{ "schemaVersion": "1.0", "item": { "slug": "sprint-os", "name": "Sprint OS", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/Batsirai/sprint-os", "canonicalUrl": "https://clawhub.ai/Batsirai/sprint-os", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/sprint-os", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=sprint-os", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "scripts/convex-setup.md", "scripts/log-sprint.sh" ], "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/sprint-os" }, "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/sprint-os", "agentPageUrl": "https://openagent3.xyz/skills/sprint-os/agent", "manifestUrl": "https://openagent3.xyz/skills/sprint-os/agent.json", "briefUrl": "https://openagent3.xyz/skills/sprint-os/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Sprint OS — 5-Minute Sprint Operating System", "body": "Built for AI agents that ship. Every sprint produces one shippable artifact — not a plan, not a summary. A real thing." }, { "title": "What This Is", "body": "Sprint OS is an operating discipline for AI agents (and humans) who need to stay in execution mode. You work in continuous 5-minute sprints. Each sprint follows the same 8-step loop. Every sprint is logged. Nothing gets batched, buried, or lost.\n\nWhen to load this skill:\n\nUser asks the agent to \"operate in sprint mode\" or \"use Sprint OS\"\nStarting a new project or work session and wanting structure\nNeeding autonomous task execution with momentum tracking\nWanting to log work to a Convex backend for tracking and deduplication" }, { "title": "The Sprint Loop", "body": "Every sprint follows this exact sequence:" }, { "title": "1. ASSESS", "body": "What is the current state? What is the gap to the target outcome?\n\nRead the active task list, relevant files, and recent sprint log\nIdentify where things stand right now\nName the gap: what's missing between current state and the outcome?" }, { "title": "2. PLAN", "body": "What is the single highest-leverage action available right now?\n\nPick ONE thing to do in this sprint\nApply the prioritization hierarchy (see below)\nDo not batch or multi-task" }, { "title": "3. SCOPE", "body": "Define \"done\" in ≤5 minutes.\n\nName the specific artifact this sprint will produce\nIf it can't be done in 5 minutes, break it into a smaller sprint\nNo sprint ends without a concrete output" }, { "title": "4. EXECUTE", "body": "Do the work. Produce the artifact.\n\nExecute the scoped task\nFocus entirely on the output — no scope creep\nIf you discover the scope was wrong, stop, re-scope, and continue" }, { "title": "5. MEASURE", "body": "Did it move the metric? What changed?\n\nState the concrete result: what artifact was produced\nName the relevant metric and whether it moved\nBe honest: \"completed\" vs \"partially completed\" vs \"blocked\"" }, { "title": "6. ADAPT", "body": "Reprioritize. Kill what's not working.\n\nBased on the result, what should the NEXT sprint be?\nIf 3 consecutive sprints produced no measurable movement: switch workstream or angle\nNever keep grinding on a dead approach — adapt immediately" }, { "title": "7. LOG", "body": "Record to sprint log + (if configured) Convex.\n\nWrite a sprint log entry (see format below) to the sprint log file, and optionally POST to the Convex endpoint." }, { "title": "8. NEXT", "body": "Immediately begin the next sprint.\n\nNo gaps. No reflection breaks longer than 30 seconds. Momentum is the goal." }, { "title": "Sprint Rules", "body": "Every sprint MUST produce a shippable artifact\nIf >5 minutes, break into smaller sprints\nNever batch-plan more than 3 sprints ahead\nBias toward momentum over perfection\nEvery sprint must connect to an active outcome\nIf blocked, log the blocker and skip to the next available sprint — never idle" }, { "title": "Prioritization Hierarchy", "body": "Before every sprint, ask:\n\n\"If I could only do ONE thing in the next 5 minutes to move closer to the outcome, what would it be?\"\n\nFix what's broken → Actively losing money or trust? Fix it first.\nOptimize what's working → Something converting? Double down before exploring new.\nTest new angles → Small experiments to find the next lever.\nBuild infrastructure → Only when 1–3 are humming." }, { "title": "Pivot Triggers", "body": "Stop the current workstream and pivot when:\n\n3 consecutive sprints with no measurable movement → switch workstream or angle\nChannel hitting diminishing returns → reduce allocation, test alternatives\nUnexpected win (viral, press, referral spike) → drop lower-priority, capitalize immediately\nCustomer feedback pattern emerging → elevate to top of sprint queue" }, { "title": "Sprint Log Format", "body": "Write one entry per sprint to sprint-log.md in the working directory:\n\n## Sprint [N] — [YYYY-MM-DD HH:MM]\n\n**Project:** [project name]\n**Workstream:** [marketing / development / content / research / etc.]\n**Task:** [what you did]\n**Artifact:** [what was produced — link or one-line description]\n**Metric:** [what moved, or \"no movement\"]\n**Status:** completed | partial | blocked\n**Blocker:** [only if blocked — what's stopping you]\n**Next sprint:** [what comes next]" }, { "title": "Convex Integration (Optional)", "body": "If CONVEX_SPRINT_URL is set, POST every sprint log entry to the Convex HTTP endpoint. This enables:\n\nSprint history across sessions\nWorkstream breakdown reports\nContent deduplication (check before creating)\nMetric trend tracking" }, { "title": "Setup", "body": "Deploy the Convex backend in scripts/convex-setup.md\nSet CONVEX_SPRINT_URL to your Convex HTTP site URL (e.g., https://your-deployment.convex.site)\nSprints will auto-log on step 7 of each loop" }, { "title": "Endpoints", "body": "MethodPathPurposePOST/sprints/logLog a completed sprintGET/sprints/recent?project=X&limit=NRecent sprint historyGET/sprints/stats?project=X&days=NWorkstream breakdownPOST/metrics/recordRecord a metric valueGET/metrics/latest?metric=XCurrent metric valueGET/metrics/trend?metric=X&days=NMetric over timePOST/content/logLog content creationGET/content/search?query=XDeduplication check" }, { "title": "Sprint Log Payload", "body": "curl -X POST $CONVEX_SPRINT_URL/sprints/log \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"sprintId\": 1,\n \"project\": \"my-project\",\n \"workstream\": \"marketing\",\n \"task\": \"Write homepage headline variants\",\n \"artifact\": \"3 headline variants in headlines.md\",\n \"metric\": \"no movement yet\",\n \"status\": \"completed\",\n \"owner\": \"agent\",\n \"timestamp\": 1740000000000\n }'" }, { "title": "Script", "body": "Use scripts/log-sprint.sh for quick CLI logging:\n\n./scripts/log-sprint.sh \\\n --project \"my-project\" \\\n --workstream \"development\" \\\n --task \"Fix checkout redirect bug\" \\\n --artifact \"PR #42 opened\" \\\n --metric \"checkout CVR: TBD pending deploy\" \\\n --status \"completed\"" }, { "title": "Morning", "body": "Read active task list\nASSESS the current state of all outcomes\nSet today's #1 priority\nBegin sprint 1" }, { "title": "Continuous", "body": "Sprint back-to-back, 5 minutes each\nLog every sprint (file + Convex if configured)\nSpawn sub-agents for heavy execution work\nNever stop between sprints for more than 30 seconds" }, { "title": "End of Day", "body": "Complete the sprint log\nUpdate active task list with what moved\nSet tomorrow's #1 priority\nRun scripts/log-sprint.sh --daily-summary if Convex is configured" }, { "title": "Weekly (Friday)", "body": "Review: which workstream had the most impact?\nWhich sprints were wasted? Why?\nBiggest bottleneck assessment\nRestack priorities for next week" }, { "title": "Daily Status", "body": "📊 DAY [X] — [DATE]\nSPRINTS: [completed today] | TOP WIN: [best result]\nBLOCKER: [biggest obstacle]\nMETRICS: [key metric] → [current value]\nTOMORROW: [1–2 sentences]" }, { "title": "Weekly Review", "body": "📈 WEEK [X] — [DATE RANGE]\nSPRINTS: [total] (by workstream breakdown)\nWINS: [top 3 with metrics]\nMISSES: [top 3 with root cause]\nLESSONS: [top 3]\nNEXT WEEK: [top 3 priorities]\nESCALATIONS: [decisions needed from human]" }, { "title": "Usage Examples", "body": "# Start sprint operating mode\n\"Enter sprint mode. My project is [X]. Target outcome: [Y].\"\n\n# Run a sprint\n\"Run sprint on: write 3 email subject line variants for the welcome sequence.\"\n\n# Review recent sprints\n\"Show my sprint log for today.\"\n\n# Weekly review\n\"Generate weekly sprint review.\"\n\n# With Convex logging\n\"Log sprint: task=wrote homepage copy, artifact=homepage-v2.md, metric=awaiting test, status=completed\"" }, { "title": "File Structure", "body": "sprint-os/\n├── SKILL.md ← This file\n├── README.md ← Human-readable overview\n└── scripts/\n ├── log-sprint.sh ← CLI sprint logger (Convex optional)\n └── convex-setup.md ← Instructions for Convex backend setup\n\nSprint OS v1.0 — February 2026\nA product by Carson Jarvis (@CarsonJarvisAI)" } ], "body": "Sprint OS — 5-Minute Sprint Operating System\n\nBuilt for AI agents that ship. Every sprint produces one shippable artifact — not a plan, not a summary. A real thing.\n\nWhat This Is\n\nSprint OS is an operating discipline for AI agents (and humans) who need to stay in execution mode. You work in continuous 5-minute sprints. Each sprint follows the same 8-step loop. Every sprint is logged. Nothing gets batched, buried, or lost.\n\nWhen to load this skill:\n\nUser asks the agent to \"operate in sprint mode\" or \"use Sprint OS\"\nStarting a new project or work session and wanting structure\nNeeding autonomous task execution with momentum tracking\nWanting to log work to a Convex backend for tracking and deduplication\nThe Sprint Loop\n\nEvery sprint follows this exact sequence:\n\n1. ASSESS\n\nWhat is the current state? What is the gap to the target outcome?\n\nRead the active task list, relevant files, and recent sprint log\nIdentify where things stand right now\nName the gap: what's missing between current state and the outcome?\n2. PLAN\n\nWhat is the single highest-leverage action available right now?\n\nPick ONE thing to do in this sprint\nApply the prioritization hierarchy (see below)\nDo not batch or multi-task\n3. SCOPE\n\nDefine \"done\" in ≤5 minutes.\n\nName the specific artifact this sprint will produce\nIf it can't be done in 5 minutes, break it into a smaller sprint\nNo sprint ends without a concrete output\n4. EXECUTE\n\nDo the work. Produce the artifact.\n\nExecute the scoped task\nFocus entirely on the output — no scope creep\nIf you discover the scope was wrong, stop, re-scope, and continue\n5. MEASURE\n\nDid it move the metric? What changed?\n\nState the concrete result: what artifact was produced\nName the relevant metric and whether it moved\nBe honest: \"completed\" vs \"partially completed\" vs \"blocked\"\n6. ADAPT\n\nReprioritize. Kill what's not working.\n\nBased on the result, what should the NEXT sprint be?\nIf 3 consecutive sprints produced no measurable movement: switch workstream or angle\nNever keep grinding on a dead approach — adapt immediately\n7. LOG\n\nRecord to sprint log + (if configured) Convex.\n\nWrite a sprint log entry (see format below) to the sprint log file, and optionally POST to the Convex endpoint.\n\n8. NEXT\n\nImmediately begin the next sprint.\n\nNo gaps. No reflection breaks longer than 30 seconds. Momentum is the goal.\n\nSprint Rules\nEvery sprint MUST produce a shippable artifact\nIf >5 minutes, break into smaller sprints\nNever batch-plan more than 3 sprints ahead\nBias toward momentum over perfection\nEvery sprint must connect to an active outcome\nIf blocked, log the blocker and skip to the next available sprint — never idle\nPrioritization Hierarchy\n\nBefore every sprint, ask:\n\n\"If I could only do ONE thing in the next 5 minutes to move closer to the outcome, what would it be?\"\n\nFix what's broken → Actively losing money or trust? Fix it first.\nOptimize what's working → Something converting? Double down before exploring new.\nTest new angles → Small experiments to find the next lever.\nBuild infrastructure → Only when 1–3 are humming.\nPivot Triggers\n\nStop the current workstream and pivot when:\n\n3 consecutive sprints with no measurable movement → switch workstream or angle\nChannel hitting diminishing returns → reduce allocation, test alternatives\nUnexpected win (viral, press, referral spike) → drop lower-priority, capitalize immediately\nCustomer feedback pattern emerging → elevate to top of sprint queue\nSprint Log Format\n\nWrite one entry per sprint to sprint-log.md in the working directory:\n\n## Sprint [N] — [YYYY-MM-DD HH:MM]\n\n**Project:** [project name]\n**Workstream:** [marketing / development / content / research / etc.]\n**Task:** [what you did]\n**Artifact:** [what was produced — link or one-line description]\n**Metric:** [what moved, or \"no movement\"]\n**Status:** completed | partial | blocked\n**Blocker:** [only if blocked — what's stopping you]\n**Next sprint:** [what comes next]\n\nConvex Integration (Optional)\n\nIf CONVEX_SPRINT_URL is set, POST every sprint log entry to the Convex HTTP endpoint. This enables:\n\nSprint history across sessions\nWorkstream breakdown reports\nContent deduplication (check before creating)\nMetric trend tracking\nSetup\nDeploy the Convex backend in scripts/convex-setup.md\nSet CONVEX_SPRINT_URL to your Convex HTTP site URL (e.g., https://your-deployment.convex.site)\nSprints will auto-log on step 7 of each loop\nEndpoints\nMethod\tPath\tPurpose\nPOST\t/sprints/log\tLog a completed sprint\nGET\t/sprints/recent?project=X&limit=N\tRecent sprint history\nGET\t/sprints/stats?project=X&days=N\tWorkstream breakdown\nPOST\t/metrics/record\tRecord a metric value\nGET\t/metrics/latest?metric=X\tCurrent metric value\nGET\t/metrics/trend?metric=X&days=N\tMetric over time\nPOST\t/content/log\tLog content creation\nGET\t/content/search?query=X\tDeduplication check\nSprint Log Payload\ncurl -X POST $CONVEX_SPRINT_URL/sprints/log \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"sprintId\": 1,\n \"project\": \"my-project\",\n \"workstream\": \"marketing\",\n \"task\": \"Write homepage headline variants\",\n \"artifact\": \"3 headline variants in headlines.md\",\n \"metric\": \"no movement yet\",\n \"status\": \"completed\",\n \"owner\": \"agent\",\n \"timestamp\": 1740000000000\n }'\n\nScript\n\nUse scripts/log-sprint.sh for quick CLI logging:\n\n./scripts/log-sprint.sh \\\n --project \"my-project\" \\\n --workstream \"development\" \\\n --task \"Fix checkout redirect bug\" \\\n --artifact \"PR #42 opened\" \\\n --metric \"checkout CVR: TBD pending deploy\" \\\n --status \"completed\"\n\nDaily Rhythm\nMorning\nRead active task list\nASSESS the current state of all outcomes\nSet today's #1 priority\nBegin sprint 1\nContinuous\nSprint back-to-back, 5 minutes each\nLog every sprint (file + Convex if configured)\nSpawn sub-agents for heavy execution work\nNever stop between sprints for more than 30 seconds\nEnd of Day\nComplete the sprint log\nUpdate active task list with what moved\nSet tomorrow's #1 priority\nRun scripts/log-sprint.sh --daily-summary if Convex is configured\nWeekly (Friday)\nReview: which workstream had the most impact?\nWhich sprints were wasted? Why?\nBiggest bottleneck assessment\nRestack priorities for next week\nReporting Formats\nDaily Status\n📊 DAY [X] — [DATE]\nSPRINTS: [completed today] | TOP WIN: [best result]\nBLOCKER: [biggest obstacle]\nMETRICS: [key metric] → [current value]\nTOMORROW: [1–2 sentences]\n\nWeekly Review\n📈 WEEK [X] — [DATE RANGE]\nSPRINTS: [total] (by workstream breakdown)\nWINS: [top 3 with metrics]\nMISSES: [top 3 with root cause]\nLESSONS: [top 3]\nNEXT WEEK: [top 3 priorities]\nESCALATIONS: [decisions needed from human]\n\nUsage Examples\n# Start sprint operating mode\n\"Enter sprint mode. My project is [X]. Target outcome: [Y].\"\n\n# Run a sprint\n\"Run sprint on: write 3 email subject line variants for the welcome sequence.\"\n\n# Review recent sprints\n\"Show my sprint log for today.\"\n\n# Weekly review\n\"Generate weekly sprint review.\"\n\n# With Convex logging\n\"Log sprint: task=wrote homepage copy, artifact=homepage-v2.md, metric=awaiting test, status=completed\"\n\nFile Structure\nsprint-os/\n├── SKILL.md ← This file\n├── README.md ← Human-readable overview\n└── scripts/\n ├── log-sprint.sh ← CLI sprint logger (Convex optional)\n └── convex-setup.md ← Instructions for Convex backend setup\n\n\nSprint OS v1.0 — February 2026 A product by Carson Jarvis (@CarsonJarvisAI)" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Batsirai/sprint-os", "publisherUrl": "https://clawhub.ai/Batsirai/sprint-os", "owner": "Batsirai", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/sprint-os", "downloadUrl": "https://openagent3.xyz/downloads/sprint-os", "agentUrl": "https://openagent3.xyz/skills/sprint-os/agent", "manifestUrl": "https://openagent3.xyz/skills/sprint-os/agent.json", "briefUrl": "https://openagent3.xyz/skills/sprint-os/agent.md" } }