[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GWQVP6ECSSP7YE0AXZESGD":3,"skill-same:01M6GWQVP6ECSSP7YE0AXZESGD":102},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":24,"publishedAt":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":59,"commitSha":60,"skillDirectory":61,"forksCount":62,"repositoryHtmlUrl":63,"repositoryHomepageUrl":6,"ownerHtmlUrl":64,"ownerBlogUrl":65,"ownerDescription":66,"updatedAt":67,"install":68,"resources":81},"01M6GWQVP6ECSSP7YE0AXZESGD","handoff-mesh",null,"Built-in communication layer for multi-agent setups. Full-mesh handoff folders (any agent can hand off to any other), an hourly watcher that surfaces open handoffs, weekly archive cleanup, and a completion-reporting loop so every handoff is handled AND verified. The durable 'brain' counterpart to real-time channels like Buzz.","jiayaoqijia\u002Fcryptoskill","jiayaoqijia","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1453879?v=4","01M6GMYTX7Q7S504VC6E756ENR","YQ","01M6GMYV1QKJ1CC75MTTGT9PR0",81,"MIT","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fgentech-labs-handoff-mesh\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fgentech-labs-handoff-mesh\u002FSKILL.md",[19],{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"mesh","handoff","handoff mesh","weekly","verified","watcher","layer","hand","can","channels","multi","buzz","brain","time","surfaces","multi-agent","coordination","archive","loop","open","vault","real-time","reporting","communication","inbox","cleanup","2026-11-10 10:12:30",false,"---\nname: handoff-mesh\ndescription: \"Built-in communication layer for multi-agent setups. Full-mesh handoff folders (any agent can hand off to any other), an hourly watcher that surfaces open handoffs, weekly archive cleanup, and a completion-reporting loop so every handoff is handled AND verified. The durable 'brain' counterpart to real-time channels like Buzz.\"\nversion: 1.2.0\nauthor: Gentech\ntags: [handoff, coordination, multi-agent, mesh, inbox, communication, vault]\nlicense: MIT\n---\n\n# Handoff Mesh — Communication Layer for Multi-Agent Setups\n\n## When to Use\n- You run **more than one agent** (multi-agent strategy) and they need to hand work to each other.\n- An agent finishes something and another agent (or a human) needs to pick it up.\n- You want a **durable, searchable** coordination layer — not just real-time chat.\n- You want to know, at a glance, what handoffs are open and whether they got done.\n\n## What This Is\nA **full-mesh handoff system** built on the vault (Obsidian) — the durable brain.\nAny agent can drop a handoff into any other agent's inbox. A watcher surfaces\nopen handoffs hourly. Nightly maintenance archives old ones. And a\ncompletion-reporting loop closes the deal: the agent that reads a handoff\nreports back what it did before it's marked resolved.\n\nThis is the **storage + verification** half of agent communication. Real-time\nchannels (Buzz, Telegram) are the *talking* half; this is the *remembering and\nproving* half. They complement each other — the vault stays the source of truth.\n\n## The Layout\n```\n01-HANDOFFS\u002F\n    INBOX\u002F\n        \u003Cgroup>\u002F                    ← one receive folder per agent\u002Fgroup\n            \u003CYYYY-MM-DD>-\u003Ctopic>.md ← a handoff note for that agent\n            _archive\u002F               ← resolved notes (auto-moved, purged weekly)\n    \u003Cfrom>-to-\u003Cto>\u002F                 ← optional explicit sender→receiver folders\n```\n\n## The Protocol (4 steps — the loop)\n\n### Step 1 — SEND: drop a handoff into the target's inbox\nWrite `\u003Cdate>-\u003Ctopic>.md` into the target group's `INBOX\u002F\u003Cgroup>\u002F` folder.\nFormat:\n```markdown\n# \u003Ctopic>\n**From:** \u003Cagent\u002Fgroup>\n**To:** \u003Cgroup>\n**Date:** \u003CYYYY-MM-DD>\n**Status:** open\n\n## What's needed\n\u003Cwhat the receiving agent should do>\n\n## Context \u002F files\n\u003Cany links or paths>\n```\nCommit + push (or `ob sync`).\n\n### Step 2 — WATCH: surface open handoffs automatically\nRun the watcher hourly (or on each agent's wake-up). It scans every inbox lane\nand reports any note still `Status: open` (not resolved, not archived).\n```bash\npython3 handoff-watcher.py [vault_path]\n```\n- **Silent when clear** — only pings when there's actually something to do.\n- **Quiet overnight** — schedule it for waking hours only (e.g. 7 AM–11 PM ET).\n- Wire it as a `no_agent` cron (pure script, zero tokens) so it's cheap.\n\n### Step 3 — ACT + REPORT: the agent that reads it reports back\nThis is the half that makes handoffs *verified*, not just *seen*:\n1. **Read** the handoff → acknowledge it in the group (never silent).\n2. **Act** on it.\n3. **Report back** — post a short \"done \u002F what I did\" note to the sender's lane\n   or the group, so the loop closes. This is the completion-reporting rule.\n4. **Mark resolved + archive** only AFTER the work is verified.\n\n### Step 4 — CLEAN: archive weekly so it never gets too big\nNightly\u002Fweekly maintenance:\n- Move resolved notes to `_archive\u002F`.\n- **Purge `_archive\u002F` entries older than 7 days.**\n- Auto-archive stale OPEN notes older than 7 days (still unresolved).\n\n## The Watcher Script\n`handoff-watcher.py` (stdlib-only, stable output — safe as a `monitor_script`):\n- Lists every `\u003Cgroup>\u002F` subfolder under `INBOX\u002F`.\n- Finds `*.md` notes NOT in `_archive\u002F` and NOT marked resolved.\n- **STATEFUL — reports only NEW changes.** It keeps a state file\n  (`handoff-watcher.state.json`) of what it already reported, and only prints:\n  - ? NEW open handoffs (appeared since last run)\n  - ✅ CLEARED handoffs (were open, now resolved)\n  - ? NEW recent completions (`--days N`)\n- **Silent when nothing changed** — if no handoff appeared\u002Fcleared and no new\n  completion, it prints NOTHING, so the cron stays quiet until there's a real\n  signal. This is the watchdog pattern: report only what's new, not everything\n  every time.\n- **Also surfaces recent completions** by scanning each group's\n  `\u003Cgroup>-completions.md` — so you see what agents actually shipped, not just\n  what's open. Add `--days N` to widen the window.\n- **Tappable Obsidian deep-links** — every open handoff prints an\n  `obsidian:\u002F\u002Fopen?vault=NAME&file=...` link that opens the note in the\n  user's Obsidian app. Set your vault name via `--vault-name NAME` (or edit\n  `VAULT_NAME` in the script). The links only open if the note has synced to\n  the device (Obsidian Sync) first.\n\nWire it as a `no_agent` cron with the **empty-stdout = silent** semantics:\nnon-empty output is delivered, empty output posts nothing. State file keeps it\nquiet between genuine changes.\n\nExample:\n```bash\n# Daily window of 2 days, vault named \"gentech\":\npython3 handoff-watcher.py --days 2 --vault-name gentech\n```\n\n## Second Brain Setup Preset — wire a new agent's brain in one go\nUse this when someone adds a **new agent \u002F second brain** to an existing\nfleet. It wires the full mesh so the new agent reads and acts on handoffs\nautomatically, out of the box:\n\n1. **Create the inbox lanes** for the new agent under `01-HANDOFFS\u002FINBOX\u002F`:\n   ```\n   01-HANDOFFS\u002FINBOX\u002F\u003Cnewgroup>\u002F\n       _archive\u002F          # resolved notes (auto-moved, purged weekly)\n   ```\n   Add `\u003Cnewgroup>` to `KNOWN_GROUPS` in `handoff-watcher.py`.\n\n2. **Create the completion file** so the watcher can report what this agent ships:\n   `01-HANDOFFS\u002F\u003Cnewgroup>-completions.md` (start with `# \u003CGroup> Completions`).\n\n3. **Install the skill** on the new profile:\n   ```bash\n   # copy the whole handoff-mesh skill dir into the new profile's skills\n   cp -r skills\u002Fhandoff-mesh \u002Froot\u002F.hermes\u002Fprofiles\u002F\u003Cnew>\u002Fskills\u002F\n   ```\n   Copy `scripts\u002Fhandoff-watcher.py` to `\u002Froot\u002F.hermes\u002Fprofiles\u002F\u003Cnew>\u002Fscripts\u002F`.\n\n4. **Wire the cron** (`no_agent`, pure script, zero tokens). Create with\n   Hermes cron, `script=handoff-watcher.py`, `deliver=origin`, schedule\n   `*\u002F15 11-23,0-3 * * *` (every 15 min, 7 AM–11 PM ET) — or any waking-hours\n   cadence. Set `--vault-name \u003Cyour-vault>` in the script args so the links\n   open correctly.\n\n5. **Consolidate with wake-up**: patch the new profile's wake-up-protocol\n   Step 3 to (a) check the INBOX for open handoffs, and (b) report a\n   completion note back to the sender before marking resolved. This makes the\n   loop (read → act → report → resolve) run on every session start.\n\nOnce wired, the new agent's watcher fires every 15 min, surfaces open handoffs\nwith tappable Obsidian links + recent completions, and the agent's wake-up\ncloses the loop — all fleet-wide, all zero-token.\n\n## Decision Table\n| Situation | Action |\n|-----------|--------|\n| Agent A finishes work for Agent B | A writes handoff to B's inbox |\n| Handoff sits open >1 hour | Watcher surfaces it; B picks it up |\n| B reads the handoff | B acknowledges + acts + reports back |\n| B completes the work | B marks resolved + archives, reports what it did |\n| Handoff unresolved >7 days | Nightly maintenance auto-archives it |\n\n## Pitfalls\n- **Reading without reporting** — a handoff archived as \"resolved\" with no\n  completion note is a silent failure. Always report what you did.\n- **No archive cleanup** — inboxes grow unbounded. Purge `_archive\u002F` weekly.\n- **Watcher pinging overnight** — schedule it for waking hours only.\n- **Only watching your own inbox** — in a mesh, check ALL lanes; any agent can\n  hand off to any other.\n- **Real-time chat ≠ durable record** — keep the handoff in the vault; chat is\n  for talking, the vault is for remembering.\n\n## Verification\n- [ ] Every agent\u002Fgroup has an `INBOX\u002F\u003Cgroup>\u002F` folder + `_archive\u002F`.\n- [ ] Watcher surfaces open handoffs hourly (silent when clear).\n- [ ] Agent that reads a handoff reports back what it did.\n- [ ] Resolved notes archived; `_archive\u002F` purged weekly.\n- [ ] No handoff left unread or unreported at a stopping point.\n","# Handoff Mesh — Communication Layer for Multi-Agent Setups\n\n## When to Use\n- You run **more than one agent** (multi-agent strategy) and they need to hand work to each other.\n- An agent finishes something and another agent (or a human) needs to pick it up.\n- You want a **durable, searchable** coordination layer — not just real-time chat.\n- You want to know, at a glance, what handoffs are open and whether they got done.\n\n## What This Is\nA **full-mesh handoff system** built on the vault (Obsidian) — the durable brain.\nAny agent can drop a handoff into any other agent's inbox. A watcher surfaces\nopen handoffs hourly. Nightly maintenance archives old ones. And a\ncompletion-reporting loop closes the deal: the agent that reads a handoff\nreports back what it did before it's marked resolved.\n\nThis is the **storage + verification** half of agent communication. Real-time\nchannels (Buzz, Telegram) are the *talking* half; this is the *remembering and\nproving* half. They complement each other — the vault stays the source of truth.\n\n## The Layout\n```\n01-HANDOFFS\u002F\n    INBOX\u002F\n        \u003Cgroup>\u002F                    ← one receive folder per agent\u002Fgroup\n            \u003CYYYY-MM-DD>-\u003Ctopic>.md ← a handoff note for that agent\n            _archive\u002F               ← resolved notes (auto-moved, purged weekly)\n    \u003Cfrom>-to-\u003Cto>\u002F                 ← optional explicit sender→receiver folders\n```\n\n## The Protocol (4 steps — the loop)\n\n### Step 1 — SEND: drop a handoff into the target's inbox\nWrite `\u003Cdate>-\u003Ctopic>.md` into the target group's `INBOX\u002F\u003Cgroup>\u002F` folder.\nFormat:\n```markdown\n# \u003Ctopic>\n**From:** \u003Cagent\u002Fgroup>\n**To:** \u003Cgroup>\n**Date:** \u003CYYYY-MM-DD>\n**Status:** open\n\n## What's needed\n\u003Cwhat the receiving agent should do>\n\n## Context \u002F files\n\u003Cany links or paths>\n```\nCommit + push (or `ob sync`).\n\n### Step 2 — WATCH: surface open handoffs automatically\nRun the watcher hourly (or on each agent's wake-up). It scans every inbox lane\nand reports any note still `Status: open` (not resolved, not archived).\n```bash\npython3 handoff-watcher.py [vault_path]\n```\n- **Silent when clear** — only pings when there's actually something to do.\n- **Quiet overnight** — schedule it for waking hours only (e.g. 7 AM–11 PM ET).\n- Wire it as a `no_agent` cron (pure script, zero tokens) so it's cheap.\n\n### Step 3 — ACT + REPORT: the agent that reads it reports back\nThis is the half that makes handoffs *verified*, not just *seen*:\n1. **Read** the handoff → acknowledge it in the group (never silent).\n2. **Act** on it.\n3. **Report back** — post a short \"done \u002F what I did\" note to the sender's lane\n   or the group, so the loop closes. This is the completion-reporting rule.\n4. **Mark resolved + archive** only AFTER the work is verified.\n\n### Step 4 — CLEAN: archive weekly so it never gets too big\nNightly\u002Fweekly maintenance:\n- Move resolved notes to `_archive\u002F`.\n- **Purge `_archive\u002F` entries older than 7 days.**\n- Auto-archive stale OPEN notes older than 7 days (still unresolved).\n\n## The Watcher Script\n`handoff-watcher.py` (stdlib-only, stable output — safe as a `monitor_script`):\n- Lists every `\u003Cgroup>\u002F` subfolder under `INBOX\u002F`.\n- Finds `*.md` notes NOT in `_archive\u002F` and NOT marked resolved.\n- **STATEFUL — reports only NEW changes.** It keeps a state file\n  (`handoff-watcher.state.json`) of what it already reported, and only prints:\n  - ? NEW open handoffs (appeared since last run)\n  - ✅ CLEARED handoffs (were open, now resolved)\n  - ? NEW recent completions (`--days N`)\n- **Silent when nothing changed** — if no handoff appeared\u002Fcleared and no new\n  completion, it prints NOTHING, so the cron stays quiet until there's a real\n  signal. This is the watchdog pattern: report only what's new, not everything\n  every time.\n- **Also surfaces recent completions** by scanning each group's\n  `\u003Cgroup>-completions.md` — so you see what agents actually shipped, not just\n  what's open. Add `--days N` to widen the window.\n- **Tappable Obsidian deep-links** — every open handoff prints an\n  `obsidian:\u002F\u002Fopen?vault=NAME&file=...` link that opens the note in the\n  user's Obsidian app. Set your vault name via `--vault-name NAME` (or edit\n  `VAULT_NAME` in the script). The links only open if the note has synced to\n  the device (Obsidian Sync) first.\n\nWire it as a `no_agent` cron with the **empty-stdout = silent** semantics:\nnon-empty output is delivered, empty output posts nothing. State file keeps it\nquiet between genuine changes.\n\nExample:\n```bash\n# Daily window of 2 days, vault named \"gentech\":\npython3 handoff-watcher.py --days 2 --vault-name gentech\n```\n\n## Second Brain Setup Preset — wire a new agent's brain in one go\nUse this when someone adds a **new agent \u002F second brain** to an existing\nfleet. It wires the full mesh so the new agent reads and acts on handoffs\nautomatically, out of the box:\n\n1. **Create the inbox lanes** for the new agent under `01-HANDOFFS\u002FINBOX\u002F`:\n   ```\n   01-HANDOFFS\u002FINBOX\u002F\u003Cnewgroup>\u002F\n       _archive\u002F          # resolved notes (auto-moved, purged weekly)\n   ```\n   Add `\u003Cnewgroup>` to `KNOWN_GROUPS` in `handoff-watcher.py`.\n\n2. **Create the completion file** so the watcher can report what this agent ships:\n   `01-HANDOFFS\u002F\u003Cnewgroup>-completions.md` (start with `# \u003CGroup> Completions`).\n\n3. **Install the skill** on the new profile:\n   ```bash\n   # copy the whole handoff-mesh skill dir into the new profile's skills\n   cp -r skills\u002Fhandoff-mesh \u002Froot\u002F.hermes\u002Fprofiles\u002F\u003Cnew>\u002Fskills\u002F\n   ```\n   Copy `scripts\u002Fhandoff-watcher.py` to `\u002Froot\u002F.hermes\u002Fprofiles\u002F\u003Cnew>\u002Fscripts\u002F`.\n\n4. **Wire the cron** (`no_agent`, pure script, zero tokens). Create with\n   Hermes cron, `script=handoff-watcher.py`, `deliver=origin`, schedule\n   `*\u002F15 11-23,0-3 * * *` (every 15 min, 7 AM–11 PM ET) — or any waking-hours\n   cadence. Set `--vault-name \u003Cyour-vault>` in the script args so the links\n   open correctly.\n\n5. **Consolidate with wake-up**: patch the new profile's wake-up-protocol\n   Step 3 to (a) check the INBOX for open handoffs, and (b) report a\n   completion note back to the sender before marking resolved. This makes the\n   loop (read → act → report → resolve) run on every session start.\n\nOnce wired, the new agent's watcher fires every 15 min, surfaces open handoffs\nwith tappable Obsidian links + recent completions, and the agent's wake-up\ncloses the loop — all fleet-wide, all zero-token.\n\n## Decision Table\n| Situation | Action |\n|-----------|--------|\n| Agent A finishes work for Agent B | A writes handoff to B's inbox |\n| Handoff sits open >1 hour | Watcher surfaces it; B picks it up |\n| B reads the handoff | B acknowledges + acts + reports back |\n| B completes the work | B marks resolved + archives, reports what it did |\n| Handoff unresolved >7 days | Nightly maintenance auto-archives it |\n\n## Pitfalls\n- **Reading without reporting** — a handoff archived as \"resolved\" with no\n  completion note is a silent failure. Always report what you did.\n- **No archive cleanup** — inboxes grow unbounded. Purge `_archive\u002F` weekly.\n- **Watcher pinging overnight** — schedule it for waking hours only.\n- **Only watching your own inbox** — in a mesh, check ALL lanes; any agent can\n  hand off to any other.\n- **Real-time chat ≠ durable record** — keep the handoff in the vault; chat is\n  for talking, the vault is for remembering.\n\n## Verification\n- [ ] Every agent\u002Fgroup has an `INBOX\u002F\u003Cgroup>\u002F` folder + `_archive\u002F`.\n- [ ] Watcher surfaces open handoffs hourly (silent when clear).\n- [ ] Agent that reads a handoff reports back what it did.\n- [ ] Resolved notes archived; `_archive\u002F` purged weekly.\n- [ ] No handoff left unread or unreported at a stopping point.\n",{"name":5,"tags":56,"author":57,"license":15,"version":58,"description":7},[26,41,40,25,49,48,45],"Gentech","1.2.0","main","3df1d0d67b30ff15236561f8c0f9f06d33f42dfd","skills\u002Fmcp-servers\u002Fgentech-labs-handoff-mesh",17,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia","https:\u002F\u002Feth2030.com","Hardcore infra. Building @alt-research and applied cryptography.","2026-11-13 02:31:19",{"source":8,"skillName":5,"commands":69,"prompt":79,"zipAvailable":80},[70,73,76],{"tool":71,"command":72},"npx","npx skills add jiayaoqijia\u002Fcryptoskill --skill handoff-mesh",{"tool":74,"command":75},"bunx","bunx skills add jiayaoqijia\u002Fcryptoskill --skill handoff-mesh",{"tool":77,"command":78},"pnpm","pnpm dlx skills add jiayaoqijia\u002Fcryptoskill --skill handoff-mesh","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fgentech-labs-handoff-mesh\u002FSKILL.md",true,[82,86,92,98],{"path":83,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":16},"LICENSE","许可证",1068,{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Fhandoff-watcher.py","SCRIPT","脚本",9702,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fgentech-labs-handoff-mesh\u002Fscripts\u002Fhandoff-watcher.py",{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"SOURCE.md","REFERENCE","参考文档",364,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fgentech-labs-handoff-mesh\u002FSOURCE.md",{"path":99,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":100,"sourceHtmlUrl":101},"TRUST.auto.yaml",2058,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fgentech-labs-handoff-mesh\u002FTRUST.auto.yaml",[103,131,154,172,185,195],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":107,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":51},"01M712C436EQYE43342Q4E7GG1","recipe-performance","Diagnose a specific MetaMask user flow's real-app performance and Sentry critical-user-flow telemetry with deterministic mm-harness recipes. Use for CUF boundaries, cold\u002Fwarm\u002Fbackground-resume behavior, latency regressions, lifecycle tags, duplicate or blocking network requests, long tasks, layout\u002Fpaint cost, screen redraws, React rerenders, or browser trace analysis where tests alone cannot prove the real app.","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fwallets\u002Fmetamask-official-recipe-performance\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fwallets\u002Fmetamask-official-recipe-performance\u002FSKILL.md",[],[111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130],"performance","recipe performance","recipe","mm","sentry","harness","app","deterministic","recipes","flow","cold","critical","analysis","tasks","react","browser","layout","screen","network","metamask",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":135,"licenseFileUrl":136,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":51},"01M70XT2F8A5CQZ81JBP98KSW3","mexc-spot-websocket","MEXC Spot WebSocket workflows for public streams, protobuf handling, depth maintenance, listen keys, and private streams without exposing API keys.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fmncrftfrcnm-mexc-spot-websocket\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fmncrftfrcnm-mexc-spot-websocket\u002FSKILL.md",[],[140,141,142,143,144,145,146,147,148,149,150,151,152,153],"mexc spot websocket","spot","websocket","api","workflows","public","listen","streams","depth","keys","for","api keys","maintenance","protobuf",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":135,"licenseFileUrl":158,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":51},"01M70XT0MBXN3WZY1BKN0CPNKR","mexc-spot-rest","MEXC Spot REST workflows for public data, signed account requests, orders, wallet\u002Fadmin actions, and secure signing without exposing API keys.","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fmncrftfrcnm-mexc-spot-rest\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fmncrftfrcnm-mexc-spot-rest\u002FSKILL.md",[],[162,141,163,164,165,166,167,151,150,149,168,169,170,145,171,144,143],"mexc spot rest","REST","admin","signing","Wallet","requests","actions","secure","data","orders",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":135,"licenseFileUrl":176,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":51},"01M70XSYSVZ2N0N91XCAR2CAK0","mexc-futures-websocket","MEXC Futures WebSocket workflows for public streams, private account\u002Forder\u002Fposition streams, ping\u002Fpong, subscriptions, and depth maintenance.","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fmncrftfrcnm-mexc-futures-websocket\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fmncrftfrcnm-mexc-futures-websocket\u002FSKILL.md",[],[180,181,142,182,183,152,150,184,148,147,145,144],"mexc futures websocket","futures","position","ping","subscriptions",{"skillNo":186,"name":187,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":188,"sourceHtmlUrl":189,"categories":190,"keywords":191,"publishedAt":51},"01M6H0ZWHVE5W04WG2DKQE2SQC","0xklen-version-and-refresh-sanctions-lists","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fpayments\u002F0xklen-version-and-refresh-sanctions-lists\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fpayments\u002F0xklen-version-and-refresh-sanctions-lists\u002FSKILL.md",[],[192,193,194],"refresh","0xklen version and refresh sanctions lists","version",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":199,"sourceHtmlUrl":200,"categories":201,"keywords":202,"publishedAt":51},"01M6H0Z28Q3R8J0S799GJQWXM3","verify-tests-cover-changed-lines","Use when a PR adds code that the existing suite may not exercise. Measures patch coverage — the share of newly changed lines hit by tests — before approving.","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fpayments\u002F0xklen-verify-tests-cover-changed-lines\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fpayments\u002F0xklen-verify-tests-cover-changed-lines\u002FSKILL.md",[],[203,204,205,206,207,208,209,210,211,212,213],"tests","cover","verify tests cover changed lines","verify","coverage","pr","exercise","use","patch","code","share"]