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

scripts/validate_delivery.py

View on GitHub
#!/usr/bin/env python3
from __future__ import annotations
import argparse,json
from pathlib import Path
from semantic_core import load_json, validate_schema, finding
from validate_state import validate as validate_state

REQ_MAP={'satisfied':'satisfied','not_applicable':'not_applicable','deferred':'deferred','blocked':'blocked','superseded':'superseded'}

def validate(state,manifest,root=None):
    skill_root=Path(__file__).resolve().parents[1]
    findings=validate_schema(manifest,skill_root/'schemas/delivery-manifest.schema.json')
    state_findings,registry,closure=validate_state(state,skill_root)
    # include state semantic errors because readiness cannot outrun canonical state
    findings += [f for f in state_findings if f.severity=='ERROR']
    if not isinstance(state,dict) or not isinstance(manifest,dict):
        return findings,{'computed_delivery_ready':False,'epistemic_closure':closure}
    partial=manifest.get('delivery_kind','complete')=='partial'
    for layer,key in (('epistemic','computed_epistemic_closed'),('runtime','computed_runtime_closed')):
        result=closure[layer]
        if result.get('applicable') and not result[key]:
            findings.append(finding('WARNING' if partial else 'ERROR','DELIVERY_CLOSURE_BLOCKED',f'{layer} closure is unresolved: {result["blockers"]}'))
    for collection in ('requirements','acceptance_criteria','artifacts'):
        rows=manifest.get(collection,[])
        if not isinstance(rows,list) or any(not isinstance(x,dict) for x in rows):
            return findings,{'computed_delivery_ready':False,'epistemic_closure':closure}
        ids=[x.get('id') for x in rows]
        if len(ids)!=len(set(ids)):
            findings.append(finding('ERROR','DELIVERY_DUPLICATE_ID',f'duplicate id in {collection}'))
    if manifest.get('work_id')!=state.get('work_id'): findings.append(finding('ERROR','WORK_ID_MISMATCH','manifest.work_id does not match state.work_id'))
    if manifest.get('state_version')!=state.get('state_version'): findings.append(finding('ERROR','STATE_VERSION_MISMATCH','manifest.state_version does not match canonical state_version'))
    state_req={x['id']:x for x in state.get('requirements',[]) if isinstance(x,dict) and x.get('id')}
    man_req={x['id']:x for x in manifest.get('requirements',[]) if isinstance(x,dict) and x.get('id')}
    for rid in man_req:
        if rid not in state_req: findings.append(finding('ERROR','REQ_NOT_CANONICAL',f'{rid} appears in manifest but not canonical state',rid))
    for rid,srec in state_req.items():
        if rid not in man_req: findings.append(finding('ERROR','REQ_MISSING_MANIFEST',f'{rid} missing from delivery manifest',rid)); continue
        m=man_req[rid]; ms=m.get('declared_status'); ss=srec.get('declared_status')
        compatible = (ms=='not_applicable' and ss in ('deferred','superseded')) or ms==ss or (ms=='satisfied' and ss=='satisfied')
        if not compatible: findings.append(finding('ERROR','REQ_STATE_DIVERGENCE',f'{rid}: manifest={ms}, canonical={ss}',rid))
        for ref in m.get('artifact_refs',[]) or []:
            if ref not in registry or registry[ref]['record_type']!='artifact': findings.append(finding('ERROR','REQ_ARTIFACT_REF',f'{rid} artifact_ref {ref} missing/wrong type',rid,ref))
        for ref in m.get('represents',[]) or []:
            if ref not in registry: findings.append(finding('ERROR','REQ_REPRESENTS_REF',f'{rid} represents unknown {ref}',rid,ref))
        for ref in m.get('verification_refs',[]) or []:
            if ref not in registry or registry[ref]['record_type']!='verification': findings.append(finding('ERROR','REQ_VER_REF',f'{rid} verification_ref {ref} missing/wrong type',rid,ref))
            elif registry[ref]['effective_status']!='passed': findings.append(finding('ERROR','REQ_VER_NOT_PASSED',f'{rid} verification {ref} is {registry[ref]["effective_status"]}',rid,ref))
    state_acc={x['id']:x for x in state.get('acceptance_criteria',[]) if isinstance(x,dict) and x.get('id')}
    man_acc={x['id']:x for x in manifest.get('acceptance_criteria',[]) if isinstance(x,dict) and x.get('id')}
    for aid in man_acc:
        if aid not in state_acc: findings.append(finding('ERROR','ACC_NOT_CANONICAL',f'{aid} appears in manifest but not canonical state',aid))
    for aid,srec in state_acc.items():
        if aid not in man_acc: findings.append(finding('ERROR','ACC_MISSING_MANIFEST',f'{aid} missing from delivery manifest',aid)); continue
        ms=man_acc[aid].get('declared_status'); ss=srec.get('declared_status')
        if ms!=ss: findings.append(finding('ERROR','ACC_STATE_DIVERGENCE',f'{aid}: manifest={ms}, canonical={ss}',aid))
        for ref in man_acc[aid].get('artifact_refs',[]) or []:
            if ref not in registry or registry[ref]['record_type']!='artifact': findings.append(finding('ERROR','ACC_ARTIFACT_REF',f'{aid} artifact_ref {ref} missing/wrong type',aid,ref))
            elif registry[ref]['effective_status']!='current': findings.append(finding('ERROR','ACC_ARTIFACT_NOT_CURRENT',f'{aid} artifact {ref} is not current',aid,ref))
        for ref in man_acc[aid].get('verification_refs',[]) or []:
            if ref not in registry or registry[ref]['record_type']!='verification': findings.append(finding('ERROR','ACC_VER_REF',f'{aid} verification_ref {ref} missing/wrong type',aid,ref))
            elif registry[ref]['effective_status']!='passed': findings.append(finding('ERROR','ACC_VER_NOT_PASSED',f'{aid} verification {ref} is {registry[ref]["effective_status"]}',aid,ref))
    state_art={x['id']:x for x in state.get('artifacts',[]) if isinstance(x,dict) and x.get('id')}
    delivered={x.get('id') for x in manifest.get('artifacts',[])}
    for aid,rec in state_art.items():
        if rec.get('materiality')=='material' and rec.get('declared_status') not in ('historical','superseded') and aid not in delivered:
            findings.append(finding('ERROR','ART_MISSING_MANIFEST',f'{aid} material artifact is absent from delivery manifest',aid))
    for m in manifest.get('artifacts',[]) or []:
        aid=m.get('id'); s=state_art.get(aid)
        if not s: findings.append(finding('ERROR','ART_STATE_MISSING',f'manifest artifact {aid} absent from canonical state',aid)); continue
        for key in ('path','role','based_on_state_version'):
            if m.get(key)!=s.get(key): findings.append(finding('ERROR','ART_IDENTITY_MISMATCH',f'{aid} manifest {key} differs from canonical artifact',aid))
        eff=registry.get(aid,{}).get('effective_status')
        required_current=s.get('materiality')=='material' and s.get('declared_status') not in ('historical','superseded')
        if (eff=='current' or required_current) and not m.get('declared_current'):
            findings.append(finding('ERROR','ART_CURRENT_DOWNGRADE',f'{aid} canonical current/required artifact cannot be downgraded by manifest flag',aid))
        if required_current and eff!='current':
            findings.append(finding('ERROR','ART_REQUIRED_NOT_CURRENT',f'{aid} required material artifact is not current',aid))
        if m.get('declared_current') and eff!='current': findings.append(finding('ERROR','ART_NOT_CURRENT',f'{aid} declared current in manifest but effective status is {eff}',aid))
        for ref in m.get('represents',[]) or []:
            if ref not in registry: findings.append(finding('ERROR','ART_REPRESENTS_REF',f'{aid} represents unknown {ref}',aid,ref))
        for ref in m.get('verification_refs',[]) or []:
            if ref not in registry or registry[ref]['record_type']!='verification': findings.append(finding('ERROR','ART_VER_REF',f'{aid} verification_ref {ref} missing/wrong type',aid,ref))
            elif registry[ref]['effective_status']!='passed': findings.append(finding('ERROR','ART_VER_NOT_PASSED',f'{aid} verification {ref} is {registry[ref]["effective_status"]}',aid,ref))
        if required_current and not m.get('path'):
            findings.append(finding('ERROR','ART_PATH_REQUIRED',f'{aid} material current artifact needs a path',aid))
        if root and m.get('declared_current') and m.get('path'):
            p=(Path(root)/m['path']).resolve(); rr=Path(root).resolve()
            try: p.relative_to(rr)
            except ValueError: findings.append(finding('ERROR','ART_PATH_ESCAPE',f'{aid} path escapes root',aid))
            else:
                if not p.exists(): findings.append(finding('ERROR','ART_FILE_MISSING',f'{aid} current artifact file missing: {m["path"]}',aid))
    if partial:
        if state.get('declared_status') in ('closed','delivery_ready'):
            findings.append(finding('ERROR','PARTIAL_FALSE_COMPLETION','partial handoff cannot declare canonical work closed/ready'))
        remaining=set(manifest.get('remaining_obligation_refs',[]))
        obligations={rid for rid,n in registry.items() if n['record'].get('materiality')=='material' and
            n['record_type'] in ('requirement','acceptance_criterion') and n['effective_status'] not in ('satisfied','not_applicable','superseded')}
        if obligations-remaining: findings.append(finding('ERROR','PARTIAL_OMITTED_OBLIGATION','remaining obligations omitted: '+','.join(sorted(obligations-remaining))))
        if remaining-set(registry): findings.append(finding('ERROR','PARTIAL_UNKNOWN_OBLIGATION','unknown remaining obligation references'))
    structurally_ready=not any(f.severity=='ERROR' for f in findings) and not manifest.get('inconsistencies')
    computed_ready=structurally_ready and not partial and not manifest.get('blocking_items')
    if manifest.get('declared_delivery_ready') and not computed_ready: findings.append(finding('ERROR','DECLARED_READY_FALSE','declared_delivery_ready=true but computed_delivery_ready=false'))
    return findings, {'computed_delivery_ready':computed_ready,'computed_task_complete':computed_ready,
        'computed_partial_ready':bool(partial and structurally_ready),'epistemic_closure':closure}

def main():
    ap=argparse.ArgumentParser(); ap.add_argument('state_json'); ap.add_argument('delivery_manifest'); ap.add_argument('--root'); ap.add_argument('--json',action='store_true'); a=ap.parse_args()
    try: s=load_json(Path(a.state_json)); m=load_json(Path(a.delivery_manifest))
    except Exception as e: print('ERROR:',e); return 1
    fs,comp=validate(s,m,Path(a.root) if a.root else None)
    if a.json: print(json.dumps({'findings':[f.as_dict() for f in fs],**comp},indent=2))
    else:
        for f in fs: print(f'{f.severity} [{f.code}] {f.message}')
        print('computed_delivery_ready:',comp['computed_delivery_ready'])
    return 1 if any(f.severity=='ERROR' for f in fs) else 0
if __name__=='__main__': raise SystemExit(main())
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