{ "schemaVersion": "1.0", "item": { "slug": "ultra-agent-stinct", "name": "Ultra Agent Stinct", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/grimmjoww/ultra-agent-stinct", "canonicalUrl": "https://clawhub.ai/grimmjoww/ultra-agent-stinct", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/ultra-agent-stinct", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ultra-agent-stinct", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "references/escalation-guide.md", "references/git-workflow.md", "SKILL.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. 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": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/ultra-agent-stinct" }, "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/ultra-agent-stinct", "agentPageUrl": "https://openagent3.xyz/skills/ultra-agent-stinct/agent", "manifestUrl": "https://openagent3.xyz/skills/ultra-agent-stinct/agent.json", "briefUrl": "https://openagent3.xyz/skills/ultra-agent-stinct/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": "Ultra Agent Stinct", "body": "Your internal debugging instinct. When something breaks while you're working, this is how you fix it." }, { "title": "Always Follow These (Any Time You Touch Code)", "body": "These rules apply every time, even for quick fixes. No exceptions." }, { "title": "Safety", "body": "Read before edit. Never edit without read first — exact text match required or it fails\nwrite overwrites entirely. Use edit for changes to existing files\nNever delete without asking. Prefer safe deletion over rm -rf\nNever push without asking. git push only when the user explicitly says to\nNever commit without asking. Stage and commit only on request\nBackup awareness. Before large refactors, suggest a branch or stash" }, { "title": "Good Practices", "body": "Always verify your fix. After every change, re-run the failing command or tests. Never assume it worked\nTell the user what happened. After fixing, briefly explain what broke and what you changed\nRead the error first. Don't guess at fixes — read the actual error message, stack trace, or test output before touching code\nMinimal changes. Fix the bug, don't refactor the neighborhood. Keep diffs small and focused" }, { "title": "When to Activate Full Workflow", "body": "If you hit an error during a task, try a quick fix first while following the rules above. But if you:\n\nGet stuck — your first fix didn't work, same error or new ones\nHit something complex — errors across multiple files, unfamiliar code, architectural issues\nNeed structure — not sure where the bug is or where to start\n\nThen activate Ultra Agent Stinct — follow the full structured workflows below step by step." }, { "title": "Debug Workflow", "body": "When you encounter an error or something breaks:\n\n1. Reproduce — Run the failing command:\n\nexec command:\"\" workdir:\"\"\n\n2. Read the error — Parse the stack trace. Identify file + line number.\n\n3. Read the code — Read the relevant file(s):\n\nread path:\"\"\n\n4. Trace the cause — Follow the call chain. Read imports, dependencies, config. Check for:\n\nTypos, wrong variable names\nMissing imports or dependencies\nType mismatches, null/undefined access\nWrong paths, missing env vars\nLogic errors in conditionals\n\n5. Fix — Apply the minimal correct fix:\n\nread path:\"\"\nedit path:\"\" old:\"\" new:\"\"\n\n6. Verify — Re-run the original failing command. Confirm the fix works.\n\n7. Report — Tell the user what broke and what you fixed (brief). Then continue your original task." }, { "title": "Writing New Code", "body": "When you need to create or modify code as part of a task:\n\n1. Understand the project — Check existing patterns:\n\nexec command:\"ls -la\" workdir:\"\"\n\nRead package.json, pyproject.toml, Cargo.toml, or equivalent. Match existing style and conventions.\n\n2. Plan first — Before writing, outline what you'll create. Think through structure, dependencies, edge cases.\n\n3. Write — Create the file:\n\nwrite path:\"\" content:\"\"\n\n4. Verify — Run it, test it, make sure it actually works before moving on." }, { "title": "Running Tests", "body": "1. Find the test runner:\n\nNode.js: npm test / npx jest / npx vitest\nPython: pytest / python -m unittest\nRust: cargo test\nGo: go test ./...\n\n2. Run tests:\n\nexec command:\"\" workdir:\"\" timeout:120\n\n3. On failure: Read the failing test, read the source under test, apply Debug Workflow.\n\n4. On success: Report summary and continue." }, { "title": "Git Integration", "body": "Only when the user asks to commit, stage, or check git status.\n\nexec command:\"git status\" workdir:\"\"\nexec command:\"git diff --stat\" workdir:\"\"\nexec command:\"git add \" workdir:\"\"\nexec command:\"git commit -m ''\" workdir:\"\"\n\nFor detailed git workflows, see references/git-workflow.md." }, { "title": "Spawning Coding Agents (Heavy Tasks)", "body": "For large tasks (multi-file refactors, entire features, long builds), spawn a background agent:\n\nexec pty:true workdir:\"\" background:true command:\"claude ''\"\n\nMonitor:\n\nprocess action:list\nprocess action:log sessionId:\nprocess action:poll sessionId:\n\nSee references/escalation-guide.md for when to self-handle vs delegate." }, { "title": "Cross-Platform Quick Reference", "body": "TaskmacOS/LinuxWindows (Git Bash)Find filesfind . -name \"*.ts\" -not -path \"*/node_modules/*\"SameSearch codegrep -rn \"pattern\" --include=\"*.ts\" .SameProcess listps aux | grep nodetasklist | findstr nodeKill processkill -9 taskkill //f //pid Pythonpython3 (or python)pythonOpen fileopen start " }, { "title": "Context Management", "body": "Keep tool calls focused — one task per chain\nDon't read files already in your system prompt\nFor large files, read targeted sections rather than the whole thing\nIf context is getting heavy, summarize findings before continuing" } ], "body": "Ultra Agent Stinct\n\nYour internal debugging instinct. When something breaks while you're working, this is how you fix it.\n\nAlways Follow These (Any Time You Touch Code)\n\nThese rules apply every time, even for quick fixes. No exceptions.\n\nSafety\nRead before edit. Never edit without read first — exact text match required or it fails\nwrite overwrites entirely. Use edit for changes to existing files\nNever delete without asking. Prefer safe deletion over rm -rf\nNever push without asking. git push only when the user explicitly says to\nNever commit without asking. Stage and commit only on request\nBackup awareness. Before large refactors, suggest a branch or stash\nGood Practices\nAlways verify your fix. After every change, re-run the failing command or tests. Never assume it worked\nTell the user what happened. After fixing, briefly explain what broke and what you changed\nRead the error first. Don't guess at fixes — read the actual error message, stack trace, or test output before touching code\nMinimal changes. Fix the bug, don't refactor the neighborhood. Keep diffs small and focused\nWhen to Activate Full Workflow\n\nIf you hit an error during a task, try a quick fix first while following the rules above. But if you:\n\nGet stuck — your first fix didn't work, same error or new ones\nHit something complex — errors across multiple files, unfamiliar code, architectural issues\nNeed structure — not sure where the bug is or where to start\n\nThen activate Ultra Agent Stinct — follow the full structured workflows below step by step.\n\nDebug Workflow\n\nWhen you encounter an error or something breaks:\n\n1. Reproduce — Run the failing command:\n\nexec command:\"\" workdir:\"\"\n\n\n2. Read the error — Parse the stack trace. Identify file + line number.\n\n3. Read the code — Read the relevant file(s):\n\nread path:\"\"\n\n\n4. Trace the cause — Follow the call chain. Read imports, dependencies, config. Check for:\n\nTypos, wrong variable names\nMissing imports or dependencies\nType mismatches, null/undefined access\nWrong paths, missing env vars\nLogic errors in conditionals\n\n5. Fix — Apply the minimal correct fix:\n\nread path:\"\"\nedit path:\"\" old:\"\" new:\"\"\n\n\n6. Verify — Re-run the original failing command. Confirm the fix works.\n\n7. Report — Tell the user what broke and what you fixed (brief). Then continue your original task.\n\nWriting New Code\n\nWhen you need to create or modify code as part of a task:\n\n1. Understand the project — Check existing patterns:\n\nexec command:\"ls -la\" workdir:\"\"\n\n\nRead package.json, pyproject.toml, Cargo.toml, or equivalent. Match existing style and conventions.\n\n2. Plan first — Before writing, outline what you'll create. Think through structure, dependencies, edge cases.\n\n3. Write — Create the file:\n\nwrite path:\"\" content:\"\"\n\n\n4. Verify — Run it, test it, make sure it actually works before moving on.\n\nRunning Tests\n\n1. Find the test runner:\n\nNode.js: npm test / npx jest / npx vitest\nPython: pytest / python -m unittest\nRust: cargo test\nGo: go test ./...\n\n2. Run tests:\n\nexec command:\"\" workdir:\"\" timeout:120\n\n\n3. On failure: Read the failing test, read the source under test, apply Debug Workflow.\n\n4. On success: Report summary and continue.\n\nGit Integration\n\nOnly when the user asks to commit, stage, or check git status.\n\nexec command:\"git status\" workdir:\"\"\nexec command:\"git diff --stat\" workdir:\"\"\nexec command:\"git add \" workdir:\"\"\nexec command:\"git commit -m ''\" workdir:\"\"\n\n\nFor detailed git workflows, see references/git-workflow.md.\n\nSpawning Coding Agents (Heavy Tasks)\n\nFor large tasks (multi-file refactors, entire features, long builds), spawn a background agent:\n\nexec pty:true workdir:\"\" background:true command:\"claude ''\"\n\n\nMonitor:\n\nprocess action:list\nprocess action:log sessionId:\nprocess action:poll sessionId:\n\n\nSee references/escalation-guide.md for when to self-handle vs delegate.\n\nCross-Platform Quick Reference\nTask\tmacOS/Linux\tWindows (Git Bash)\nFind files\tfind . -name \"*.ts\" -not -path \"*/node_modules/*\"\tSame\nSearch code\tgrep -rn \"pattern\" --include=\"*.ts\" .\tSame\nProcess list\tps aux | grep node\ttasklist | findstr node\nKill process\tkill -9 \ttaskkill //f //pid \nPython\tpython3 (or python)\tpython\nOpen file\topen \tstart \nContext Management\nKeep tool calls focused — one task per chain\nDon't read files already in your system prompt\nFor large files, read targeted sections rather than the whole thing\nIf context is getting heavy, summarize findings before continuing" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/grimmjoww/ultra-agent-stinct", "publisherUrl": "https://clawhub.ai/grimmjoww/ultra-agent-stinct", "owner": "grimmjoww", "version": "1.2.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/ultra-agent-stinct", "downloadUrl": "https://openagent3.xyz/downloads/ultra-agent-stinct", "agentUrl": "https://openagent3.xyz/skills/ultra-agent-stinct/agent", "manifestUrl": "https://openagent3.xyz/skills/ultra-agent-stinct/agent.json", "briefUrl": "https://openagent3.xyz/skills/ultra-agent-stinct/agent.md" } }