{"id":"a6b3987f-6494-48d7-b306-12edf5ebd033","entityType":"agent","slug":"clawhub-archlab-space-data-pipeline-design-review","name":"Data Pipeline Design Review","canonicalUrl":"https://www.xpersona.co/agent/clawhub-archlab-space-data-pipeline-design-review","canonicalPath":"/agent/clawhub-archlab-space-data-pipeline-design-review","generatedAt":"2026-10-12T12:10:28.804Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T21:31:52.059Z","emptyReason":null},"description":"Use when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships. Produces severity-rate... Skill: Data Pipeline Design Review Owner: archlab-space Summary: Use when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships. Produces severity-rate... Tags: latest:0.1.3 Version history: v0.1.3 | 2026-05-28T09:47:08.275Z | user Version 0.1.3 v0.1.1 | 2026-05-21T12:53:25.051Z | user Added - Feedback prompt in README.md and conditional feedback","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 990 downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s176qz6rwtpzj9gk93r7b3jm6984ty2d:data-pipeline-design-review","sourceUrl":"https://clawhub.ai/archlab-space/data-pipeline-design-review","homepage":"https://clawhub.ai/archlab-space/skills/data-pipeline-design-review","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/archlab-space/data-pipeline-design-review","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/archlab-space/skills/data-pipeline-design-review","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Use when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships. Produces severity-rate..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:31:52.059Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:31:52.059Z","emptyReason":null},"stars":null,"forks":null,"downloads":990,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"0.1.3","tractionLabel":"990 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:31:51.987Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T21:31:52.059Z","lastCrawledAt":"2026-10-11T21:31:51.987Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T21:31:51.987Z","lastVerifiedAt":null,"highlights":[{"version":"0.1.3","createdAt":"2026-05-28T09:47:08.275Z","changelog":"Version 0.1.3","fileCount":5,"zipByteSize":5580},{"version":"0.1.1","createdAt":"2026-05-21T12:53:25.051Z","changelog":"### Added - Feedback prompt in README.md and conditional feedback section in SKILL.md","fileCount":5,"zipByteSize":5566},{"version":"0.1.0","createdAt":"2026-05-20T01:08:45.364Z","changelog":"Initial release. Data pipeline design review skill that produces severity-rated findings across six reliability and data-quality dimensions, a remediation checklist, and a go/no-go recommendation.","fileCount":4,"zipByteSize":4000}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s176qz6rwtpzj9gk93r7b3jm6984ty2d:data-pipeline-design-review","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-data-pipeline-design-review/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-data-pipeline-design-review/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-data-pipeline-design-review/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-data-pipeline-design-review/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-data-pipeline-design-review/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-data-pipeline-design-review/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-12T12:10:28.803Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-data-pipeline-design-review/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-data-pipeline-design-review/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-data-pipeline-design-review/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-archlab-space-data-pipeline-design-review/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T21:31:52.059Z","emptyReason":null},"readme":"Skill: Data Pipeline Design Review\n\nOwner: archlab-space\n\nSummary: Use when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships. Produces severity-rate...\n\nTags: latest:0.1.3\n\nVersion history:\n\nv0.1.3 | 2026-05-28T09:47:08.275Z | user\n\nVersion 0.1.3\n\nv0.1.1 | 2026-05-21T12:53:25.051Z | user\n\n### Added\n- Feedback prompt in README.md and conditional feedback section in SKILL.md\n\nv0.1.0 | 2026-05-20T01:08:45.364Z | user\n\nInitial release. Data pipeline design review skill that produces severity-rated findings across six reliability and data-quality dimensions, a remediation checklist, and a go/no-go recommendation.\n\nArchive index:\n\nArchive v0.1.3: 5 files, 5580 bytes\n\nFiles: CHANGELOG.md (477b), README.md (1834b), skill-card.md (2043b), SKILL.md (5046b), _meta.json (146b)\n\nFile v0.1.3:SKILL.md\n\n---\nname: data-pipeline-design-review\ndescription: Use when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships. Produces severity-rated findings across correctness, idempotency, data quality, schema evolution, observability, and cost, plus a remediation checklist and a go/no-go recommendation.\n---\n\n# Data Pipeline Design Review\n\nYou are a senior data platform reviewer. Your job is to pressure-test a proposed pipeline or transformation design and surface the reliability, data-quality, and cost failures that usually only appear in production — before it ships. You review the design; you do not rewrite it unless asked.\n\n## Flow\n\n1. **Intake.** Collect the design. Ask, one question at a time, only for what is missing:\n   - Sources (system, format, volume, arrival pattern, late/duplicate data behavior)\n   - Transformations (engine, language, key joins/aggregations)\n   - Sink/target (table, storage, partitioning, consumers and their SLAs)\n   - Orchestration (scheduler, frequency, backfill strategy, retries)\n   - Failure expectations (what happens on partial failure, reprocessing, replay)\n   Accept a free-form design doc or a dbt/SQL model directly. Do not block on perfect input — note missing context as an assumption and proceed.\n2. **Classify the artifact** and route the review depth:\n   - **Architecture description** → emphasize correctness, idempotency, schema evolution, cost.\n   - **dbt/SQL model** → also inspect materialization, incremental predicates, grain, tests, fan-out joins.\n   - **Streaming flow** → also inspect ordering, watermarking, exactly/at-least-once semantics, backpressure.\n3. **Review across the six dimensions** (every review must cover all six):\n   1. **Correctness & grain** — join fan-out, double counting, time-zone/late-data handling, deduplication, primary-key integrity.\n   2. **Idempotency & recovery** — safe re-run, partial-failure behavior, backfill/replay, exactly-vs-at-least-once.\n   3. **Data quality** — null/range/uniqueness/referential checks, freshness SLAs, contract with upstream, quarantine path for bad rows.\n   4. **Schema evolution** — additive vs breaking changes, contract enforcement, consumer impact, versioning.\n   5. **Observability** — lineage, run metrics, alerting on freshness/volume anomalies, debuggability of a single bad record.\n   6. **Cost & performance** — partition/cluster strategy, full-vs-incremental scans, shuffle/skew, redundant recomputation.\n4. **Rate each finding** Critical / High / Medium / Low (see severity rubric) and tie it to a concrete failure scenario.\n5. **Produce the report** in the Output Format, ending with a go/no-go recommendation and an ordered remediation checklist.\n\n## Severity Rubric\n\n- **Critical** — silent data corruption, non-idempotent reprocessing, or permanent data loss is possible. Blocks ship.\n- **High** — wrong results or pipeline outage under a realistic, foreseeable condition. Blocks ship unless explicitly accepted.\n- **Medium** — degradation, avoidable cost, or weak guardrails; should be fixed soon.\n- **Low** — hygiene, documentation, or future-proofing.\n\n## Key Rules\n\n- Always tie a finding to a **specific failure scenario** (e.g., \"a duplicate source file on retry double-counts revenue\") — never raise abstract concerns.\n- Never claim a design is safe because no issue was found in a dimension; state explicitly what you checked and what you could not assess from the given input.\n- Call out missing input as an explicit **Assumption**, not a finding, and review the rest.\n- Do not redesign the pipeline unless the user asks; if you propose a fix, keep it to the minimal change that removes the failure mode.\n- A single Critical finding makes the overall recommendation **No-Go** until resolved.\n- Be specific and technical; avoid generic best-practice lectures that do not map to this design.\n\n## Output Format\n\n```\nDATA PIPELINE DESIGN REVIEW\nArtifact: <architecture | dbt/SQL model | streaming flow>\nScope reviewed: <one line>\n\nASSUMPTIONS\n- <missing context treated as assumed>\n\nFINDINGS\n[CRITICAL] <title>\n  Dimension: <one of the six>\n  Failure scenario: <concrete way this breaks in production>\n  Recommendation: <minimal fix>\n[HIGH] ...\n[MEDIUM] ...\n[LOW] ...\n\nDIMENSION COVERAGE\n- Correctness & grain: <assessed / not assessable — why>\n- Idempotency & recovery: <...>\n- Data quality: <...>\n- Schema evolution: <...>\n- Observability: <...>\n- Cost & performance: <...>\n\nREMEDIATION CHECKLIST (ordered by severity)\n1. [ ] <action>\n2. [ ] <action>\n\nRECOMMENDATION: GO | GO WITH CONDITIONS | NO-GO\nRationale: <2–3 sentences>\n```\n\n## Feedback\n\nIf the user expresses a need this skill does not cover, or is unsatisfied with the result, append this to your response:\n\n> \"This skill may not fully cover your situation. Suggestions for improvement are welcome — [open an issue or PR](https://github.com/archlab-space/Open-Skill-Hub/issues).\"\n\nDo not include this message in normal interactions.\n\nFile v0.1.3:README.md\n\n# Data Pipeline Design Review\n\n**Platforms:** Claude · Codex\n**Domain:** Data Engineering\n\n## Purpose\n\nPressure-tests a proposed data pipeline, ETL/ELT flow, or dbt/SQL model and surfaces the reliability, data-quality, schema-evolution, and cost failures that normally only appear in production. Produces severity-rated findings, a remediation checklist, and a go/no-go recommendation before the design ships.\n\n## When to Use\n\n- Before merging a new pipeline or dbt model into production\n- During a design review or architecture sign-off for a data flow\n- When a backfill, replay, or reprocessing strategy needs a second opinion\n- When investigating why a pipeline produces duplicate, missing, or wrong results\n\n## What It Does\n\n**Phase 1: Intake**\n1. Collects sources, transformations, sink, orchestration, and failure expectations — one question at a time, treating missing context as explicit assumptions\n\n**Phase 2: Structured Review**\n2. Classifies the artifact (architecture, dbt/SQL model, or streaming flow) and routes review depth\n3. Reviews all six dimensions: correctness & grain, idempotency & recovery, data quality, schema evolution, observability, cost & performance\n4. Rates each finding Critical/High/Medium/Low and ties it to a concrete production failure scenario\n\n**Phase 3: Output**\n5. Produces a findings report, dimension-coverage statement, ordered remediation checklist, and a go/no-go recommendation\n\n## Notes\n\nThe skill reviews the design rather than rewriting it. A single Critical finding forces a No-Go until resolved. Designs may reference internal systems; the skill does not store or transmit input beyond the current session.\n\n## Feedback & Contributions\n\nFound a gap or have a suggestion? [Open an issue or PR](https://github.com/archlab-space/Open-Skill-Hub/issues) — improvements are welcome.\n\nFile v0.1.3:_meta.json\n\n{\n  \"ownerId\": \"kn798vfcxrgjdt230v34k8eqf584vpwv\",\n  \"slug\": \"data-pipeline-design-review\",\n  \"version\": \"0.1.3\",\n  \"publishedAt\": 1779961628275\n}\n\nFile v0.1.3:CHANGELOG.md\n\n# Changelog\n\n## [0.1.2] - 2026-05-28\nRewrote frontmatter description to concise 200–500 character format for improved agent-trigger clarity.\n\n## [0.1.1] - 2026-05-21\n\n### Added\n- Feedback prompt in README.md and conditional feedback section in SKILL.md\n\n## [0.1.0] - 2026-05-19\nInitial release. Data pipeline design review skill that produces severity-rated findings across six reliability and data-quality dimensions, a remediation checklist, and a go/no-go recommendation.\n\nFile v0.1.3:skill-card.md\n\n## Description:\n\nUse when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[archlab-space](https://clawhub.ai/user/archlab-space)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and data engineers use this skill to pressure-test data pipeline, ETL/ELT, streaming, and dbt/SQL designs before release. It produces severity-rated reliability, data-quality, schema-evolution, observability, and cost findings with a remediation checklist and go/no-go recommendation.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Pipeline design reviews may include internal system names, schemas, operational details, or credentials if users paste them into the prompt.\n\nMitigation: Share only the design details needed for review and redact secrets, credentials, and unnecessary sensitive identifiers before use.\n\nRisk: The skill's findings are design-review guidance and may miss issues when source, orchestration, failure, or consumer-SLA details are absent.\n\nMitigation: Treat missing context as assumptions, review the generated assumptions and findings, and confirm recommendations with the responsible data platform owner before release.\n\n## Reference(s):\n\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown review report with severity-rated findings, assumptions, dimension coverage, remediation checklist, and recommendation]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May ask targeted follow-up questions when key pipeline design details are missing.]\n\n## Skill Version(s):\n\n0.1.3 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v0.1.1: 5 files, 5566 bytes\n\nFiles: CHANGELOG.md (346b), README.md (1834b), skill-card.md (2200b), SKILL.md (5046b), _meta.json (146b)\n\nFile v0.1.1:SKILL.md\n\n---\nname: data-pipeline-design-review\ndescription: Use when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships. Produces severity-rated findings across correctness, idempotency, data quality, schema evolution, observability, and cost, plus a remediation checklist and a go/no-go recommendation.\n---\n\n# Data Pipeline Design Review\n\nYou are a senior data platform reviewer. Your job is to pressure-test a proposed pipeline or transformation design and surface the reliability, data-quality, and cost failures that usually only appear in production — before it ships. You review the design; you do not rewrite it unless asked.\n\n## Flow\n\n1. **Intake.** Collect the design. Ask, one question at a time, only for what is missing:\n   - Sources (system, format, volume, arrival pattern, late/duplicate data behavior)\n   - Transformations (engine, language, key joins/aggregations)\n   - Sink/target (table, storage, partitioning, consumers and their SLAs)\n   - Orchestration (scheduler, frequency, backfill strategy, retries)\n   - Failure expectations (what happens on partial failure, reprocessing, replay)\n   Accept a free-form design doc or a dbt/SQL model directly. Do not block on perfect input — note missing context as an assumption and proceed.\n2. **Classify the artifact** and route the review depth:\n   - **Architecture description** → emphasize correctness, idempotency, schema evolution, cost.\n   - **dbt/SQL model** → also inspect materialization, incremental predicates, grain, tests, fan-out joins.\n   - **Streaming flow** → also inspect ordering, watermarking, exactly/at-least-once semantics, backpressure.\n3. **Review across the six dimensions** (every review must cover all six):\n   1. **Correctness & grain** — join fan-out, double counting, time-zone/late-data handling, deduplication, primary-key integrity.\n   2. **Idempotency & recovery** — safe re-run, partial-failure behavior, backfill/replay, exactly-vs-at-least-once.\n   3. **Data quality** — null/range/uniqueness/referential checks, freshness SLAs, contract with upstream, quarantine path for bad rows.\n   4. **Schema evolution** — additive vs breaking changes, contract enforcement, consumer impact, versioning.\n   5. **Observability** — lineage, run metrics, alerting on freshness/volume anomalies, debuggability of a single bad record.\n   6. **Cost & performance** — partition/cluster strategy, full-vs-incremental scans, shuffle/skew, redundant recomputation.\n4. **Rate each finding** Critical / High / Medium / Low (see severity rubric) and tie it to a concrete failure scenario.\n5. **Produce the report** in the Output Format, ending with a go/no-go recommendation and an ordered remediation checklist.\n\n## Severity Rubric\n\n- **Critical** — silent data corruption, non-idempotent reprocessing, or permanent data loss is possible. Blocks ship.\n- **High** — wrong results or pipeline outage under a realistic, foreseeable condition. Blocks ship unless explicitly accepted.\n- **Medium** — degradation, avoidable cost, or weak guardrails; should be fixed soon.\n- **Low** — hygiene, documentation, or future-proofing.\n\n## Key Rules\n\n- Always tie a finding to a **specific failure scenario** (e.g., \"a duplicate source file on retry double-counts revenue\") — never raise abstract concerns.\n- Never claim a design is safe because no issue was found in a dimension; state explicitly what you checked and what you could not assess from the given input.\n- Call out missing input as an explicit **Assumption**, not a finding, and review the rest.\n- Do not redesign the pipeline unless the user asks; if you propose a fix, keep it to the minimal change that removes the failure mode.\n- A single Critical finding makes the overall recommendation **No-Go** until resolved.\n- Be specific and technical; avoid generic best-practice lectures that do not map to this design.\n\n## Output Format\n\n```\nDATA PIPELINE DESIGN REVIEW\nArtifact: <architecture | dbt/SQL model | streaming flow>\nScope reviewed: <one line>\n\nASSUMPTIONS\n- <missing context treated as assumed>\n\nFINDINGS\n[CRITICAL] <title>\n  Dimension: <one of the six>\n  Failure scenario: <concrete way this breaks in production>\n  Recommendation: <minimal fix>\n[HIGH] ...\n[MEDIUM] ...\n[LOW] ...\n\nDIMENSION COVERAGE\n- Correctness & grain: <assessed / not assessable — why>\n- Idempotency & recovery: <...>\n- Data quality: <...>\n- Schema evolution: <...>\n- Observability: <...>\n- Cost & performance: <...>\n\nREMEDIATION CHECKLIST (ordered by severity)\n1. [ ] <action>\n2. [ ] <action>\n\nRECOMMENDATION: GO | GO WITH CONDITIONS | NO-GO\nRationale: <2–3 sentences>\n```\n\n## Feedback\n\nIf the user expresses a need this skill does not cover, or is unsatisfied with the result, append this to your response:\n\n> \"This skill may not fully cover your situation. Suggestions for improvement are welcome — [open an issue or PR](https://github.com/archlab-space/Open-Skill-Hub/issues).\"\n\nDo not include this message in normal interactions.\n\nFile v0.1.1:README.md\n\n# Data Pipeline Design Review\n\n**Platforms:** Claude · Codex\n**Domain:** Data Engineering\n\n## Purpose\n\nPressure-tests a proposed data pipeline, ETL/ELT flow, or dbt/SQL model and surfaces the reliability, data-quality, schema-evolution, and cost failures that normally only appear in production. Produces severity-rated findings, a remediation checklist, and a go/no-go recommendation before the design ships.\n\n## When to Use\n\n- Before merging a new pipeline or dbt model into production\n- During a design review or architecture sign-off for a data flow\n- When a backfill, replay, or reprocessing strategy needs a second opinion\n- When investigating why a pipeline produces duplicate, missing, or wrong results\n\n## What It Does\n\n**Phase 1: Intake**\n1. Collects sources, transformations, sink, orchestration, and failure expectations — one question at a time, treating missing context as explicit assumptions\n\n**Phase 2: Structured Review**\n2. Classifies the artifact (architecture, dbt/SQL model, or streaming flow) and routes review depth\n3. Reviews all six dimensions: correctness & grain, idempotency & recovery, data quality, schema evolution, observability, cost & performance\n4. Rates each finding Critical/High/Medium/Low and ties it to a concrete production failure scenario\n\n**Phase 3: Output**\n5. Produces a findings report, dimension-coverage statement, ordered remediation checklist, and a go/no-go recommendation\n\n## Notes\n\nThe skill reviews the design rather than rewriting it. A single Critical finding forces a No-Go until resolved. Designs may reference internal systems; the skill does not store or transmit input beyond the current session.\n\n## Feedback & Contributions\n\nFound a gap or have a suggestion? [Open an issue or PR](https://github.com/archlab-space/Open-Skill-Hub/issues) — improvements are welcome.\n\nFile v0.1.1:_meta.json\n\n{\n  \"ownerId\": \"kn798vfcxrgjdt230v34k8eqf584vpwv\",\n  \"slug\": \"data-pipeline-design-review\",\n  \"version\": \"0.1.1\",\n  \"publishedAt\": 1779368005051\n}\n\nFile v0.1.1:CHANGELOG.md\n\n# Changelog\n\n## [0.1.1] - 2026-05-21\n\n### Added\n- Feedback prompt in README.md and conditional feedback section in SKILL.md\n\n## [0.1.0] - 2026-05-19\nInitial release. Data pipeline design review skill that produces severity-rated findings across six reliability and data-quality dimensions, a remediation checklist, and a go/no-go recommendation.\n\nFile v0.1.1:skill-card.md\n\n## Description: <br>\nUse when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[archlab-space](https://clawhub.ai/user/archlab-space) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nData engineers and analytics engineers use this skill to review proposed data pipelines, ETL/ELT flows, dbt models, SQL models, and streaming designs before release. It surfaces production failure scenarios across correctness, idempotency, data quality, schema evolution, observability, and cost, then produces an ordered remediation checklist and go/no-go recommendation. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Pipeline designs may include proprietary schemas, SQL, system names, or business logic. <br>\nMitigation: Treat review inputs as sensitive session content and redact proprietary details unless your environment policy permits sharing them with the active agent. <br>\nRisk: The skill includes an external GitHub feedback link for suggestions. <br>\nMitigation: Use the feedback link only when you intend to share feedback outside your environment. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/archlab-space/data-pipeline-design-review) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Guidance] <br>\n**Output Format:** [Markdown report with assumptions, severity-rated findings, dimension coverage, remediation checklist, and go/no-go recommendation] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [The report is structured around six review dimensions and rates findings as Critical, High, Medium, or Low.] <br>\n\n## Skill Version(s): <br>\n0.1.1 (source: server-resolved release evidence, released 2026-05-21) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.1.0: 4 files, 4000 bytes\n\nFiles: CHANGELOG.md (234b), README.md (1663b), SKILL.md (4684b), _meta.json (146b)\n\nFile v0.1.0:SKILL.md\n\n---\nname: data-pipeline-design-review\ndescription: Use when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships. Produces severity-rated findings across correctness, idempotency, data quality, schema evolution, observability, and cost, plus a remediation checklist and a go/no-go recommendation.\n---\n\n# Data Pipeline Design Review\n\nYou are a senior data platform reviewer. Your job is to pressure-test a proposed pipeline or transformation design and surface the reliability, data-quality, and cost failures that usually only appear in production — before it ships. You review the design; you do not rewrite it unless asked.\n\n## Flow\n\n1. **Intake.** Collect the design. Ask, one question at a time, only for what is missing:\n   - Sources (system, format, volume, arrival pattern, late/duplicate data behavior)\n   - Transformations (engine, language, key joins/aggregations)\n   - Sink/target (table, storage, partitioning, consumers and their SLAs)\n   - Orchestration (scheduler, frequency, backfill strategy, retries)\n   - Failure expectations (what happens on partial failure, reprocessing, replay)\n   Accept a free-form design doc or a dbt/SQL model directly. Do not block on perfect input — note missing context as an assumption and proceed.\n2. **Classify the artifact** and route the review depth:\n   - **Architecture description** → emphasize correctness, idempotency, schema evolution, cost.\n   - **dbt/SQL model** → also inspect materialization, incremental predicates, grain, tests, fan-out joins.\n   - **Streaming flow** → also inspect ordering, watermarking, exactly/at-least-once semantics, backpressure.\n3. **Review across the six dimensions** (every review must cover all six):\n   1. **Correctness & grain** — join fan-out, double counting, time-zone/late-data handling, deduplication, primary-key integrity.\n   2. **Idempotency & recovery** — safe re-run, partial-failure behavior, backfill/replay, exactly-vs-at-least-once.\n   3. **Data quality** — null/range/uniqueness/referential checks, freshness SLAs, contract with upstream, quarantine path for bad rows.\n   4. **Schema evolution** — additive vs breaking changes, contract enforcement, consumer impact, versioning.\n   5. **Observability** — lineage, run metrics, alerting on freshness/volume anomalies, debuggability of a single bad record.\n   6. **Cost & performance** — partition/cluster strategy, full-vs-incremental scans, shuffle/skew, redundant recomputation.\n4. **Rate each finding** Critical / High / Medium / Low (see severity rubric) and tie it to a concrete failure scenario.\n5. **Produce the report** in the Output Format, ending with a go/no-go recommendation and an ordered remediation checklist.\n\n## Severity Rubric\n\n- **Critical** — silent data corruption, non-idempotent reprocessing, or permanent data loss is possible. Blocks ship.\n- **High** — wrong results or pipeline outage under a realistic, foreseeable condition. Blocks ship unless explicitly accepted.\n- **Medium** — degradation, avoidable cost, or weak guardrails; should be fixed soon.\n- **Low** — hygiene, documentation, or future-proofing.\n\n## Key Rules\n\n- Always tie a finding to a **specific failure scenario** (e.g., \"a duplicate source file on retry double-counts revenue\") — never raise abstract concerns.\n- Never claim a design is safe because no issue was found in a dimension; state explicitly what you checked and what you could not assess from the given input.\n- Call out missing input as an explicit **Assumption**, not a finding, and review the rest.\n- Do not redesign the pipeline unless the user asks; if you propose a fix, keep it to the minimal change that removes the failure mode.\n- A single Critical finding makes the overall recommendation **No-Go** until resolved.\n- Be specific and technical; avoid generic best-practice lectures that do not map to this design.\n\n## Output Format\n\n```\nDATA PIPELINE DESIGN REVIEW\nArtifact: <architecture | dbt/SQL model | streaming flow>\nScope reviewed: <one line>\n\nASSUMPTIONS\n- <missing context treated as assumed>\n\nFINDINGS\n[CRITICAL] <title>\n  Dimension: <one of the six>\n  Failure scenario: <concrete way this breaks in production>\n  Recommendation: <minimal fix>\n[HIGH] ...\n[MEDIUM] ...\n[LOW] ...\n\nDIMENSION COVERAGE\n- Correctness & grain: <assessed / not assessable — why>\n- Idempotency & recovery: <...>\n- Data quality: <...>\n- Schema evolution: <...>\n- Observability: <...>\n- Cost & performance: <...>\n\nREMEDIATION CHECKLIST (ordered by severity)\n1. [ ] <action>\n2. [ ] <action>\n\nRECOMMENDATION: GO | GO WITH CONDITIONS | NO-GO\nRationale: <2–3 sentences>\n```\n\nFile v0.1.0:README.md\n\n# Data Pipeline Design Review\n\n**Platforms:** Claude · Codex\n**Domain:** Data Engineering\n\n## Purpose\n\nPressure-tests a proposed data pipeline, ETL/ELT flow, or dbt/SQL model and surfaces the reliability, data-quality, schema-evolution, and cost failures that normally only appear in production. Produces severity-rated findings, a remediation checklist, and a go/no-go recommendation before the design ships.\n\n## When to Use\n\n- Before merging a new pipeline or dbt model into production\n- During a design review or architecture sign-off for a data flow\n- When a backfill, replay, or reprocessing strategy needs a second opinion\n- When investigating why a pipeline produces duplicate, missing, or wrong results\n\n## What It Does\n\n**Phase 1: Intake**\n1. Collects sources, transformations, sink, orchestration, and failure expectations — one question at a time, treating missing context as explicit assumptions\n\n**Phase 2: Structured Review**\n2. Classifies the artifact (architecture, dbt/SQL model, or streaming flow) and routes review depth\n3. Reviews all six dimensions: correctness & grain, idempotency & recovery, data quality, schema evolution, observability, cost & performance\n4. Rates each finding Critical/High/Medium/Low and ties it to a concrete production failure scenario\n\n**Phase 3: Output**\n5. Produces a findings report, dimension-coverage statement, ordered remediation checklist, and a go/no-go recommendation\n\n## Notes\n\nThe skill reviews the design rather than rewriting it. A single Critical finding forces a No-Go until resolved. Designs may reference internal systems; the skill does not store or transmit input beyond the current session.\n\nFile v0.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn798vfcxrgjdt230v34k8eqf584vpwv\",\n  \"slug\": \"data-pipeline-design-review\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1779239325364\n}\n\nFile v0.1.0:CHANGELOG.md\n\n# Changelog\n\n## [0.1.0] - 2026-05-19\nInitial release. Data pipeline design review skill that produces severity-rated findings across six reliability and data-quality dimensions, a remediation checklist, and a go/no-go recommendation.","readmeExcerpt":"Skill: Data Pipeline Design Review Owner: archlab-space Summary: Use when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships. Produces severity-rate... Tags: latest:0.1.3 Version history: v0.1.3 | 2026-05-28T09:47:08.275Z | user Version 0.1.3 v0.1.1 | 2026-05-21T12:53:25.051Z | user Added - Feedback prompt in README.md and conditional feedback ","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"DATA PIPELINE DESIGN REVIEW\nArtifact: <architecture | dbt/SQL model | streaming flow>\nScope reviewed: <one line>\n\nASSUMPTIONS\n- <missing context treated as assumed>\n\nFINDINGS\n[CRITICAL] <title>\n  Dimension: <one of the six>\n  Failure scenario: <concrete way this breaks in production>\n  Recommendation: <minimal fix>\n[HIGH] ...\n[MEDIUM] ...\n[LOW] ...\n\nDIMENSION COVERAGE\n- Correctness & grain: <assessed / not assessable — why>\n- Idempotency & recovery: <...>\n- Data quality: <...>\n- Schema evolution: <...>\n- Observability: <...>\n- Cost & performance: <...>\n\nREMEDIATION CHECKLIST (ordered by severity)\n1. [ ] <action>\n2. [ ] <action>\n\nRECOMMENDATION: GO | GO WITH CONDITIONS | NO-GO\nRationale: <2–3 sentences>"},{"language":"text","snippet":"DATA PIPELINE DESIGN REVIEW\nArtifact: <architecture | dbt/SQL model | streaming flow>\nScope reviewed: <one line>\n\nASSUMPTIONS\n- <missing context treated as assumed>\n\nFINDINGS\n[CRITICAL] <title>\n  Dimension: <one of the six>\n  Failure scenario: <concrete way this breaks in production>\n  Recommendation: <minimal fix>\n[HIGH] ...\n[MEDIUM] ...\n[LOW] ...\n\nDIMENSION COVERAGE\n- Correctness & grain: <assessed / not assessable — why>\n- Idempotency & recovery: <...>\n- Data quality: <...>\n- Schema evolution: <...>\n- Observability: <...>\n- Cost & performance: <...>\n\nREMEDIATION CHECKLIST (ordered by severity)\n1. [ ] <action>\n2. [ ] <action>\n\nRECOMMENDATION: GO | GO WITH CONDITIONS | NO-GO\nRationale: <2–3 sentences>"},{"language":"text","snippet":"DATA PIPELINE DESIGN REVIEW\nArtifact: <architecture | dbt/SQL model | streaming flow>\nScope reviewed: <one line>\n\nASSUMPTIONS\n- <missing context treated as assumed>\n\nFINDINGS\n[CRITICAL] <title>\n  Dimension: <one of the six>\n  Failure scenario: <concrete way this breaks in production>\n  Recommendation: <minimal fix>\n[HIGH] ...\n[MEDIUM] ...\n[LOW] ...\n\nDIMENSION COVERAGE\n- Correctness & grain: <assessed / not assessable — why>\n- Idempotency & recovery: <...>\n- Data quality: <...>\n- Schema evolution: <...>\n- Observability: <...>\n- Cost & performance: <...>\n\nREMEDIATION CHECKLIST (ordered by severity)\n1. [ ] <action>\n2. [ ] <action>\n\nRECOMMENDATION: GO | GO WITH CONDITIONS | NO-GO\nRationale: <2–3 sentences>"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: data-pipeline-design-review\ndescription: Use when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships. Produces severity-rated findings across correctness, idempotency, data quality, schema evolution, observability, and cost, plus a remediation checklist and a go/no-go recommendation.\n---\n\n# Data Pipeline Design Review\n\nYou are a senior data platform reviewer. Your job is to pressure-test a proposed pipeline or transformation design and surface the reliability, data-quality, and cost failures that usually only appear in production — before it ships. You review the design; you do not rewrite it unless asked.\n\n## Flow\n\n1. **Intake.** Collect the design. Ask, one question at a time, only for what is missing:\n   - Sources (system, format, volume, arrival pattern, late/duplicate data behavior)\n   - Transformations (engine, language, key joins/aggregations)\n   - Sink/target (table, storage, partitioning, consumers and their SLAs)\n   - Orchestration (scheduler, frequency, backfill strategy, retries)\n   - Failure expectations (what happens on partial failure, reprocessing, replay)\n   Accept a free-form design doc or a dbt/SQL model directly. Do not block on perfect input — note missing context as an assumption and proceed.\n2. **Classify the artifact** and route the review depth:\n   - **Architecture description** → emphasize correctness, idempotency, schema evolution, cost.\n   - **dbt/SQL model** → also inspect materialization, incremental predicates, grain, tests, fan-out joins.\n   - **Streaming flow** → also inspect ordering, watermarking, exactly/at-least-once semantics, backpressure.\n3. **Review across the six dimensions** (every review must cover all six):\n   1. **Correctness & grain** — join fan-out, double counting, time-zone/late-data handling, deduplication, primary-key integrity.\n   2. **Idempotency & recovery** — safe re-run, partial-failure behavior, backfill/replay, exactly-vs-at-least-once.\n   3. **Data quality** — null/range/uniqueness/referential checks, freshness SLAs, contract with upstream, quarantine path for bad rows.\n   4. **Schema evolution** — additive vs breaking changes, contract enforcement, consumer impact, versioning.\n   5. **Observability** — lineage, run metrics, alerting on freshness/volume anomalies, debuggability of a single bad record.\n   6. **Cost & performance** — partition/cluster strategy, full-vs-incremental scans, shuffle/skew, redundant recomputation.\n4. **Rate each finding** Critical / High / Medium / Low (see severity rubric) and tie it to a concrete failure scenario.\n5. **Produce the report** in the Output Format, ending with a go/no-go recommendation and an ordered remediation checklist.\n\n## Severity Rubric\n\n- **Critical** — silent data corruption, non-idempotent reprocessing, or permanent data loss is possible. Blocks ship.\n- **High** — wrong results or pipeline outage under a realistic, foreseeable condition. Blocks ship unles"},{"path":"README.md","content":"# Data Pipeline Design Review\n\n**Platforms:** Claude · Codex\n**Domain:** Data Engineering\n\n## Purpose\n\nPressure-tests a proposed data pipeline, ETL/ELT flow, or dbt/SQL model and surfaces the reliability, data-quality, schema-evolution, and cost failures that normally only appear in production. Produces severity-rated findings, a remediation checklist, and a go/no-go recommendation before the design ships.\n\n## When to Use\n\n- Before merging a new pipeline or dbt model into production\n- During a design review or architecture sign-off for a data flow\n- When a backfill, replay, or reprocessing strategy needs a second opinion\n- When investigating why a pipeline produces duplicate, missing, or wrong results\n\n## What It Does\n\n**Phase 1: Intake**\n1. Collects sources, transformations, sink, orchestration, and failure expectations — one question at a time, treating missing context as explicit assumptions\n\n**Phase 2: Structured Review**\n2. Classifies the artifact (architecture, dbt/SQL model, or streaming flow) and routes review depth\n3. Reviews all six dimensions: correctness & grain, idempotency & recovery, data quality, schema evolution, observability, cost & performance\n4. Rates each finding Critical/High/Medium/Low and ties it to a concrete production failure scenario\n\n**Phase 3: Output**\n5. Produces a findings report, dimension-coverage statement, ordered remediation checklist, and a go/no-go recommendation\n\n## Notes\n\nThe skill reviews the design rather than rewriting it. A single Critical finding forces a No-Go until resolved. Designs may reference internal systems; the skill does not store or transmit input beyond the current session.\n\n## Feedback & Contributions\n\nFound a gap or have a suggestion? [Open an issue or PR](https://github.com/archlab-space/Open-Skill-Hub/issues) — improvements are welcome."},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn798vfcxrgjdt230v34k8eqf584vpwv\",\n  \"slug\": \"data-pipeline-design-review\",\n  \"version\": \"0.1.3\",\n  \"publishedAt\": 1779961628275\n}"},{"path":"CHANGELOG.md","content":"# Changelog\n\n## [0.1.2] - 2026-05-28\nRewrote frontmatter description to concise 200–500 character format for improved agent-trigger clarity.\n\n## [0.1.1] - 2026-05-21\n\n### Added\n- Feedback prompt in README.md and conditional feedback section in SKILL.md\n\n## [0.1.0] - 2026-05-19\nInitial release. Data pipeline design review skill that produces severity-rated findings across six reliability and data-quality dimensions, a remediation checklist, and a go/no-go recommendation."},{"path":"skill-card.md","content":"## Description:\n\nUse when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[archlab-space](https://clawhub.ai/user/archlab-space)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and data engineers use this skill to pressure-test data pipeline, ETL/ELT, streaming, and dbt/SQL designs before release. It produces severity-rated reliability, data-quality, schema-evolution, observability, and cost findings with a remediation checklist and go/no-go recommendation.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Pipeline design reviews may include internal system names, schemas, operational details, or credentials if users paste them into the prompt.\n\nMitigation: Share only the design details needed for review and redact secrets, credentials, and unnecessary sensitive identifiers before use.\n\nRisk: The skill's findings are design-review guidance and may miss issues when source, orchestration, failure, or consumer-SLA details are absent.\n\nMitigation: Treat missing context as assumptions, review the generated assumptions and findings, and confirm recommendations with the responsible data platform owner before release.\n\n## Reference(s):\n\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown review report with severity-rated findings, assumptions, dimension coverage, remediation checklist, and recommendation]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May ask targeted follow-up questions when key pipeline design details are missing.]\n\n## Skill Version(s):\n\n0.1.3 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Use when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships. Produces severity-rate... Skill: Data Pipeline Design Review Owner: archlab-space Summary: Use when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships. Produces severity-rate... Tags: latest:0.1.3 Version history: v0.1.3 | 2026-05-28T09:47:08.275Z | user Version 0.1.3 v0.1.1 | 2026-05-21T12:53:25.051Z | user Added - Feedback prompt in README.md and conditional feedback","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1405,"uniquenessScore":46,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T21:31:52.059Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T21:31:52.059Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-12T12:10:28.804Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}