run-pipeline
Skill304 starsChanged 2 months agoMITView on GitHub
Plan and run coordinated analysis using explicit input bindings, isolated workers, run-local artifacts, and the Python workflow controller.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- harness/harness-skillstheir own version, first seen Nov 1, 2026
- neurospin-projects/2026_bdrabczuk_champollion_mcptheir own version, first seen Nov 1, 2026
- rgoerwit/ai-investment-agenttheir own version, first seen Oct 8, 2026
- Duckz289/Pipeline-to-proposal-Plugin-STANDARDtheir own version, first seen Jul 27, 2026
- bohewu/agents_pipelinetheir own version, first seen Jul 11, 2026
- AlanSyue/my-skillstheir own version, first seen Feb 26, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- harness/harness-skills★ 134same name
- rgoerwit/ai-investment-agent★ 71same name
- AlanSyue/my-skills★ 2same name
- Duckz289/Pipeline-to-proposal-Plugin-STANDARD★ 2same name
- bohewu/agents_pipeline★ 1same name
- neurospin-projects/2026_bdrabczuk_champollion_mcp★ 0same 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 repository65 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- always-compareSkill
- analysis-designSkill
- analyst-coreSkill
- archaeologySkill
- archive-analysisSkill
- auth-preflightSkill
- businessSkill
- causalSkill
- chart-to-driveSkill
- close-the-loopSkill
- codex-reviewSkill
- compare-datasetsSkill
- connect-dataSkill
- connect-snowflakeSkill
- context-compareSkill
- context-traceSkill
- data-inspectSkill
- data-mapSkill
- data-profilingSkill
- data-quality-checkSkill
- datasetsSkill
- distribution-profilerSkill
- evalSkill
- evaluate-graderSkill
- experiment-briefSkill
- experimentSkill
- exploreSkill
- exportSkill
- forecastSkill
- google-doc-exportSkill
- google-slides-exportSkill
- guardrailsSkill
- historySkill
- improve-contextSkill
- knowledge-bootstrapSkill
- log-correctionSkill
- maintain-contextSkill
- metric-specSkill
- metricsSkill
- monitor-evalsSkill
- notion-exportSkill
- paceSkill
- patternsSkill
- question-framingSkill
- question-routerSkill
- reliabilitySkill
- resume-pipelineSkill
- runsSkill
- score-analysisSkill
- session-handoffSkill
- setup-dev-contextSkill
- setup-notionSkill
- setupSkill
- setup-slackSkill
- setup-snowflakeSkill
- srm-checkSkill
- stakeholder-communicationSkill
- stress-testSkill
- switch-datasetSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Do not add presentation work to an analysis-only or validation-only request.
- Very specific: line 14
Read plans.md, agents/registry.yaml, and the selected worker contracts.
- Distinctive: line 16
Do not infer required inputs from whatever happens to exist in global outputs.
- Distinctive: line 35
Never invent missing data, credentials, meaning, or approval.
- Very specific: line 38
When context.question is present, the controller builds a deterministic manifest and bounded bundle for each worker from the frozen run …
- Distinctive: line 45
Use the active project Python environment:
- Distinctive: line 70
After the proposed scope is authorized:
- Distinctive: line 93
Read final status and actual artifacts.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Run an analytical workflow
Choose the amount of work that serves the request. A chart, investigation, validation report, and presentation have different completion conditions. Do not add presentation work to an analysis-only or validation-only request.
Inspect and propose
Read plans.md, agents/registry.yaml, and the selected worker contracts.
The registry declares coordination; contracts declare input requirements.
Do not infer required inputs from whatever happens to exist in global outputs.
Prepare a request JSON under working/requests/ with:
plan: an existing named plan.variables: concrete filename placeholder values.bindings: each worker's input values or explicit producer references.output_paths: exact paths replacing wildcard/dynamic output declarations.external_dependencies: input names replacing omitted producers.approval_gates: required approvals withid,after, andbefore.context: the exact analyticalquestion, plus optionalworker_questionswhen a worker needs a narrower framing.
For produced inputs use {"from": "worker.result"}. The first registered output
is result; later outputs are artifact_2, etc. Inspect the registry before
selecting one. For existing files supply an exact path, computed sha256,
and a purpose explaining why the file suits this question. Evaluate dataset,
scope and age as well: a hash establishes identity, not analytical suitability.
Never invent missing data, credentials, meaning, or approval. Ask only for inputs that cannot be safely supplied from the request and verified context.
When context.question is present, the controller builds a deterministic manifest and bounded
bundle for each worker from the frozen run snapshot. It attaches both as explicit inputs and blocks
on trusted-definition conflicts. The bundle records supply. Workers must cite relevant context item
IDs, and downstream validation still checks whether the work applied them.
Compile before executing
Use the active project Python environment:
import json
from pathlib import Path
from helpers.pipeline.compile_plan import compile_named_plan
from helpers.pipeline.controller import Controller
root = Path.cwd()
request = json.loads(Path("working/requests/request.json").read_text())
definition, inputs = compile_named_plan(root, request)
print(json.dumps(definition, indent=2))Replace the request path with the actual file. Review jobs, input bindings,
handoffs, deliverables and stopping conditions before execution.
dry-run=true ends here without creating a run or launching workers. Compilation
is not model execution or proof of analytical correctness.
For custom workflows use the explicit definition format in
docs/PIPELINE-CONTROLLER.md. A list of worker names alone is not a complete
workflow contract.
Execute through the controller
After the proposed scope is authorized:
run = Controller.create(root, definition, inputs)
print(run.directory)Then invoke python -m helpers.pipeline.controller run EXACT_RUN_DIRECTORY.
The controller uses Claude Code with claude-opus-4-6, a fresh process per job,
normal permissions, and explicit output paths. Never bypass permissions or
silently execute a blocked isolated job inline. Workers must not recursively
invoke this skill or edit controller state.
Code owns readiness, bounded retries, artifact checks, status and completion. Query logging inherits a worker-specific directory. Only validated run-local artifacts enter the handoff ledger. This is logical isolation, not an OS sandbox.
Numeric historical checkpoints in plans are not executable approvals. New gates are explicit. Record an approval only after the named person approves the actual evidence; local actor strings do not authenticate identities.
Inspect and report
Read final status and actual artifacts. An optional failure produces a degraded run, even when a deliverable exists. Missing required evidence is not success. Structural checks do not establish analytical correctness. Apply the relevant analytical methods and preserve limitations.
Presentation workers retain their own chart, storytelling and export standards. This entry point does not impose those deliverables on unrelated plans.
Resume only the explicitly identified run using /resume-pipeline. Do not copy
global artifacts into a run to make it look complete. See
docs/PIPELINE-CONTROLLER.md for migration and current limitations.
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.

