orchestration-workflows
Skill1 starsChanged 5 months agoMITView on GitHub
Define and execute multi-stage development workflows with quality gates at each stage, so complex work moves through explicit plan, implement, review, verify, and handoff checkpoints instead of a single unstructured pass. Use this skill for complex features, security-sensitive changes, multi-agent coordination, high-risk refactors, release preparation, or any task where a simple single-pass workflow is insufficient. Prefer it when several agents or roles must coordinate around artifacts and gating evidence.
In this repository117 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- advanced-orchestrationSkill
- architect-agentSkill
- implementer-agentSkill
- quality-councilSkill
- reviewer-agentSkill
- tester-agentSkill
- writer-critic-pairSkill
- authoring-skillsSkill
- api-endpoint-qualitySkill
- async-job-qualitySkill
- auth-qualitySkill
- db-migration-qualitySkill
- frontend-state-qualitySkill
- acceptance-criteriaSkill
- adaptive-flowSkill
- adaptive-prompt-selectionSkill
- adversarial-code-reviewSkill
- architecture-decision-recordsSkill
- brainstormingSkill
- brownfield-spec-enhancementSkill
- bug-fix-lifecycleSkill
- checkpoint-validationSkill
- cicd-integrationSkill
- clarify-before-codeSkill
- claude-code-hooks-packSkill
- code-context-packSkill
- code-intelligence-reviewSkill
- context-policySkill
- context-rich-implementationSkill
- crash-proof-planningSkill
- critique-pass-protocolSkill
- dependency-aware-task-orderingSkill
- deprecation-migrationSkill
- disciplined-diagnosisSkill
- docs-authorSkill
- executing-plansSkill
- external-skillSkill
- finishing-a-development-branchSkill
- git-guardrailsSkill
- goal-driven-executionSkill
- grill-user-before-buildingSkill
- guard-bypass-protocolSkill
- improve-codebase-architectureSkill
- incremental-reviewSkill
- issue-slicingSkill
- lessons-learned-dbSkill
- loop-engineeringSkill
- model-aware-configSkill
- model-weakness-memorySkill
- multi-repo-learningSkill
- plan-driven-executionSkill
- plan-from-specSkill
- prd-from-contextSkill
- project-constitutionSkill
- prompt-architectureSkill
- prototype-before-commitmentSkill
- quality-engineSkill
- quality-execution-contractSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Use this skill for complex features, security-sensitive changes, multi-agent coordination, high-risk refactors, release preparation, or any …
≈ “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
Skill: Orchestration Workflows
Purpose
Define and execute multi-stage development workflows with quality gates at each stage, so complex work moves through explicit plan, implement, review, verify, and handoff checkpoints instead of a single unstructured pass.
When to use
Use this skill for complex features, security-sensitive changes, multi-agent coordination, high-risk refactors, release preparation, or any task where a simple single-pass workflow is insufficient. Prefer it when several agents or roles must coordinate around artifacts and gating evidence.
Inputs
- Workflow definition: a JSON workflow file conforming to
schemas/orchestration-workflow.json. - Task context: requirements, acceptance criteria, constraints, and relevant repository context.
- Agent assignments: named roles for stages such as architect, engineer, reviewer, tester, debugger, or orchestrator.
- Quality config: gate manifest, quality engine settings, validation expectations, and any project-specific overrides.
Outputs
- Ordered stage results with pass, fail, blocked, or skipped status.
- Gate results per stage with required-for-advance decisions.
- Stage artifacts such as plans, code changes, reviews, verification reports, and handoff summaries.
- Final orchestration report under
docs/reports/orchestration/.
Workflow
- Select a workflow template from
templates/workflow-*.jsonor create a custom workflow definition. - Customize stages for the task: stage IDs, roles, inputs, outputs, timeouts, retry policy, and gate references.
- Assign agents to each stage and confirm each agent understands its expected inputs and outputs.
- Execute stages sequentially using
scripts/orchestrate-workflow.mjs --workflow <path>or thevibe-orchestratecommand. - Enforce gates at each stage. Required gates block advancement when they fail; advisory or warning gates produce evidence and risk notes.
- Generate a final summary report with stage outcomes, blockers, gate evidence, and handoff notes.
- Handoff to the next agent, reviewer, or maintainer with the report and all required artifacts.
Failure modes
- Workflow template does not match task risk, causing either under-gating or excessive ceremony.
- Stage outputs are not produced, leaving downstream agents without enough context.
- Required gates are marked advisory or optional and real blockers are missed.
- Gate failures are bypassed without documented risk acceptance.
- Agent role ownership is ambiguous and work stalls between stages.
- Reports are generated but not reviewed before merge or handoff.
Verification checklist
- Workflow file exists and matches
schemas/orchestration-workflow.json. - Each stage has a clear owner role, expected inputs, and expected outputs.
- Required gates are appropriate for the stage and task risk.
- Blocking gate failures stop advancement and include remediation guidance.
- Optional stages are intentionally marked and safe to skip.
- Final report is written to
docs/reports/orchestration/and included in the handoff.
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.

