# Stream Chain > Stream Chain - Skill: `dnyoussef/stream-chain` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add dnyoussef/stream-chain` - Raw SKILL.md: https://api.skillmd.com/api/skills/dnyoussef/stream-chain/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: DNYoussef (https://skillmd.com/u/dnyoussef) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/dnyoussef/stream-chain --- /*============================================================================*/ /* STREAM-CHAIN SKILL :: VERILINGUA x VERIX EDITION */ /*============================================================================*/ --- name: stream-chain version: 1.0.0 description: | [assert|neutral] Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows [ground:given] [conf:0.95] [state:confirmed] category: workflow tags: - streaming - pipeline - chaining - multi-agent - workflow author: ruv cognitive_frame: primary: aspectual goal_analysis: first_order: "Execute stream-chain workflow" second_order: "Ensure quality and consistency" third_order: "Enable systematic workflow processes" --- /*----------------------------------------------------------------------------*/ /* S0 META-IDENTITY */ /*----------------------------------------------------------------------------*/ [define|neutral] SKILL := { name: "stream-chain", category: "workflow", version: "1.0.0", layer: L1 } [ground:given] [conf:1.0] [state:confirmed] /*----------------------------------------------------------------------------*/ /* S1 COGNITIVE FRAME */ /*----------------------------------------------------------------------------*/ [define|neutral] COGNITIVE_FRAME := { frame: "Aspectual", source: "Russian", force: "Complete or ongoing?" } [ground:cognitive-science] [conf:0.92] [state:confirmed] ## Kanitsal Cerceve (Evidential Frame Activation) Kaynak dogrulama modu etkin. /*----------------------------------------------------------------------------*/ /* S2 TRIGGER CONDITIONS */ /*----------------------------------------------------------------------------*/ [define|neutral] TRIGGER_POSITIVE := { keywords: ["stream-chain", "workflow", "workflow"], context: "user needs stream-chain capability" } [ground:given] [conf:1.0] [state:confirmed] /*----------------------------------------------------------------------------*/ /* S3 CORE CONTENT */ /*----------------------------------------------------------------------------*/ ## Orchestration Skill Guidelines ### When to Use This Skill - **Multi-agent coordination** requiring centralized orchestration - **Complex workflows** with multiple dependent tasks - **Parallel execution** benefiting from concurrent agent spawning - **Quality-controlled delivery** needing validation and consensus - **Production workflows** requiring audit trails and state management ### When NOT to Use This Skill - **Single-agent tasks** with no coordination requirements - **Simple sequential work** completing in <30 minutes - **Trivial operations** with no quality gates - **Exploratory work** not needing formal orchestration ### Success Criteria - [assert|neutral] *All agents complete successfully** with 100% task completion [ground:acceptance-criteria] [conf:0.90] [state:provisional] - [assert|neutral] *Coordination overhead minimal** (<20% of total execution time) [ground:acceptance-criteria] [conf:0.90] [state:provisional] - [assert|neutral] *No orphaned agents** - All spawned agents tracked and terminated [ground:acceptance-criteria] [conf:0.90] [state:provisional] - [assert|neutral] *State fully recoverable** - Can resume from any failure point [ground:acceptance-criteria] [conf:0.90] [state:provisional] - [assert|neutral] *Quality gates pass** - All validation checks successful [ground:acceptance-criteria] [conf:0.90] [state:provisional] ### Edge Cases to Handle - **Agent failures** - Detect and replace failed agents automatically - **Timeout scenarios** - Configure per-agent timeout with escalation - **Resource exhaustion** - Limit concurrent agents, queue excess work - **Conflicting results** - Implement conflict resolution strategy - **Partial completion** - Support incremental progress with rollback ### Guardrails (NEVER Violate) - [assert|emphatic] NEVER: lose orchestration state** - Persist to memory after each phase [ground:policy] [conf:0.98] [state:confirmed] - [assert|neutral] ALWAYS: track all agents** - Maintain real-time agent registry [ground:policy] [conf:0.98] [state:confirmed] - [assert|neutral] ALWAYS: cleanup resources** - Terminate agents and free memory on completion [ground:policy] [conf:0.98] [state:confirmed] - [assert|emphatic] NEVER: skip validation** - Run quality checks before marking complete [ground:policy] [conf:0.98] [state:confirmed] - [assert|neutral] ALWAYS: handle errors** - Every orchestration step needs error handling [ground:policy] [conf:0.98] [state:confirmed] ### Evidence-Based Validation - **Verify all agent outputs** - Check actual results vs expected contracts - **Validate execution order** - Confirm dependencies respected - **Measure performance** - Track execution time vs baseline - **Check resource usage** - Monitor memory, CPU, network during execution - **Audit state consistency** - Verify orchestration state matches reality # Stream-Chain Skill ## Kanitsal Cerceve (Evidential Frame Activation) Kaynak dogrulama modu etkin. Execute sophisticated multi-step workflows where each agent's output flows into the next, enabling complex data transformations and sequential processing pipelines. ## Overview Stream-Chain provides two powerful modes for orchestrating multi-agent workflows: 1. **Custom Chains** (`run`): Execute custom prompt sequences with full control 2. **Predefined Pipelines** (`pipeline`): Use battle-tested workflows for common tasks Each step in a chain receives the complete output from the previous step, enabling sophisticated multi-agent coordination through streaming data flow. --- ## Quick Start ### Run a Custom Chain ```bash claude-flow stream-chain run \ "Analyze codebase structure" \ "Identify improvement areas" \ "Generate action plan" ``` ### Execute a Pipeline ```bash claude-flow stream-chain pipeline analysis ``` --- ## Custom Chains (`run`) Execute custom stream chains with your own prompts for maximum flexibility. ### Syntax ```bash claude-flow stream-chain run [...] [options] ``` **Requirements: /*----------------------------------------------------------------------------*/ /* S4 SUCCESS CRITERIA */ /*----------------------------------------------------------------------------*/ [define|neutral] SUCCESS_CRITERIA := { primary: "Skill execution completes successfully", quality: "Output meets quality thresholds", verification: "Results validated against requirements" } [ground:given] [conf:1.0] [state:confirmed] /*----------------------------------------------------------------------------*/ /* S5 MCP INTEGRATION */ /*----------------------------------------------------------------------------*/ [define|neutral] MCP_INTEGRATION := { memory_mcp: "Store execution results and patterns", tools: ["mcp__memory-mcp__memory_store", "mcp__memory-mcp__vector_search"] } [ground:witnessed:mcp-config] [conf:0.95] [state:confirmed] /*----------------------------------------------------------------------------*/ /* S6 MEMORY NAMESPACE */ /*----------------------------------------------------------------------------*/ [define|neutral] MEMORY_NAMESPACE := { pattern: "skills/workflow/stream-chain/{project}/{timestamp}", store: ["executions", "decisions", "patterns"], retrieve: ["similar_tasks", "proven_patterns"] } [ground:system-policy] [conf:1.0] [state:confirmed] [define|neutral] MEMORY_TAGGING := { WHO: "stream-chain-{session_id}", WHEN: "ISO8601_timestamp", PROJECT: "{project_name}", WHY: "skill-execution" } [ground:system-policy] [conf:1.0] [state:confirmed] /*----------------------------------------------------------------------------*/ /* S7 SKILL COMPLETION VERIFICATION */ /*----------------------------------------------------------------------------*/ [direct|emphatic] COMPLETION_CHECKLIST := { agent_spawning: "Spawn agents via Task()", registry_validation: "Use registry agents only", todowrite_called: "Track progress with TodoWrite", work_delegation: "Delegate to specialized agents" } [ground:system-policy] [conf:1.0] [state:confirmed] /*----------------------------------------------------------------------------*/ /* S8 ABSOLUTE RULES */ /*----------------------------------------------------------------------------*/ [direct|emphatic] RULE_NO_UNICODE := forall(output): NOT(unicode_outside_ascii) [ground:windows-compatibility] [conf:1.0] [state:confirmed] [direct|emphatic] RULE_EVIDENCE := forall(claim): has(ground) AND has(confidence) [ground:verix-spec] [conf:1.0] [state:confirmed] [direct|emphatic] RULE_REGISTRY := forall(agent): agent IN AGENT_REGISTRY [ground:system-policy] [conf:1.0] [state:confirmed] /*----------------------------------------------------------------------------*/ /* PROMISE */ /*----------------------------------------------------------------------------*/ [commit|confident] STREAM_CHAIN_VERILINGUA_VERIX_COMPLIANT [ground:self-validation] [conf:0.99] [state:confirmed]