Skip to content

zy839971925-zyy/Agent--deep-research-Workflow-Skills / integrations/deepseek-harness/skills/reasoning-workflow

reasoning-workflow

Verified

Default silent workflow for everyday questions, research, writing, design and engineering. Match effort to the request, resolve costly ambiguity, find specialist resources and verify the requested outcome. Explicitly selectable with “调用我的 workflow skills”.

FileKindSize
RELEASE.jsonconfig509 B
SKILL.mdskill md5.4 KB
UPGRADE.mdmarkdown13.1 KB
assets/icon.svgother3.1 KB
families/audit-verification.mdmarkdown1.1 KB
families/core-reasoning.mdmarkdown2.0 KB
families/decision-analysis.mdmarkdown698 B
families/deep-research.mdmarkdown2.2 KB
families/execution-control.mdmarkdown1.5 KB
families/workflow-learning.mdmarkdown500 B
references/change-governance-and-effectiveness.mdmarkdown12.0 KB
references/clarification-gate.mdmarkdown6.9 KB
references/comparative-synthesis.mdmarkdown3.2 KB
references/decision-and-recommendation.mdmarkdown6.6 KB
references/domain-patterns.mdmarkdown4.2 KB
references/engineering-delivery.mdmarkdown2.8 KB
references/evidence-and-provenance.mdmarkdown7.3 KB
references/formal-review-and-audit.mdmarkdown7.4 KB
references/harness-integration.mdmarkdown7.5 KB
references/harness-profiles.mdmarkdown11.8 KB
references/host-adapter.mdmarkdown11.8 KB
references/human-context-and-interpretation.mdmarkdown3.9 KB
references/hypotheses-and-bias-control.mdmarkdown6.2 KB
references/information-target-navigation.mdmarkdown7.4 KB
references/inquiry-and-research.mdmarkdown9.1 KB
references/measurement-and-operationalization.mdmarkdown3.1 KB
references/model-adaptation.mdmarkdown7.5 KB
references/multimodal-and-data.mdmarkdown3.4 KB
references/problem-framing-and-effort.mdmarkdown8.6 KB
references/reasoning-structure-and-decomposition.mdmarkdown5.5 KB
references/relationships-and-systems.mdmarkdown4.2 KB
references/research-modes-and-methods.mdmarkdown17.1 KB
references/research-to-report.mdmarkdown3.8 KB
references/retrieval-and-observation.mdmarkdown14.4 KB
references/runtime-and-delegation.mdmarkdown8.9 KB
references/semantic-state-contract.mdmarkdown5.7 KB
references/specialist-resources.mdmarkdown2.8 KB
references/state-model-and-invariants.mdmarkdown7.1 KB
references/synchronization-and-recovery.mdmarkdown9.6 KB
references/synthesis-execution-and-verification.mdmarkdown6.7 KB
references/task-strategies.mdmarkdown4.9 KB
references/time-scenarios-and-forecasting.mdmarkdown3.6 KB
references/traceability-and-integrity.mdmarkdown6.2 KB
references/ultra-research.mdmarkdown9.1 KB
references/worked-examples.mdmarkdown5.1 KB
references/workflow-learning-and-capa.mdmarkdown4.4 KB
references/writing-for-the-reader.mdmarkdown1.7 KB
routing-index.jsonconfig18.0 KB
schemas/capability-snapshot.schema.jsonconfig1.1 KB
schemas/checkpoint-manifest.schema.jsonconfig5.6 KB
schemas/delivery-manifest.schema.jsonconfig4.9 KB
schemas/dual-verification.schema.jsonconfig2.6 KB
schemas/edge-policy.jsonconfig3.8 KB
schemas/event.schema.jsonconfig1.9 KB
schemas/execution-node-state.schema.jsonconfig2.7 KB
schemas/execution-plan.schema.jsonconfig5.7 KB
schemas/execution-schedule.schema.jsonconfig3.7 KB
schemas/learning-record.schema.jsonconfig4.5 KB
schemas/raw-record.schema.jsonconfig3.3 KB
schemas/review-bundle.schema.jsonconfig1.6 KB
schemas/task-profile.schema.jsonconfig4.2 KB
schemas/work-state.schema.jsonconfig90.9 KB
schemas/worker-proposal.schema.jsonconfig3.1 KB
scripts/build_distribution.pyscript1.7 KB
scripts/check_report_evidence.pyscript3.6 KB
scripts/harness_bridge.pyscript9.2 KB
scripts/host_adapter.pyscript2.1 KB
scripts/learning_core.pyscript6.3 KB
scripts/prepare_task.pyscript2.6 KB
scripts/reference_core.pyscript1.4 KB
scripts/requirements.txtmanifest37 B
scripts/retrieve_learnings.pyscript1.6 KB
scripts/route_resources.pyscript4.1 KB
scripts/route_task.pyscript1.0 KB
scripts/routing_core.pyscript6.5 KB
scripts/runtime_core.pyscript36.4 KB
scripts/semantic_core.pyscript14.9 KB
scripts/validate_delivery.pyexecutablescript10.4 KB
scripts/validate_dual_verification.pyscript3.1 KB
scripts/validate_events.pyscript2.8 KB
scripts/validate_learning.pyscript718 B
scripts/validate_raw.pyscript3.0 KB
scripts/validate_runtime.pyexecutablescript2.5 KB
scripts/validate_state.pyexecutablescript3.3 KB
scripts/validate_workflow.pyscript9.0 KB

routing-index.json

View on GitHub
{
  "schema_version": "1.0",
  "rule": "Related links are navigation hints, never automatic-load instructions. Load references through the current deterministic route and real unresolved gaps; required_reference_ids (including explicit Ultra methods) cannot be dropped by phase limits or missing tags.",
  "families": [
    {
      "id": "core-reasoning",
      "description": "Universal problem framing, decomposition, relationships, causal chains, hypotheses and interpretation."
    },
    {
      "id": "deep-research",
      "description": "Model-driven orientation, evidence needs, retrieval, provenance, freshness and research synthesis."
    },
    {
      "id": "decision-analysis",
      "description": "Objectives, alternatives, measurements, trade-offs and recommendations."
    },
    {
      "id": "execution-control",
      "description": "Plans, schedules, capabilities, workers, state, checkpoint, recovery and replay safety."
    },
    {
      "id": "audit-verification",
      "description": "Contract verification, independent review, closure, effectiveness and workflow adherence."
    },
    {
      "id": "workflow-learning",
      "description": "Post-run CAPA, experience memory, eval-gated learning promotion and rollback. Maintenance plane only."
    }
  ],
  "references": [
    {
      "id": "problem-framing-and-effort",
      "family": "core-reasoning",
      "path": "references/problem-framing-and-effort.md",
      "load_when_tags": [
        "framing",
        "depth",
        "autonomy",
        "clarification",
        "task-profile",
        "representation"
      ],
      "typical_depth": [
        "light",
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 1
    },
    {
      "id": "reasoning-structure-and-decomposition",
      "family": "core-reasoning",
      "path": "references/reasoning-structure-and-decomposition.md",
      "load_when_tags": [
        "decomposition",
        "recomposition",
        "structure",
        "granularity",
        "reasoning-stagnation"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 2
    },
    {
      "id": "relationships-and-systems",
      "family": "core-reasoning",
      "path": "references/relationships-and-systems.md",
      "load_when_tags": [
        "causal-chain",
        "systems",
        "relationships",
        "feedback",
        "mechanism"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "high",
      "default_priority": 2
    },
    {
      "id": "hypotheses-and-bias-control",
      "family": "core-reasoning",
      "path": "references/hypotheses-and-bias-control.md",
      "load_when_tags": [
        "hypotheses",
        "competing-explanations",
        "bias",
        "falsification"
      ],
      "typical_depth": [
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 3
    },
    {
      "id": "human-context-and-interpretation",
      "family": "core-reasoning",
      "path": "references/human-context-and-interpretation.md",
      "load_when_tags": [
        "human-context",
        "interpretation",
        "statement"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 4
    },
    {
      "id": "worked-examples",
      "family": "core-reasoning",
      "path": "references/worked-examples.md",
      "load_when_tags": [
        "examples",
        "workflow-example"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "high",
      "default_priority": 9
    },
    {
      "id": "inquiry-and-research",
      "family": "deep-research",
      "path": "references/inquiry-and-research.md",
      "load_when_tags": [
        "deep-research",
        "evidence-need",
        "research-loop",
        "frame-discovery"
      ],
      "typical_depth": [
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "high",
      "default_priority": 1
    },
    {
      "id": "information-target-navigation",
      "family": "deep-research",
      "path": "references/information-target-navigation.md",
      "load_when_tags": [
        "information-target",
        "problem-decomposition",
        "response-field",
        "search-path-stagnation",
        "research-frontier"
      ],
      "typical_depth": [
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 0
    },
    {
      "id": "retrieval-and-observation",
      "family": "deep-research",
      "path": "references/retrieval-and-observation.md",
      "load_when_tags": [
        "retrieval",
        "orientation-retrieval",
        "evidence-retrieval",
        "observation",
        "web-search",
        "query-strategy",
        "query-reformulation"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 2
    },
    {
      "id": "evidence-and-provenance",
      "family": "deep-research",
      "path": "references/evidence-and-provenance.md",
      "load_when_tags": [
        "evidence",
        "provenance",
        "citation",
        "source-independence"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "high",
      "default_priority": 1
    },
    {
      "id": "time-scenarios-and-forecasting",
      "family": "deep-research",
      "path": "references/time-scenarios-and-forecasting.md",
      "load_when_tags": [
        "forecast",
        "time",
        "scenario",
        "freshness",
        "volatility",
        "forecast-update"
      ],
      "typical_depth": [
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 3
    },
    {
      "id": "multimodal-and-data",
      "family": "deep-research",
      "path": "references/multimodal-and-data.md",
      "load_when_tags": [
        "multimodal",
        "data",
        "files",
        "images",
        "data-generating-process",
        "selection"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 4
    },
    {
      "id": "decision-and-recommendation",
      "family": "decision-analysis",
      "path": "references/decision-and-recommendation.md",
      "load_when_tags": [
        "decision",
        "recommendation",
        "tradeoff",
        "choice",
        "allocation",
        "option-set",
        "preference-uncertainty",
        "robustness",
        "clarification-voi"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "high",
      "default_priority": 1
    },
    {
      "id": "measurement-and-operationalization",
      "family": "decision-analysis",
      "path": "references/measurement-and-operationalization.md",
      "load_when_tags": [
        "measurement",
        "metric",
        "proxy",
        "operationalization",
        "evaluator-validity",
        "measurement-chain"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 2
    },
    {
      "id": "runtime-and-delegation",
      "family": "execution-control",
      "path": "references/runtime-and-delegation.md",
      "load_when_tags": [
        "execution",
        "delegation",
        "swarm",
        "schedule",
        "worker",
        "capability",
        "failure-diagnosis",
        "replanning"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": true,
      "context_cost_class": "high",
      "default_priority": 1
    },
    {
      "id": "synchronization-and-recovery",
      "family": "execution-control",
      "path": "references/synchronization-and-recovery.md",
      "load_when_tags": [
        "checkpoint",
        "resume",
        "recovery",
        "replay",
        "side-effect",
        "checkpoint-alignment"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": true,
      "context_cost_class": "high",
      "default_priority": 1
    },
    {
      "id": "state-model-and-invariants",
      "family": "execution-control",
      "path": "references/state-model-and-invariants.md",
      "load_when_tags": [
        "state",
        "canonical-state",
        "invariants",
        "durable"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": true,
      "context_cost_class": "high",
      "default_priority": 2
    },
    {
      "id": "semantic-state-contract",
      "family": "execution-control",
      "path": "references/semantic-state-contract.md",
      "load_when_tags": [
        "semantic-state",
        "lifecycle",
        "effective-state"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": true,
      "context_cost_class": "high",
      "default_priority": 2
    },
    {
      "id": "traceability-and-integrity",
      "family": "execution-control",
      "path": "references/traceability-and-integrity.md",
      "load_when_tags": [
        "traceability",
        "integrity",
        "event",
        "lineage"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": true,
      "context_cost_class": "medium",
      "default_priority": 3
    },
    {
      "id": "domain-patterns",
      "family": "execution-control",
      "path": "references/domain-patterns.md",
      "load_when_tags": [
        "domain-pattern",
        "implementation-pattern"
      ],
      "typical_depth": [
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 8
    },
    {
      "id": "synthesis-execution-and-verification",
      "family": "audit-verification",
      "path": "references/synthesis-execution-and-verification.md",
      "load_when_tags": [
        "verification",
        "synthesis",
        "closure",
        "artifact-contract",
        "orthogonal-verification"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": true,
      "context_cost_class": "high",
      "default_priority": 1
    },
    {
      "id": "formal-review-and-audit",
      "family": "audit-verification",
      "path": "references/formal-review-and-audit.md",
      "load_when_tags": [
        "audit",
        "review",
        "adherence",
        "dual-review",
        "adversarial-review",
        "reviewer-independence",
        "evaluator-validity",
        "orthogonal-verification"
      ],
      "typical_depth": [
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": true,
      "context_cost_class": "high",
      "default_priority": 1
    },
    {
      "id": "change-governance-and-effectiveness",
      "family": "audit-verification",
      "path": "references/change-governance-and-effectiveness.md",
      "load_when_tags": [
        "change-governance",
        "effectiveness",
        "capa",
        "high-consequence"
      ],
      "typical_depth": [
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 2
    },
    {
      "id": "workflow-learning-and-capa",
      "family": "workflow-learning",
      "path": "references/workflow-learning-and-capa.md",
      "load_when_tags": [
        "learning",
        "capa",
        "regression",
        "self-evolution",
        "maintenance",
        "negative-transfer",
        "applicability"
      ],
      "typical_depth": [
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": true,
      "context_cost_class": "high",
      "default_priority": 1
    },
    {
      "id": "ultra-research",
      "family": "deep-research",
      "path": "references/ultra-research.md",
      "load_when_tags": [
        "ultra",
        "fresh-frame",
        "evidence-ecology",
        "missingness",
        "boundary",
        "research-path-reset",
        "pivotal-claims"
      ],
      "typical_depth": [
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "high",
      "default_priority": 1
    },
    {
      "id": "model-adaptation",
      "family": "core-reasoning",
      "path": "references/model-adaptation.md",
      "load_when_tags": [
        "model-adaptation",
        "gpt-6-plus",
        "codex",
        "compute-allocation",
        "multi-agent",
        "compaction",
        "scaffolding",
        "claude-frontier",
        "harness-adaptation"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 5
    },
    {
      "id": "comparative-synthesis",
      "family": "deep-research",
      "path": "references/comparative-synthesis.md",
      "load_when_tags": [
        "cross-study-comparison",
        "benchmark-comparison",
        "model-comparison",
        "evidence-synthesis"
      ],
      "typical_depth": [
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 3
    },
    {
      "id": "harness-profiles",
      "family": "core-reasoning",
      "path": "references/harness-profiles.md",
      "load_when_tags": [
        "harness-adaptation",
        "codex",
        "claude-code",
        "chatgpt-chat",
        "claude-chat",
        "grok-chat",
        "skill-installation"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 8
    },
    {
      "id": "research-modes-and-methods",
      "family": "deep-research",
      "path": "references/research-modes-and-methods.md",
      "load_when_tags": [
        "empirical-research",
        "real-world-research",
        "technical-research",
        "architecture-research",
        "pre-build",
        "hybrid-research",
        "tradeoff-scenarios"
      ],
      "typical_depth": [
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "medium",
      "default_priority": 4
    },
    {
      "id": "clarification-gate",
      "family": "core-reasoning",
      "path": "references/clarification-gate.md",
      "load_when_tags": [
        "clarification",
        "ambiguous-request",
        "user-question",
        "missing-input",
        "before-asking",
        "grill-me",
        "requirements-interview",
        "costly-ambiguity"
      ],
      "typical_depth": [
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "low",
      "default_priority": 3
    },
    {
      "id": "engineering-delivery",
      "family": "execution-control",
      "path": "references/engineering-delivery.md",
      "load_when_tags": [
        "engineering-delivery",
        "compatibility",
        "release-install",
        "regression"
      ],
      "typical_depth": [
        "light",
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "low",
      "default_priority": 50,
      "on_demand_only": true
    },
    {
      "id": "specialist-resources",
      "family": "core-reasoning",
      "path": "references/specialist-resources.md",
      "load_when_tags": [
        "specialist-resource",
        "design-reference",
        "motion-reference",
        "library-selection"
      ],
      "typical_depth": [
        "light",
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "low",
      "default_priority": 50,
      "on_demand_only": true
    },
    {
      "id": "writing-for-the-reader",
      "family": "core-reasoning",
      "path": "references/writing-for-the-reader.md",
      "load_when_tags": [
        "writing-style",
        "audience",
        "editing-voice"
      ],
      "typical_depth": [
        "light",
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "low",
      "default_priority": 50,
      "on_demand_only": true
    },
    {
      "id": "research-to-report",
      "family": "deep-research",
      "path": "references/research-to-report.md",
      "load_when_tags": [
        "report-synthesis",
        "claim-support",
        "evidence-update"
      ],
      "typical_depth": [
        "light",
        "standard",
        "deep",
        "max",
        "ultra"
      ],
      "machine_enforced": false,
      "context_cost_class": "low",
      "default_priority": 50,
      "on_demand_only": true
    }
  ]
}
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall