[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77MM1JP2J03Y3F11WNGNFYF":3,"skill-same:01M77MM1JP2J03Y3F11WNGNFYF":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M77MM1JP2J03Y3F11WNGNFYF","global-agent-guardrails",null,"Configure the shared guard against catastrophic shell commands in local AI agents. Use when changing block patterns, adding an agent or machine, or investigating why a command was or wasn't blocked.","davidondrej\u002Fskills","davidondrej","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F131768515?v=4","01M77MHARFKYVNT9FV22807T8F","David Ondrej","01M77MHASHNDV507F9NTVKR2CY",4310,"MIT","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fglobal-agent-guardrails\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: global-agent-guardrails\ndescription: \"Configure the shared guard against catastrophic shell commands in local AI agents. Use when changing block patterns, adding an agent or machine, or investigating why a command was or wasn't blocked.\"\n---\n\n# Global Agent Guardrails\n\nBlock catastrophic shell commands before a coding agent runs them. One patterns file feeds a shared hook script, or a small native adapter, for each agent. This guards against accidents, not malicious agents: obfuscation like `python -c \"shutil.rmtree(...)\"` slips past any regex.\n\nThis is a generic recipe built on each tool's public hook system. [Cloudroom](https:\u002F\u002Fwww.cloudroom.dev\u002Fsecurity) ships a built-in Command Guard based on this design, on by default.\n\n## File map\n\n```\n~\u002F.agents\u002Fhooks\u002Fdangerous-patterns.txt   # THE denylist: one POSIX-ERE regex per line, # comments\n~\u002F.agents\u002Fhooks\u002Fdeny-dangerous.sh        # shared guard: hook JSON on stdin -> exit 2 blocks\n~\u002F.agents\u002Fhooks\u002Ftest-guard.sh            # test suite: run after ANY pattern change\n~\u002F.config\u002Fopencode\u002Fplugins\u002Fcommand-guard.ts   # OpenCode adapter (throws to block)\n~\u002F.pi\u002Fagent\u002Fextensions\u002Fcommand-guard.ts       # Pi adapter (returns {block:true})\n~\u002F.hermes\u002Fplugins\u002Fcommand-guard\u002F              # Hermes plugin (returns {\"action\":\"block\"})\n```\n\n## Check installation\n\n```bash\nls ~\u002F.agents\u002Fhooks\u002Fdeny-dangerous.sh ~\u002F.agents\u002Fhooks\u002Fdangerous-patterns.txt\n~\u002F.agents\u002Fhooks\u002Ftest-guard.sh   # must end \"failed: 0\"\n```\n\nIf missing, rebuild from the script below and the wiring table.\n\n## Guard script\n\n`deny-dangerous.sh` reads the hook JSON on stdin, pulls out the command, and tests it against every pattern. Its core:\n\n```bash\n#!\u002Fbin\u002Fbash\nPATTERNS=\"$HOME\u002F.agents\u002Fhooks\u002Fdangerous-patterns.txt\"\ncommand -v jq >\u002Fdev\u002Fnull || exit 0\nCMD=$(jq -r '.tool_input.command \u002F\u002F .toolInput.command \u002F\u002F .command \u002F\u002F empty' 2>\u002Fdev\u002Fnull)\n[ -n \"$CMD\" ] && [ -f \"$PATTERNS\" ] || exit 0\nwhile IFS= read -r pattern; do\n  case \"$pattern\" in ''|\\#*) continue ;; esac\n  if printf '%s\\n' \"$CMD\" | grep -qE -- \"$pattern\"; then\n    echo \"Blocked by the command guard. Matched: $pattern. Do not retry or work around it; tell the user.\" >&2\n    exit 2\n  fi\ndone \u003C \"$PATTERNS\"\n```\n\nCursor wants JSON instead of exit 2: with the `cursor` arg, print `{\"permission\":\"deny\",\"agent_message\":\"...\"}` or `{\"permission\":\"allow\"}` and exit 0.\n\n## Add or tune a pattern\n\n1. Edit `~\u002F.agents\u002Fhooks\u002Fdangerous-patterns.txt`. Write POSIX ERE (`grep -E`). Use `[[:space:]]`, never `\\s` — adapters auto-convert `[:space:]` to `\\s` for JS\u002FPython and compile in multiline mode.\n2. Add block and allow cases to `test-guard.sh`, then run it; all must pass.\n3. Verify the new pattern compiles in the adapter engines:\n\n```bash\npython3 -c 'import re,pathlib; [re.compile(l.strip().replace(\"[:space:]\",r\"\\s\"),re.M) for l in pathlib.Path.home().joinpath(\".agents\u002Fhooks\u002Fdangerous-patterns.txt\").read_text().splitlines() if l.strip() and not l.startswith(\"#\")]; print(\"ok\")'\n```\n\n4. Consumers re-read patterns for every command. Exception: Droid uses `commandBlocklist` in `~\u002F.factory\u002Fsettings.json` — mirror changes there manually.\n\nBlock only catastrophic commands: irreversible data loss, disk wipes, repo deletion, rewritten remote history. Recoverable local commands (`git status`, `git clean -fdx`, `rm -rf node_modules`) stay allowed. Over-blocking trains people to turn the guard off.\n\nEach group in the patterns file has a comment saying what it blocks and what deliberately stays allowed. Read those comments before changing a pattern, and keep them current.\n\n## Per-agent wiring (user-global)\n\n| Agent | Config | Event | Blocks via |\n|---|---|---|---|\n| Claude Code | `~\u002F.claude\u002Fsettings.json` | `PreToolUse` matcher `Bash` | shared script, exit 2 |\n| Codex CLI\u002Fapp\u002FIDE | `~\u002F.codex\u002Fhooks.json` | `PreToolUse` matcher `Bash` | shared script, exit 2 |\n| Cursor IDE + CLI | `~\u002F.cursor\u002Fhooks.json` | `beforeShellExecution` | shared script with `cursor` arg, deny JSON |\n| Grok (xAI) | auto-loads Claude + Cursor hook files (compat on by default); native option `~\u002F.grok\u002Fhooks\u002F*.json` | `PreToolUse` | shared script (reads `.toolInput.command`) |\n| OpenCode | `~\u002F.config\u002Fopencode\u002Fplugins\u002Fcommand-guard.ts` | `tool.execute.before` | adapter throws Error |\n| Pi | `~\u002F.pi\u002Fagent\u002Fextensions\u002Fcommand-guard.ts` | `pi.on(\"tool_call\")` | adapter returns `{block:true}` |\n| Hermes | `~\u002F.hermes\u002Fplugins\u002Fcommand-guard\u002F` (`plugin.yaml` + `__init__.py`) | `pre_tool_call` hook | plugin returns `{\"action\":\"block\"}` |\n| Droid (Factory) | `~\u002F.factory\u002Fsettings.json` | native `commandBlocklist` | hard-block, no approval possible |\n| Devin CLI | `~\u002F.config\u002Fdevin\u002Fconfig.json` | `PreToolUse` matcher `^exec$` | shared script, exit 2 |\n\nClaude\u002FCodex hook entry; for Devin, replace `Bash` with `^exec$`. Merge into the existing `hooks` object; never overwrite it:\n\n```json\n{\"hooks\": {\"PreToolUse\": [{\"matcher\": \"Bash\", \"hooks\": [{\"type\": \"command\", \"command\": \"\u002FABSOLUTE\u002FHOME\u002F.agents\u002Fhooks\u002Fdeny-dangerous.sh\"}]}]}}\n```\n\nCursor entry (payload has `.command`, so pass the `cursor` arg):\n\n```json\n{\"beforeShellExecution\": [{\"command\": \"\u002FABSOLUTE\u002FHOME\u002F.agents\u002Fhooks\u002Fdeny-dangerous.sh cursor\", \"failClosed\": false}]}\n```\n\nUse absolute paths in configs (`~` expansion is inconsistent across agents).\n\n## Tool behavior to know\n\n- **Codex trust is hash-pinned.** Any edit to the hook ENTRY in `hooks.json` (not the patterns file) invalidates trust. Run `\u002Fhooks` in Codex and re-trust, or Codex skips the hook. Trust hashes live in `[hooks.state]` in `~\u002F.codex\u002Fconfig.toml` and are shared by CLI, desktop app, and IDE extension. CI\u002Fscripts: `--dangerously-bypass-hook-trust`.\n- **Cursor: set `failClosed` to `false`.** Cursor's background\u002Fworker hosts cannot execute hook scripts, so fail-closed blocks EVERY command there.\n- **Hermes plugin manifest key is `provides_hooks`** (not `hooks`). The plugin must be listed under `plugins.enabled` in `~\u002F.hermes\u002Fconfig.yaml` (the `hermes plugins enable` CLI prompts interactively and hangs non-interactive shells). Hermes skips a hook that throws, so keep the plugin trivial. Shell tool name is `terminal`.\n- **Pi blocks the tool when a `tool_call` handler throws.** The adapter must catch its own errors, or a broken patterns file bricks every bash call.\n- **Droid semantics:** `commandDenylist` = ask for confirmation; `commandBlocklist` = never runs, even at full autonomy with `--skip-permissions-unsafe`. Use the blocklist for catastrophic entries.\n- **Payload shapes:** the command lives at `.tool_input.command` (Claude\u002FCodex\u002FDevin), `.toolInput.command` (Grok), `.command` (Cursor). Keep all three in the jq fallback chain.\n- **Adapter regexes require multiline mode.** Keep JavaScript's `m` flag and Python's `re.M` so `^` matches each shell line like `grep`.\n- **False-positive class:** a harmless command whose ARGUMENT text contains a dangerous-looking string (e.g. passing a prompt mentioning `git push --force` on a CLI) gets blocked. Workaround: put the text in a file and reference it.\n- **No pre-command hook (as of 2026-07):** Gemini CLI, Qwen Code, Amp, kimi-cli. Cloud-hosted runs (Codex cloud tasks, Cursor background agents) do not load local hooks either.\n\n## E2E verification\n\nSafe probe: ask the agent to run `git push --force` from a NON-git directory — blocked = guard works; \"not a git repository\" = guard failed but no harm done.\n\n```bash\ncd \"$(mktemp -d)\"\nclaude -p 'Run exactly: git push --force. Report the result in one line.' --permission-mode bypassPermissions\ncodex exec --skip-git-repo-check 'Run exactly: git push --force. Report the result in one line.' \u003C \u002Fdev\u002Fnull\ndroid exec --auto high -f prompt.txt        # prompt text in a file (see false-positive gotcha)\npi -p --no-session 'Run exactly: git push --force. Report the result in one line.'\nhermes chat --query 'Run exactly this terminal command: git push --force. Report in one line.'\n```\n\nDirect script test:\n\n```bash\necho '{\"tool_input\":{\"command\":\"rm -rf \u002F\"}}' | ~\u002F.agents\u002Fhooks\u002Fdeny-dangerous.sh; echo \"exit=$?\"   # expect exit=2\n```\n","# Global Agent Guardrails\n\nBlock catastrophic shell commands before a coding agent runs them. One patterns file feeds a shared hook script, or a small native adapter, for each agent. This guards against accidents, not malicious agents: obfuscation like `python -c \"shutil.rmtree(...)\"` slips past any regex.\n\nThis is a generic recipe built on each tool's public hook system. [Cloudroom](https:\u002F\u002Fwww.cloudroom.dev\u002Fsecurity) ships a built-in Command Guard based on this design, on by default.\n\n## File map\n\n```\n~\u002F.agents\u002Fhooks\u002Fdangerous-patterns.txt   # THE denylist: one POSIX-ERE regex per line, # comments\n~\u002F.agents\u002Fhooks\u002Fdeny-dangerous.sh        # shared guard: hook JSON on stdin -> exit 2 blocks\n~\u002F.agents\u002Fhooks\u002Ftest-guard.sh            # test suite: run after ANY pattern change\n~\u002F.config\u002Fopencode\u002Fplugins\u002Fcommand-guard.ts   # OpenCode adapter (throws to block)\n~\u002F.pi\u002Fagent\u002Fextensions\u002Fcommand-guard.ts       # Pi adapter (returns {block:true})\n~\u002F.hermes\u002Fplugins\u002Fcommand-guard\u002F              # Hermes plugin (returns {\"action\":\"block\"})\n```\n\n## Check installation\n\n```bash\nls ~\u002F.agents\u002Fhooks\u002Fdeny-dangerous.sh ~\u002F.agents\u002Fhooks\u002Fdangerous-patterns.txt\n~\u002F.agents\u002Fhooks\u002Ftest-guard.sh   # must end \"failed: 0\"\n```\n\nIf missing, rebuild from the script below and the wiring table.\n\n## Guard script\n\n`deny-dangerous.sh` reads the hook JSON on stdin, pulls out the command, and tests it against every pattern. Its core:\n\n```bash\n#!\u002Fbin\u002Fbash\nPATTERNS=\"$HOME\u002F.agents\u002Fhooks\u002Fdangerous-patterns.txt\"\ncommand -v jq >\u002Fdev\u002Fnull || exit 0\nCMD=$(jq -r '.tool_input.command \u002F\u002F .toolInput.command \u002F\u002F .command \u002F\u002F empty' 2>\u002Fdev\u002Fnull)\n[ -n \"$CMD\" ] && [ -f \"$PATTERNS\" ] || exit 0\nwhile IFS= read -r pattern; do\n  case \"$pattern\" in ''|\\#*) continue ;; esac\n  if printf '%s\\n' \"$CMD\" | grep -qE -- \"$pattern\"; then\n    echo \"Blocked by the command guard. Matched: $pattern. Do not retry or work around it; tell the user.\" >&2\n    exit 2\n  fi\ndone \u003C \"$PATTERNS\"\n```\n\nCursor wants JSON instead of exit 2: with the `cursor` arg, print `{\"permission\":\"deny\",\"agent_message\":\"...\"}` or `{\"permission\":\"allow\"}` and exit 0.\n\n## Add or tune a pattern\n\n1. Edit `~\u002F.agents\u002Fhooks\u002Fdangerous-patterns.txt`. Write POSIX ERE (`grep -E`). Use `[[:space:]]`, never `\\s` — adapters auto-convert `[:space:]` to `\\s` for JS\u002FPython and compile in multiline mode.\n2. Add block and allow cases to `test-guard.sh`, then run it; all must pass.\n3. Verify the new pattern compiles in the adapter engines:\n\n```bash\npython3 -c 'import re,pathlib; [re.compile(l.strip().replace(\"[:space:]\",r\"\\s\"),re.M) for l in pathlib.Path.home().joinpath(\".agents\u002Fhooks\u002Fdangerous-patterns.txt\").read_text().splitlines() if l.strip() and not l.startswith(\"#\")]; print(\"ok\")'\n```\n\n4. Consumers re-read patterns for every command. Exception: Droid uses `commandBlocklist` in `~\u002F.factory\u002Fsettings.json` — mirror changes there manually.\n\nBlock only catastrophic commands: irreversible data loss, disk wipes, repo deletion, rewritten remote history. Recoverable local commands (`git status`, `git clean -fdx`, `rm -rf node_modules`) stay allowed. Over-blocking trains people to turn the guard off.\n\nEach group in the patterns file has a comment saying what it blocks and what deliberately stays allowed. Read those comments before changing a pattern, and keep them current.\n\n## Per-agent wiring (user-global)\n\n| Agent | Config | Event | Blocks via |\n|---|---|---|---|\n| Claude Code | `~\u002F.claude\u002Fsettings.json` | `PreToolUse` matcher `Bash` | shared script, exit 2 |\n| Codex CLI\u002Fapp\u002FIDE | `~\u002F.codex\u002Fhooks.json` | `PreToolUse` matcher `Bash` | shared script, exit 2 |\n| Cursor IDE + CLI | `~\u002F.cursor\u002Fhooks.json` | `beforeShellExecution` | shared script with `cursor` arg, deny JSON |\n| Grok (xAI) | auto-loads Claude + Cursor hook files (compat on by default); native option `~\u002F.grok\u002Fhooks\u002F*.json` | `PreToolUse` | shared script (reads `.toolInput.command`) |\n| OpenCode | `~\u002F.config\u002Fopencode\u002Fplugins\u002Fcommand-guard.ts` | `tool.execute.before` | adapter throws Error |\n| Pi | `~\u002F.pi\u002Fagent\u002Fextensions\u002Fcommand-guard.ts` | `pi.on(\"tool_call\")` | adapter returns `{block:true}` |\n| Hermes | `~\u002F.hermes\u002Fplugins\u002Fcommand-guard\u002F` (`plugin.yaml` + `__init__.py`) | `pre_tool_call` hook | plugin returns `{\"action\":\"block\"}` |\n| Droid (Factory) | `~\u002F.factory\u002Fsettings.json` | native `commandBlocklist` | hard-block, no approval possible |\n| Devin CLI | `~\u002F.config\u002Fdevin\u002Fconfig.json` | `PreToolUse` matcher `^exec$` | shared script, exit 2 |\n\nClaude\u002FCodex hook entry; for Devin, replace `Bash` with `^exec$`. Merge into the existing `hooks` object; never overwrite it:\n\n```json\n{\"hooks\": {\"PreToolUse\": [{\"matcher\": \"Bash\", \"hooks\": [{\"type\": \"command\", \"command\": \"\u002FABSOLUTE\u002FHOME\u002F.agents\u002Fhooks\u002Fdeny-dangerous.sh\"}]}]}}\n```\n\nCursor entry (payload has `.command`, so pass the `cursor` arg):\n\n```json\n{\"beforeShellExecution\": [{\"command\": \"\u002FABSOLUTE\u002FHOME\u002F.agents\u002Fhooks\u002Fdeny-dangerous.sh cursor\", \"failClosed\": false}]}\n```\n\nUse absolute paths in configs (`~` expansion is inconsistent across agents).\n\n## Tool behavior to know\n\n- **Codex trust is hash-pinned.** Any edit to the hook ENTRY in `hooks.json` (not the patterns file) invalidates trust. Run `\u002Fhooks` in Codex and re-trust, or Codex skips the hook. Trust hashes live in `[hooks.state]` in `~\u002F.codex\u002Fconfig.toml` and are shared by CLI, desktop app, and IDE extension. CI\u002Fscripts: `--dangerously-bypass-hook-trust`.\n- **Cursor: set `failClosed` to `false`.** Cursor's background\u002Fworker hosts cannot execute hook scripts, so fail-closed blocks EVERY command there.\n- **Hermes plugin manifest key is `provides_hooks`** (not `hooks`). The plugin must be listed under `plugins.enabled` in `~\u002F.hermes\u002Fconfig.yaml` (the `hermes plugins enable` CLI prompts interactively and hangs non-interactive shells). Hermes skips a hook that throws, so keep the plugin trivial. Shell tool name is `terminal`.\n- **Pi blocks the tool when a `tool_call` handler throws.** The adapter must catch its own errors, or a broken patterns file bricks every bash call.\n- **Droid semantics:** `commandDenylist` = ask for confirmation; `commandBlocklist` = never runs, even at full autonomy with `--skip-permissions-unsafe`. Use the blocklist for catastrophic entries.\n- **Payload shapes:** the command lives at `.tool_input.command` (Claude\u002FCodex\u002FDevin), `.toolInput.command` (Grok), `.command` (Cursor). Keep all three in the jq fallback chain.\n- **Adapter regexes require multiline mode.** Keep JavaScript's `m` flag and Python's `re.M` so `^` matches each shell line like `grep`.\n- **False-positive class:** a harmless command whose ARGUMENT text contains a dangerous-looking string (e.g. passing a prompt mentioning `git push --force` on a CLI) gets blocked. Workaround: put the text in a file and reference it.\n- **No pre-command hook (as of 2026-07):** Gemini CLI, Qwen Code, Amp, kimi-cli. Cloud-hosted runs (Codex cloud tasks, Cursor background agents) do not load local hooks either.\n\n## E2E verification\n\nSafe probe: ask the agent to run `git push --force` from a NON-git directory — blocked = guard works; \"not a git repository\" = guard failed but no harm done.\n\n```bash\ncd \"$(mktemp -d)\"\nclaude -p 'Run exactly: git push --force. Report the result in one line.' --permission-mode bypassPermissions\ncodex exec --skip-git-repo-check 'Run exactly: git push --force. Report the result in one line.' \u003C \u002Fdev\u002Fnull\ndroid exec --auto high -f prompt.txt        # prompt text in a file (see false-positive gotcha)\npi -p --no-session 'Run exactly: git push --force. Report the result in one line.'\nhermes chat --query 'Run exactly this terminal command: git push --force. Report in one line.'\n```\n\nDirect script test:\n\n```bash\necho '{\"tool_input\":{\"command\":\"rm -rf \u002F\"}}' | ~\u002F.agents\u002Fhooks\u002Fdeny-dangerous.sh; echo \"exit=$?\"   # expect exit=2\n```\n",{"name":5,"description":7},"main","a9d4ad810cf3c303fde23bdcd5fc86df7c57daf3","skills\u002Fglobal-agent-guardrails",626,"https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills","https:\u002F\u002Fwww.cloudroom.dev","https:\u002F\u002Fgithub.com\u002Fdavidondrej","https:\u002F\u002Fwww.cloudroom.dev\u002F","founder of Cloudroom","2026-11-14 10:00:36",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add davidondrej\u002Fskills --skill global-agent-guardrails",{"tool":40,"command":41},"bunx","bunx skills add davidondrej\u002Fskills --skill global-agent-guardrails",{"tool":43,"command":44},"pnpm","pnpm dlx skills add davidondrej\u002Fskills --skill global-agent-guardrails","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fglobal-agent-guardrails\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M77MPMR6DE13EZFSMY76S6YB","varied-search","Research a topic across the web, GitHub, and X\u002FTwitter with DeepAPI and produce a concise Markdown report. Use for varied-search or requests to compare web coverage, relevant repositories, and social discussion.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fvaried-search\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M77MPG5F9H2JBW4VFHBY1VSM","total-review","Run five independent max-effort reviews (Fable 5.1, Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, Muse Wonder), merge their findings, and fix only what the user approves. Use for \u002Ftotal-review, or when the user or another agent asks for a total review.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftotal-review\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M77MP8XZJ42ZJZQV8C76B353","stop-overthinking","Manually-invoked skill that stops overthinking and forces a short, practical decision. Use only when the user explicitly invokes stop-overthinking.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fstop-overthinking\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M77MP5EGQSNF1VS9SY8CK60Q","state","Manually-invoked skill that recaps what the current thread is doing and how far along it is. Use when the user says \"state\", \"where are we\", or \"what % are we done\".","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fstate\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M77MP2H479SWAP7687RAVG7T","setup-help","Guide setup one step at a time and show what remains. Use only when the user explicitly asks for it by name.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fsetup-help\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M77MNZV9X8NPC9JZMWP8WAF8","self-archive","Archive the current Cloudroom thread and release its runtime. Use only when the user explicitly asks to self-archive, archive yourself, or archive this thread.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fself-archive\u002FSKILL.md",[],[]]