute the result: it only orchestrates.
Actions
--action | Does | Extra arguments |
dryrun | Print the round plan, no side effect | --config <cfg> |
run | Execute the sweep | --config <cfg> |
rollback | Restore a past round into a new directory | --config <cfg> --round N [--force] |
summary | Regenerate the round summaries | --config <cfg> |
verify | Check one round's recorded outcome | --config <cfg> --round N |
Hard constraints
- Never compute the result yourself. Domain math belongs in the plugin.
- Snapshot only declared critical paths. A full workdir copy is not what this does.
- Rollback is non-destructive by default. Without
--forcethe live state is only read.
Outputs
<WS>/process/gates/multi-dim-manager_<ts>.json— the gate result.- Per-round snapshot directories and the round log under
process/.
Failure handling
- A plugin exiting
1marks the roundfailed; exit2marks iterror. - A malformed config (missing space, bad YAML, no
{OUT}) aborts before any round runs. - Rolling back to an unrecorded round, or one without a post-snapshot, is refused with a message.
Limitations
- Determinism covers orchestration only; the plugin's own output is its responsibility.
- Files not declared as critical paths are never snapshotted.
.yamlconfigs needPyYAML; JSON configs run on the standard library.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.