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/traceability-and-integrity.md

View on GitHub
# Traceability and integrity

**Trigger:** Multiple requirements, durable state, multiple artifacts/representations, controlled changes, audit-sensitive work, delivery packages, or any task where omission/drift would materially matter.

**Reads:** requirements, questions/answers, premises, observations, evidence, hypotheses/uncertainty, inferences, judgments/recommendations, decisions, actions, artifacts, verification/effectiveness records, canonical state version.

**Updates:** typed trace links, requirement coverage, artifact representation contracts, delivery manifest, consistency findings, closure blockers.

**May invalidate:** delivery readiness, artifact-current status, verification, closure.

**Exit:** material records are traceable; requirements are dispositioned; required representations are reconciled; delivery blockers are explicit.

**Related:** [state model and invariants](state-model-and-invariants.md), [synchronization and recovery](synchronization-and-recovery.md), [change governance and effectiveness](change-governance-and-effectiveness.md), [formal review and audit](formal-review-and-audit.md).

**Return:** [root workflow](../SKILL.md) → Reconcile / Completion.

## End-to-end typed traceability

A citation is not the same as full traceability. For durable material work, preserve enough typed links to answer both forward and backward questions:

- Why was this decision/action taken?
- Which evidence and premises support this conclusion?
- Which artifact implements this requirement?
- Which verification proves this requirement/artifact state?
- Which outputs become stale if an upstream requirement changes?

Useful record prefixes are illustrative, not mandatory:

```text
REQ requirement
Q   pivotal question
RAW preserved source/original
OBS observation
EVD evidence record
PRE premise/assumption
HYP hypothesis
UNC uncertainty
INF inference
JDG judgment
REC recommendation
DEC decision
RSK risk
ACT action
ART artifact
VER verification/validation
EFF effectiveness
```

Example:

`REQ-001 → Q-003 → OBS-012/RAW-005 → EVD-021 → PRE-004 → HYP-002 → INF-009 → JDG-003/REC-001 → DEC-004 → ACT-006 → ART-003 → VER-018 → EFF-002`

Not every task needs every type. Use only the granularity needed to prevent material ambiguity or drift.


## Question integrity

Traceability also applies to pure Question / Reasoning work. Preserve enough linkage to answer:

- What original question is this branch answering?
- Which premises/evidence support the final inference or judgment?
- Which uncertainty remains unresolved?
- If the question was decomposed, how do the branch answers recompose into the parent answer?
- Did research drift into an adjacent question?

For complex inquiry, an answer should be able to point back to its parent question and decisive support without requiring a project/change record.

## Raw and derived lineage

Preserve source material as distinct from descendants whenever technically feasible. A transformation creates a new record with `derived_from`, not a silent replacement.

For material source records, useful metadata can include:

`raw_id | source locator | observed/retrieved_at | original name | version hint | visibility | hash/fingerprint when feasible | transformations/descendants`

A hash supports identity/integrity checking; it does not prove the source is truthful. Do not claim immutable storage when the medium cannot enforce it.

## Requirement coverage is separate from research convergence

Before delivery closure, every explicit user requirement and material acceptance condition needs a disposition such as:

`satisfied | not applicable with reason | user-approved deferred | blocked with reason | superseded`

A requirement coverage entry should link to the artifact/action that satisfies it and the verification that checks it when verification is warranted.

A useful conceptual matrix:

`requirement | source | status | artifact/action | verification | notes`

Do not declare delivery complete with a silently missing requirement simply because the substantive analysis is excellent.

## Representation contracts and cross-artifact consistency

Different artifacts may intentionally represent different subsets of the canonical state. Record the role when drift matters:

`artifact | based_on state/version | represents IDs | role(full/summary/implementation/visual/etc.) | current/stale | verification refs`

A summary can omit details without conflict. A contradiction in a shared material value, decision, requirement, version, threshold, or result is a consistency anomaly.

Examples:

```text
canonical threshold = 0.8
code = 0.75          → conflict/blocker
manual = 0.8
```

```text
full report = risks A/B/C/D
slides = risks A/C
slides role = selected-summary → not automatically inconsistent
```

No material artifact may be declared current while it materially conflicts with authoritative state or another required representation without an explicit accepted divergence.

## Delivery manifest

For multi-artifact or handoff work, maintain a compact manifest containing:

- work/state version;
- requirement coverage summary;
- delivered artifacts and their representation roles;
- verification references/status;
- stale or superseded items excluded from delivery;
- unresolved blockers/deferred items;
- whether the package is delivery-ready.

The manifest is a closure aid, not a substitute for inspecting the artifacts. Its `declared_delivery_ready` value is not authoritative: the validator computes readiness by reconciling the manifest against canonical typed state and effective verification/artifact status.

## Integrity gate

Before `delivery_ready = true`, verify as warranted:

- every requirement has an explicit disposition;
- required artifacts exist and are the intended current versions;
- no blocking material stale item is represented as current;
- required verification/validation has passed or is explicitly pending/blocked;
- required cross-artifact representations are reconciled;
- unresolved risks/limitations are disclosed at the level relevant to the user's objective.

An epistemically complete answer can still fail this gate. A delivery can pass this gate while retaining explicitly bounded uncertainty that does not block the user's requested use.

[← Return to root workflow](../SKILL.md)
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