{ "schemaVersion": "1.0", "item": { "slug": "agi-term-helper", "name": "Agi Term Helper", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/liuwujijay/agi-term-helper", "canonicalUrl": "https://clawhub.ai/liuwujijay/agi-term-helper", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/agi-term-helper", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agi-term-helper", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "_meta.json" ], "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", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/agi-term-helper" }, "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/agi-term-helper", "agentPageUrl": "https://openagent3.xyz/skills/agi-term-helper/agent", "manifestUrl": "https://openagent3.xyz/skills/agi-term-helper/agent.json", "briefUrl": "https://openagent3.xyz/skills/agi-term-helper/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": "/term — direct terminal execution (exec dispatch)", "body": "/term is a power-user shortcut: whatever you type after /term is forwarded as-is to OpenClaw’s exec tool.\n\nThis is intentionally “manual mode”:\n\nYou (the user) provide the exact shell command.\nOpenClaw does not rewrite, expand, or “helpfully” change it.\nIt’s useful when you want quick, deterministic terminal actions without a planning loop." }, { "title": "How dispatch works (important)", "body": "OpenClaw supports command-dispatch: tool skills. When you run:\n\n/term ls -la\n\nthe raw argument string (ls -la) is forwarded to the configured tool (exec) without extra parsing. In tool-dispatch mode, OpenClaw invokes the tool with params shaped like:\n\n{ command: \"\", commandName: \"\", skillName: \"\" }\n\nSee the Skills docs section on command-dispatch, command-tool, and command-arg-mode. :contentReference[oaicite:10]{index=10}" }, { "title": "When to use /term vs normal “agent runs”", "body": "Use /term when:\n\nYou already know the exact command you want.\nYou want a quick read-only check (files, git status, grep).\nYou are debugging OpenClaw itself (skills folder, logs, Peekaboo bridge status).\n\nPrefer normal agent flow when:\n\nYou want the model to decide the best approach.\nThe task may need multiple steps, safety checks, or file edits." }, { "title": "Safety model (read this once, then follow it)", "body": "/term is equivalent to letting an assistant type into your terminal.\nGood defaults:\n\nPrefer read-only commands unless you mean to change state.\nAvoid secrets in command lines (tokens, API keys, cookies).\nAvoid remote execution one-liners:\n\nno curl ... | sh\nno “download and execute” pipelines\n\n\nIf the command could delete or overwrite files, slow down and double-check paths." }, { "title": "Host + sandbox notes", "body": "Your actual execution environment depends on how you invoke exec in your setup (sandbox vs host).\nAlso note: when a session is sandboxed, environment variables are not automatically inherited by the container; you must inject them via sandbox env settings or bake them into the image. :contentReference[oaicite:11]{index=11}" }, { "title": "Quick inspection (safe, read-only)", "body": "/term pwd\n/term ls -la\n/term git status\n/term rg -n \"TODO|FIXME\" ." }, { "title": "Debug Peekaboo bridge discovery (macOS)", "body": "/term peekaboo bridge status --verbose\n\nIf the output shows “no such file or directory” for all candidates and “Selected: local (in-process)”, you likely have no bridge host running (see troubleshooting below)." }, { "title": "One-liners for structured output", "body": "If you want JSON output for parsing:\n\n/term python -c 'import json,platform; print(json.dumps({\"py\":platform.python_version()}))'" }, { "title": "“command not found”", "body": "The tool runs in whatever PATH your OpenClaw runtime provides. If you rely on Homebrew, ensure the runtime sees /opt/homebrew/bin." }, { "title": "“permission denied” / macOS privacy prompts", "body": "Some tools (screen capture / UI automation) require Screen Recording / Accessibility. Those permissions are per-process context on macOS; using PeekabooBridge is often the reliable path for automation." }, { "title": "I need richer guidance and guardrails", "body": "Install/use the companion skill terminal-helper (model-invocable) which teaches safe patterns, confirmations, and runbooks." } ], "body": "/term — direct terminal execution (exec dispatch)\n\n/term is a power-user shortcut: whatever you type after /term is forwarded as-is to OpenClaw’s exec tool.\n\nThis is intentionally “manual mode”:\n\nYou (the user) provide the exact shell command.\nOpenClaw does not rewrite, expand, or “helpfully” change it.\nIt’s useful when you want quick, deterministic terminal actions without a planning loop.\nHow dispatch works (important)\n\nOpenClaw supports command-dispatch: tool skills. When you run:\n\n/term ls -la\n\nthe raw argument string (ls -la) is forwarded to the configured tool (exec) without extra parsing. In tool-dispatch mode, OpenClaw invokes the tool with params shaped like:\n\n{ command: \"\", commandName: \"\", skillName: \"\" }\n\nSee the Skills docs section on command-dispatch, command-tool, and command-arg-mode. :contentReference[oaicite:10]{index=10}\n\nWhen to use /term vs normal “agent runs”\n\nUse /term when:\n\nYou already know the exact command you want.\nYou want a quick read-only check (files, git status, grep).\nYou are debugging OpenClaw itself (skills folder, logs, Peekaboo bridge status).\n\nPrefer normal agent flow when:\n\nYou want the model to decide the best approach.\nThe task may need multiple steps, safety checks, or file edits.\nSafety model (read this once, then follow it)\n\n/term is equivalent to letting an assistant type into your terminal. Good defaults:\n\nPrefer read-only commands unless you mean to change state.\nAvoid secrets in command lines (tokens, API keys, cookies).\nAvoid remote execution one-liners:\nno curl ... | sh\nno “download and execute” pipelines\nIf the command could delete or overwrite files, slow down and double-check paths.\nHost + sandbox notes\n\nYour actual execution environment depends on how you invoke exec in your setup (sandbox vs host). Also note: when a session is sandboxed, environment variables are not automatically inherited by the container; you must inject them via sandbox env settings or bake them into the image. :contentReference[oaicite:11]{index=11}\n\nPractical examples\nQuick inspection (safe, read-only)\n/term pwd\n/term ls -la\n/term git status\n/term rg -n \"TODO|FIXME\" .\nDebug Peekaboo bridge discovery (macOS)\n/term peekaboo bridge status --verbose\n\nIf the output shows “no such file or directory” for all candidates and “Selected: local (in-process)”, you likely have no bridge host running (see troubleshooting below).\n\nOne-liners for structured output\n\nIf you want JSON output for parsing:\n\n/term python -c 'import json,platform; print(json.dumps({\"py\":platform.python_version()}))'\nTroubleshooting\n“command not found”\n\nThe tool runs in whatever PATH your OpenClaw runtime provides. If you rely on Homebrew, ensure the runtime sees /opt/homebrew/bin.\n\n“permission denied” / macOS privacy prompts\n\nSome tools (screen capture / UI automation) require Screen Recording / Accessibility. Those permissions are per-process context on macOS; using PeekabooBridge is often the reliable path for automation.\n\nI need richer guidance and guardrails\n\nInstall/use the companion skill terminal-helper (model-invocable) which teaches safe patterns, confirmations, and runbooks." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/liuwujijay/agi-term-helper", "publisherUrl": "https://clawhub.ai/liuwujijay/agi-term-helper", "owner": "liuwujijay", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/agi-term-helper", "downloadUrl": "https://openagent3.xyz/downloads/agi-term-helper", "agentUrl": "https://openagent3.xyz/skills/agi-term-helper/agent", "manifestUrl": "https://openagent3.xyz/skills/agi-term-helper/agent.json", "briefUrl": "https://openagent3.xyz/skills/agi-term-helper/agent.md" } }