{ "schemaVersion": "1.0", "item": { "slug": "workflows", "name": "Workflows", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/askginadotai/workflows", "canonicalUrl": "https://clawhub.ai/askginadotai/workflows", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/workflows", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=workflows", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/cli-and-definition.md", "references/eval-optimize-and-artifacts.md", "references/polymarket-patterns.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "slug": "workflows", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-11T03:57:26.179Z", "expiresAt": "2026-05-18T03:57:26.179Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=workflows", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=workflows", "contentDisposition": "attachment; filename=\"workflows-1.0.2.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "workflows" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/workflows" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/workflows", "agentPageUrl": "https://openagent3.xyz/skills/workflows/agent", "manifestUrl": "https://openagent3.xyz/skills/workflows/agent.json", "briefUrl": "https://openagent3.xyz/skills/workflows/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "What It Does", "body": "Provides a practical workflow-authoring and operations standard for Gina sandbox automation.\n\nCreates and validates workflow definitions.\nRuns workflows and inspects artifacts/logs.\nApplies a repeatable eval -> optimize -> compare loop.\nUses safe TypeScript/SQL/KV patterns for step logic." }, { "title": "When To Use", "body": "You are creating or maintaining multi-step workflow orchestration.\nYou need reproducible debugging from run artifacts.\nYou want measurable improvements using baseline comparisons." }, { "title": "When Not To Use", "body": "The task is a single action with no orchestration requirement.\nYou only need high-level strategy language without runnable steps.\nYou cannot provide explicit permissions or side effects." }, { "title": "Inputs", "body": "Workflow intent and success criteria.\nTrigger definition and input schema.\nRequired tools/data sources and permission scope.\nOptional baseline run ID for optimization." }, { "title": "Outputs", "body": "Validated workflow definition (.ts).\nRunnable execution with traceable artifacts.\nEvaluation record with baseline comparison.\nClear rollback path for regressions." }, { "title": "Core Commands", "body": "workflow create \nworkflow validate \nworkflow run [--input JSON]\nworkflow status \nworkflow logs [--step ]\nworkflow eval \nworkflow optimize --baseline \nworkflow rollback " }, { "title": "Setup", "body": "Confirm workflow tooling is available (workflow list should succeed).\nScaffold or open the target workflow in /workspace/.harness/workflows/.\nKeep active versions on @latest.ts naming when versioned variants exist.\nValidate before every run: workflow validate .\nFor risky changes, capture a baseline run and eval before editing." }, { "title": "Capability Contract Checklist", "body": "For each workflow entry, explicitly define:\n\nTrigger.\nInputs.\nOutputs.\nSide effects.\nFailure modes.\nPermission scope." }, { "title": "Failure Modes", "body": "Validation failure from malformed step definitions.\nRuntime errors in TS/SQL/Bash steps.\nMissing tool permissions or tool availability.\nData shape changes causing parse/cast failures.\nTimeout/retry exhaustion in external calls." }, { "title": "Security And Permissions", "body": "Use least privilege by step using allow and block.\nDeclare permissions in the submission contract (no wildcard permissions).\nNever include raw secrets in skill text, logs, or examples.\nTreat writes (files, KV, external posts, trading actions) as explicit side effects." }, { "title": "Evidence Expectations", "body": "Setup path that a reviewer can execute in under 10 minutes.\nOne reproducible run artifact or run log example.\nClear statement of expected outputs and acceptable failure behavior." }, { "title": "Optional Directories", "body": "workflows/\n SKILL.md\n references/ # implementation and API details\n scripts/ # optional helpers for repeatable checks\n assets/ # optional diagrams/screenshots" }, { "title": "Reference Material", "body": "Deep technical references are intentionally split out:\n\nreferences/cli-and-definition.md\nreferences/eval-optimize-and-artifacts.md\nreferences/polymarket-patterns.md\n\nUse these as appendices while keeping this file focused on operational usage." } ], "body": "Workflows via Ask Gina Skill\nWhat It Does\n\nProvides a practical workflow-authoring and operations standard for Gina sandbox automation.\n\nCreates and validates workflow definitions.\nRuns workflows and inspects artifacts/logs.\nApplies a repeatable eval -> optimize -> compare loop.\nUses safe TypeScript/SQL/KV patterns for step logic.\nWhen To Use\nYou are creating or maintaining multi-step workflow orchestration.\nYou need reproducible debugging from run artifacts.\nYou want measurable improvements using baseline comparisons.\nWhen Not To Use\nThe task is a single action with no orchestration requirement.\nYou only need high-level strategy language without runnable steps.\nYou cannot provide explicit permissions or side effects.\nInputs\nWorkflow intent and success criteria.\nTrigger definition and input schema.\nRequired tools/data sources and permission scope.\nOptional baseline run ID for optimization.\nOutputs\nValidated workflow definition (.ts).\nRunnable execution with traceable artifacts.\nEvaluation record with baseline comparison.\nClear rollback path for regressions.\nCore Commands\nworkflow create \nworkflow validate \nworkflow run [--input JSON]\nworkflow status \nworkflow logs [--step ]\nworkflow eval \nworkflow optimize --baseline \nworkflow rollback \n\nSetup\nConfirm workflow tooling is available (workflow list should succeed).\nScaffold or open the target workflow in /workspace/.harness/workflows/.\nKeep active versions on @latest.ts naming when versioned variants exist.\nValidate before every run: workflow validate .\nFor risky changes, capture a baseline run and eval before editing.\nCapability Contract Checklist\n\nFor each workflow entry, explicitly define:\n\nTrigger.\nInputs.\nOutputs.\nSide effects.\nFailure modes.\nPermission scope.\nFailure Modes\nValidation failure from malformed step definitions.\nRuntime errors in TS/SQL/Bash steps.\nMissing tool permissions or tool availability.\nData shape changes causing parse/cast failures.\nTimeout/retry exhaustion in external calls.\nSecurity And Permissions\nUse least privilege by step using allow and block.\nDeclare permissions in the submission contract (no wildcard permissions).\nNever include raw secrets in skill text, logs, or examples.\nTreat writes (files, KV, external posts, trading actions) as explicit side effects.\nEvidence Expectations\nSetup path that a reviewer can execute in under 10 minutes.\nOne reproducible run artifact or run log example.\nClear statement of expected outputs and acceptable failure behavior.\nOptional Directories\nworkflows/\n SKILL.md\n references/ # implementation and API details\n scripts/ # optional helpers for repeatable checks\n assets/ # optional diagrams/screenshots\n\nReference Material\n\nDeep technical references are intentionally split out:\n\nreferences/cli-and-definition.md\nreferences/eval-optimize-and-artifacts.md\nreferences/polymarket-patterns.md\n\nUse these as appendices while keeping this file focused on operational usage." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/askginadotai/workflows", "publisherUrl": "https://clawhub.ai/askginadotai/workflows", "owner": "askginadotai", "version": "1.0.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/workflows", "downloadUrl": "https://openagent3.xyz/downloads/workflows", "agentUrl": "https://openagent3.xyz/skills/workflows/agent", "manifestUrl": "https://openagent3.xyz/skills/workflows/agent.json", "briefUrl": "https://openagent3.xyz/skills/workflows/agent.md" } }