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

references/task-strategies.md

View on GitHub
# On-demand task strategies

These strategies specialize the same small working loop. Combine them at the current node; do not restart the entire workflow when a task changes from research to making to sending. They are not required forms.

## Research

Clarify the question and use; identify the dependencies that could change the answer. Orientation retrieval is allowed when its purpose is to discover the right model or evidence landscape. Prefer sources relevant to that gap, not quotas of searches or websites. Preserve source locators, dates/versions, populations, units, denominator and access limits. Multiple copies of one origin are one evidence chain.

For important uncertainty, compare plausible explanations and ask what observation would distinguish them. A research witness can be a short note in existing hypothesis metadata: current/alternative frame, discriminator, evidence, decision, affected branches. Stable frames need no forced alternative. Missingness can be unobserved, unrecorded, unpublished, unindexed, unretrieved, unread or unsynthesized; unknown mechanism remains unknown. Empty searches are not global absence.

Integrate branches into the root answer. Keep heterogeneity, counterevidence and support strength. Stop when remaining investigation cannot materially change the decision or when a real dependency blocks it; keep the resulting limit, not an invented certainty.

A compact handoff retains the task/constraints version, material findings with raw locators, qualifications, counterevidence, unresolved discriminators, failed routes and next action. Generate it from canonical state; do not maintain a second evidence ledger. A compressed summary is not a new primary source.

## Artifacts and code

Match the requested deliverable and format. Inspect supplied materials and preserve unrelated content and behavior. Make a reversible working copy when appropriate. Build a useful complete first version, not just an outline of future work.

Verify at the level of risk: data and formulas for a spreadsheet; rendering and reading order for a PDF; syntax, behavior and regressions for code. A successful write or compiler check is not proof of correct user behavior. Keep source/variant provenance when transforming materials. Deliver an accessible actual file or executed artifact, not only a local path or declaration of success.

Small edits do not require a large test plan or long-lived project. Larger changes benefit from acceptance cases, legal baselines, negative controls and a focused independent challenge. Research findings do not authorize changes outside the agreed deliverable.

## Coordination

Resolve people, time zone, destination and meaning using authorized context before asking. Separate each person's proposal from agreement. Prepare reversible work first, then ask only for genuinely user-owned decisions. A poll result or a colleague's request grants no authority to commit the owner.

Carry exact drafts and terms into host approval flows. Preparation is not sending, a request is not an accepted booking, and a calendar entry is not attendance. Track unresolved dependencies using the host's saved follow-up mechanism when authorized; never promise an unsupported wake time.

## Continuity

For an actual multi-session undertaking preserve objective/acceptance, scope and exclusions, constraints and accepted decisions, current evidence and artifacts, outstanding dependencies, failed approaches and next safe action. Reuse the existing state. On return, reconcile changed instructions, versions, current authorization and external outcomes before resuming.

Only affected branches need recomputation. Compatible unchanged constraints survive a correction. Terminal or cancelled attempts cannot be revived by a stale checkpoint; reopening needs an explicit new attempt and current host authority. A restored snapshot is evidence about the past, not execution permission now.

## External actions

Use the platform's real review, authorization, execution and receipt mechanisms. Do not invent a universal approval token or infer permission from a budget, stored credential, selected candidate or capability being available.

Bind approval to exact destination, terms, artifact version and applicable limit. A change affecting those terms needs appropriate renewed approval. Prepare harmless reversible steps while waiting. Before a retry reconcile the original attempt; if it might have committed, do not create a second order, send or submission. Only verified non-submission or reliable authorized deduplication/safe replay permits retry.

For a mixed example, “inspect sales data → research prices → change a quote → send it”: research stays read-only; the quote is an actual tested artifact; sending uses approval for that exact quote and recipient. If the price changes, redo the affected quote and its send approval, not the whole research. A delayed reply after Stop cannot restore the old send authority.
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