{ "schemaVersion": "1.0", "item": { "slug": "skillagi", "name": "Skill AGI", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/wubotvix/skillagi", "canonicalUrl": "https://clawhub.ai/wubotvix/skillagi", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/skillagi", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skillagi", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "learnings.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "slug": "skillagi", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-03T17:44:55.564Z", "expiresAt": "2026-05-10T17:44:55.564Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skillagi", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skillagi", "contentDisposition": "attachment; filename=\"skillagi-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "skillagi" }, "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/skillagi" }, "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/skillagi", "agentPageUrl": "https://openagent3.xyz/skills/skillagi/agent", "manifestUrl": "https://openagent3.xyz/skills/skillagi/agent.json", "briefUrl": "https://openagent3.xyz/skills/skillagi/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Skillagi", "body": "Log mistakes and insights so you don't repeat them across sessions." }, { "title": "When to Log", "body": "Add a learning when you:\n\nFix a bug caused by a wrong assumption\nDiscover a project-specific convention (package manager, config, naming)\nGet corrected by the user\nFind a workaround for a tool/platform limitation\nWaste time on an approach that doesn't work here" }, { "title": "Format", "body": "Append one line to learnings.md (in this skill's directory):\n\n- [YYYY-MM-DD] topic: what happened → what to do instead\n\nKeep it to one line. If you need two sentences, you're over-explaining." }, { "title": "Examples", "body": "- [2026-02-21] pnpm not npm: Project uses pnpm workspaces → use `pnpm install`\n- [2026-02-21] Docker M1: Base image has no ARM64 variant → add `--platform linux/amd64`\n- [2026-02-21] test isolation: Shared DB state caused flaky tests → use transactions with rollback" }, { "title": "When to Review", "body": "Before starting a complex task, read learnings.md and apply anything relevant.\nDon't review for trivial one-line changes." }, { "title": "When to Clean Up", "body": "Periodically (or when the file exceeds ~50 entries):\n\nDelete entries that no longer apply (dependency upgraded, config changed)\nMerge duplicates into a single entry\nPromote critical entries that affect every session to a permanent location" }, { "title": "Promotion", "body": "Move persistent, high-impact learnings out of this file and into durable config:\n\nOpenClaw: Promote to workspace MEMORY.md, TOOLS.md, or AGENTS.md\nClaude Code: Promote to project CLAUDE.md or auto-memory (~/.claude/projects/*/memory/)\n\nOnce promoted, delete the entry from learnings.md to avoid duplication." }, { "title": "Rules", "body": "No IDs, statuses, priorities, or tags. Just the one-liner.\nNo hooks or scripts. This is a passive reference file.\nAppend-only during a session. Clean up between sessions.\nIf unsure whether something is worth logging, skip it. Only log what would save future time." } ], "body": "Skillagi\n\nLog mistakes and insights so you don't repeat them across sessions.\n\nWhen to Log\n\nAdd a learning when you:\n\nFix a bug caused by a wrong assumption\nDiscover a project-specific convention (package manager, config, naming)\nGet corrected by the user\nFind a workaround for a tool/platform limitation\nWaste time on an approach that doesn't work here\nFormat\n\nAppend one line to learnings.md (in this skill's directory):\n\n- [YYYY-MM-DD] topic: what happened → what to do instead\n\n\nKeep it to one line. If you need two sentences, you're over-explaining.\n\nExamples\n- [2026-02-21] pnpm not npm: Project uses pnpm workspaces → use `pnpm install`\n- [2026-02-21] Docker M1: Base image has no ARM64 variant → add `--platform linux/amd64`\n- [2026-02-21] test isolation: Shared DB state caused flaky tests → use transactions with rollback\n\nWhen to Review\n\nBefore starting a complex task, read learnings.md and apply anything relevant. Don't review for trivial one-line changes.\n\nWhen to Clean Up\n\nPeriodically (or when the file exceeds ~50 entries):\n\nDelete entries that no longer apply (dependency upgraded, config changed)\nMerge duplicates into a single entry\nPromote critical entries that affect every session to a permanent location\nPromotion\n\nMove persistent, high-impact learnings out of this file and into durable config:\n\nOpenClaw: Promote to workspace MEMORY.md, TOOLS.md, or AGENTS.md\nClaude Code: Promote to project CLAUDE.md or auto-memory (~/.claude/projects/*/memory/)\n\nOnce promoted, delete the entry from learnings.md to avoid duplication.\n\nRules\nNo IDs, statuses, priorities, or tags. Just the one-liner.\nNo hooks or scripts. This is a passive reference file.\nAppend-only during a session. Clean up between sessions.\nIf unsure whether something is worth logging, skip it. Only log what would save future time." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/wubotvix/skillagi", "publisherUrl": "https://clawhub.ai/wubotvix/skillagi", "owner": "wubotvix", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/skillagi", "downloadUrl": "https://openagent3.xyz/downloads/skillagi", "agentUrl": "https://openagent3.xyz/skills/skillagi/agent", "manifestUrl": "https://openagent3.xyz/skills/skillagi/agent.json", "briefUrl": "https://openagent3.xyz/skills/skillagi/agent.md" } }