# Send Scale Frameworks to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "scale", "name": "Scale Frameworks", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/ivangdavila/scale", "canonicalUrl": "https://clawhub.ai/ivangdavila/scale", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/scale", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=scale", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "architecture-scale-framework.md", "company-scale-framework.md", "execution-cadence.md", "memory-template.md", "scale-diagnostic.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "scale", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-03T12:56:53.612Z", "expiresAt": "2026-05-10T12:56:53.612Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=scale", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=scale", "contentDisposition": "attachment; filename=\"scale-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "scale" }, "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/scale" }, "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." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/scale", "downloadUrl": "https://openagent3.xyz/downloads/scale", "agentUrl": "https://openagent3.xyz/skills/scale/agent", "manifestUrl": "https://openagent3.xyz/skills/scale/agent.json", "briefUrl": "https://openagent3.xyz/skills/scale/agent.md" } } ``` ## Documentation ### Setup On first use, read setup.md for integration and activation guidance. ### When to Use Use this skill when the user wants to scale something with real constraints: technical systems, software architecture, organizations, operations, or go-to-market capacity. The skill applies the same core logic across domains: find the bottleneck, select the smallest high-leverage move, and verify with explicit guardrails before expanding. This skill is advisory and planning-focused. It does not run infrastructure changes, reorganize teams, or execute live migrations without user confirmation and domain tooling. ### Architecture Memory lives in ~/scale/. See memory-template.md for structure and status fields. ~/scale/ |- memory.md # Durable scaling context and activation preferences |- bottleneck-map.md # Active constraints and bottleneck hypotheses |- leverage-backlog.md # Candidate changes ranked by impact and effort \`- experiment-log.md # Outcomes, regressions, and rollout notes ### Quick Reference Use the smallest relevant file for the current scaling problem. TopicFileSetup and integrationsetup.mdMemory structure and statesmemory-template.mdUniversal intake and bottleneck diagnosisscale-diagnostic.mdInfrastructure and platform scalingsystem-scale-framework.mdSoftware architecture scalingarchitecture-scale-framework.mdTeam and business scalingcompany-scale-framework.mdCadence, metrics, and rollout controlexecution-cadence.md ### 1. Define Scale Target Before Solutions Always lock these inputs first: What must scale: throughput, reliability, team output, revenue, or customer base Time horizon: immediate, quarter, or year Non-negotiable constraints: budget, compliance, headcount, latency, quality No target, no valid scaling plan. ### 2. Work the BOLT Loop For every scaling request, apply BOLT in order: Bottleneck: identify the dominant limiting factor now Objective: define measurable win condition Levers: list 3 to 5 candidate interventions Test: run staged validation with rollback criteria Do not skip directly from symptoms to large transformations. ### 3. Prioritize Smallest Effective Change Default to interventions that unlock capacity fast with bounded risk: Remove queueing friction before adding complexity Improve interfaces and ownership before splitting services Standardize repeated work before hiring aggressively Big rewrites are last resort, not default strategy. ### 4. Price Second-Order Effects Explicitly Each recommendation must include likely side effects: New failure modes Cost and operational overhead growth Coordination load across teams Risk of local optimization hurting global performance If second-order risk is unknown, mark as hypothesis and constrain rollout. ### 5. Pair Every KPI with a Guardrail Never scale on a single growth metric. Pair it with guardrails: Throughput with error rate Deploy velocity with change failure rate Sales growth with gross margin and support load If guardrails degrade, pause expansion and stabilize. ### 6. Separate Temporary Boosts from Durable Capacity Label every action as one of two types: Temporary boost: overtime, manual review, tactical exceptions Durable capacity: automation, architecture simplification, reusable process Use temporary boosts only to buy time for durable capacity. ### 7. Institutionalize What Works After each successful change: Capture trigger conditions Document operating playbook and owner Add review cadence and retirement criteria Scaling compounds only when wins become repeatable systems. ### Common Traps Hiring before workflow clarity -> headcount increases coordination drag. Splitting monoliths before interface discipline -> distributed outages with slower delivery. Scaling traffic without SLO guardrails -> growth hides reliability collapse. Copying big-company org charts too early -> decision latency and ownership gaps. Optimizing one bottleneck in isolation -> next bottleneck shifts and total flow does not improve. Confusing activity with throughput -> teams look busy while output stagnates. ### Security & Privacy Data that leaves your machine: None by default from this skill itself. Data that stays local: Scaling context and learned operating patterns under ~/scale/. This skill does NOT: Execute undeclared network requests automatically. Apply irreversible technical or organizational changes without explicit user approval. Store secrets, credentials, or payment data in local memory files. Modify files outside ~/scale/ for memory storage. ### Related Skills Install with clawhub install if user confirms: architecture - Architectural fundamentals and constraints that shape scaling decisions. systems-architect - Reliability, infrastructure, and platform tradeoff patterns. startup - Stage-aware startup execution and prioritization logic. growth - Demand generation and growth loops once capacity is ready. strategy - Strategic framing and tradeoff analysis across long horizons. ### Feedback If useful: clawhub star scale Stay updated: clawhub sync ## Trust - Source: tencent - Verification: Indexed source record - Publisher: ivangdavila - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-03T12:56:53.612Z - Expires at: 2026-05-10T12:56:53.612Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/scale) - [Send to Agent page](https://openagent3.xyz/skills/scale/agent) - [JSON manifest](https://openagent3.xyz/skills/scale/agent.json) - [Markdown brief](https://openagent3.xyz/skills/scale/agent.md) - [Download page](https://openagent3.xyz/downloads/scale)