[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EXGPMC6WCSSYBVYWFA73D1":3,"skill-same:01M7EXGPMC6WCSSYBVYWFA73D1":47},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7EXGPMC6WCSSYBVYWFA73D1","bug-triage",null,"Triage bugs reported in chat\u002Fissues, search for duplicates, file or update GitHub issues with full context, and push fix PRs.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fbug-triage-agent-orchestrator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bug-triage\ndescription: Triage bugs reported in chat\u002Fissues, search for duplicates, file or update GitHub issues with full context, and push fix PRs.\ntrigger: User reports a bug, or asks to triage\u002Ffile an issue for a reported problem.\n---\n\n# Bug Triage Skill\n\nTriage bugs into well-structured GitHub issues on the Agent Orchestrator repo.\n\n> **Agent Orchestrator is Go + Electron.** The backend is a Go daemon (`backend\u002F`)\n> exposing a loopback HTTP API on `127.0.0.1:3001`; the frontend is an Electron +\n> React supervisor (`frontend\u002F`). There is **no** pm2\u002Ftmux\u002FNode runtime here —\n> the daemon owns lifecycle and sessions run under the **Zellij** runtime\n> adapter. Triage against _this_ stack, not the old TypeScript agent-orchestrator.\n\n## ⚠️ Which `ao` are you running?\n\n**`Agent Orchestrator` ships no `ao` on your PATH.** A bare `ao` very likely resolves to a\n**different** AO install — e.g. an old npm build at `~\u002F.nvm\u002F...\u002Fbin\u002Fao` that talks\nto port **:3000**. Triaging with the wrong binary produces bugs that don't exist\nin Agent Orchestrator (and miss ones that do).\n\nBefore any diagnostics:\n\n```bash\nwhich -a ao                      # see every ao on PATH — expect surprises\nao status 2>\u002Fdev\u002Fnull            # if this shows port 3000, it is NOT Agent Orchestrator\n```\n\nUse an Agent Orchestrator binary explicitly:\n\n```bash\n# Option A — build from this repo (preferred during triage)\ncd backend && go build -o \u002Ftmp\u002Fao .\u002Fcmd\u002Fao\n\u002Ftmp\u002Fao status                   # must report port: 3001\n\n# Option B — the packaged app's bundled daemon\n\"\u002FApplications\u002FAgent Orchestrator.app\u002FContents\u002FResources\u002Fdaemon\u002Fao\" status\n```\n\n**Confirm `ao status` reports `port: 3001` before trusting any output.** Throughout\nthis skill, `ao` means _your verified Agent Orchestrator binary_ (`\u002Ftmp\u002Fao` or the bundled\none), never a bare PATH lookup.\n\n> Note: spawned sessions get a PATH pin so the _session's_ `ao` resolves to the\n> daemon's own executable (see `hookPATH` in\n> `backend\u002Finternal\u002Fsession_manager\u002Fmanager.go`). That pin only applies inside\n> sessions — your interactive shell is still on its own PATH, so pin it yourself.\n\n## 1. Pre-flight\n\n- **Pull latest code:** `git pull origin main`. Stale code = bad triage.\n- **Target repo:** Always file on **`Untrivial-ai\u002Fagent-orchestrator`** (the current product repo, not\n  a fork). Agent Orchestrator is the product, not a thin fork of upstream.\n- **Verify your binary:** confirm `ao status` shows port **3001** (see warning above).\n- **Record source:** chat URL, reporter name, attachments.\n\n## 2. Gather Context\n\n### 2a. Extract the report\n\n| Source                   | How to gather                                                                                                                        |\n| ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------ |\n| **Discord\u002FSlack thread** | Read full thread. Extract: reporter name, original description (the thread starter, not whoever tagged you), screenshots, follow-ups |\n| **GitHub issue**         | `gh issue view \u003Cnumber> --repo Untrivial-ai\u002Fagent-orchestrator --json body,comments`                                                             |\n| **Live observation**     | Pull live state via the daemon: `ao status`, `ao session ls`, `ao session get \u003Cid>`                                                  |\n\n### 2b. Minimum viable report gate\n\nBefore tracing code, verify the report has enough substance:\n\n**Required (ALL):** what happened, where (page\u002Fcommand\u002Ffeature), when (after upgrade? first time?)\n\n**Required (2 of 4):** OS\u002Fshell, AO version (`ao version`), reproducibility (consistent vs intermittent), reproduction steps\n\nIf insufficient, ask:\n\n> \"I'd like to triage this but need more info: (1) **What happened?** (error\u002Fbehavior), (2) **Where?** (page\u002Fcommand), (3) **When did it start?**, (4) **How to reproduce?**\"\n\n### 2c. Local diagnostics (if bug is on same machine)\n\nGather everything yourself before asking the reporter. Use your **verified**\nAgent Orchestrator binary (`\u002Ftmp\u002Fao` here) for every `ao` call:\n\n```bash\n# Environment\n\u002Ftmp\u002Fao version && go version && echo $SHELL && uname -a\nwhich -a ao                                         # confirm no rogue ao shadows the build\ncat ~\u002F.ao\u002Frunning.json                              # PID + port handshake (expect port 3001)\n\n# Daemon health\n\u002Ftmp\u002Fao status                                      # daemon up? port? health\u002Fready probes\n\u002Ftmp\u002Fao doctor                                      # local health checks\nlsof -i :3001                                       # who's bound to the daemon port\ntail -n 100 ~\u002F.ao\u002Fdaemon.log                        # daemon log\n\n# Sessions & runtime\n\u002Ftmp\u002Fao session ls                                  # all sessions and their state\n\u002Ftmp\u002Fao session get \u003Cid>                            # one session: spawn config, runtime, lifecycle\nzellij list-sessions                                # Zellij runtime sessions backing terminals\n\n# Durable state (SQLite at ~\u002F.ao\u002Fdata)\nsqlite3 ~\u002F.ao\u002Fdata\u002Fao.db '.tables'                  # inspect schema\u002Frows if state looks wrong\n```\n\nThe daemon owns lifecycle, sessions, storage, and the terminal mux; structured\nstate lives in `~\u002F.ao\u002Fdata\u002Fao.db` (WAL: `ao.db-wal`, `ao.db-shm`). The PID+port\nhandshake is `~\u002F.ao\u002Frunning.json`.\n\n**Try the reproduction steps.** Running the actual command against the daemon on\n:3001 is worth 100 lines of code tracing.\n\n## 3. Investigate\n\n### 3a. Trace the code path\n\n**Always trace the actual code** — don't surface-level diagnose. A symptom that\nlooks like a simple `ao stop` issue is often a lifecycle\u002Fsession-manager problem\none layer down. Agent Orchestrator's layers:\n\n- CLI (Cobra, thin client over daemon HTTP): `backend\u002Finternal\u002Fcli\u002F`, entrypoint\n  `backend\u002Fcmd\u002Fao\u002Fmain.go`\n- Daemon (loopback HTTP on :3001): `backend\u002Finternal\u002Fdaemon\u002Fdaemon.go`,\n  controllers under `backend\u002Finternal\u002Fhttpd\u002Fcontrollers\u002F`\n- Sessions & lifecycle: `backend\u002Finternal\u002Fsession_manager\u002Fmanager.go`\n- Runtime adapter (Zellij): `backend\u002Finternal\u002Fadapters\u002Fruntime\u002F`\n- Agent harness adapters: `backend\u002Finternal\u002Fadapters\u002Fagent\u002F\u003Charness>\u002F`\n- Terminal mux: `backend\u002Finternal\u002Fterminal\u002F`\n- Agent hooks: `backend\u002Finternal\u002Fcli\u002Fhooks.go`\n\n```bash\ngit fetch origin main && git log --oneline origin\u002Fmain -5   # current HEAD\n# Record the commit hash you're analyzing against\n```\n\n**Git archaeology** — find which commits introduced\u002Fremoved specific code:\n\n```bash\ngit log --oneline -S 'exact-string' -- \u003Cfile>\ngit show \u003Csha> -- \u003Cfile> | grep -B 5 -A 10 'pattern'\n```\n\n**Research dependencies** (Zellij, the agent harness binary, Electron, React, the\nSQLite driver) — check installed vs latest version, search their issue trackers,\ncheck changelogs. Root cause is sometimes in a dependency, not Agent Orchestrator.\n\n### 3b. Cross-platform check\n\nAO targets **macOS, Linux, and Windows**. If env info indicates Windows (or is\nunknown), check for these patterns:\n\n- **Path separators** — hardcoded `\u002F` or `\\`; use `filepath.Join`, not string concat\n- **Shell syntax** — PowerShell lacks `&&`, `$VAR`, `$(cat ...)`, `\u002Fdev\u002Fnull`, here-docs\n- **`runtime.GOOS == \"windows\"` scattered inline** — centralize platform checks\n- **Process-tree kills** — POSIX process groups vs Windows job objects\n- **`localhost`** — Windows resolves to `::1` first; the daemon binds the explicit\n  loopback host (see `config.LoopbackHost`) to avoid IPv4\u002FIPv6 stalls\n- **Case-insensitive filesystems** — don't compare paths with raw `==`\n- **PATH \u002F binary resolution** — `.exe`\u002F`PATHEXT` lookup, the session PATH pin\n  (`hookPATH` in `backend\u002Finternal\u002Fsession_manager\u002Fmanager.go`)\n\nKey files: `backend\u002Finternal\u002Fconfig\u002Fconfig.go`, `backend\u002Finternal\u002Fsession_manager\u002Fmanager.go`,\n`backend\u002Finternal\u002Fadapters\u002Fruntime\u002F`, `backend\u002Finternal\u002Fterminal\u002F`.\n\n### 3c. Stop-and-ask triggers\n\nStop and ask for more info if:\n\n- **3 failed hypotheses** — traced 3 code paths, none explain it\n- **Root cause is a dependency** — file with the dependency reference, don't guess a local fix\n- **UI-only bug** and you can't screenshot — ask reporter to describe\n- **Can't reproduce** — ask for different config\u002Fsequence\n\n## 4. Search for Duplicates\n\nSearch with multiple strategies, always using `--state all` (closed bugs regress):\n\n```bash\ngh issue list --repo Untrivial-ai\u002Fagent-orchestrator --state all --search \"\u003Csymptom>\"\ngh issue list --repo Untrivial-ai\u002Fagent-orchestrator --state all --search \"\u003Ccomponent-name>\"\ngh issue list --repo Untrivial-ai\u002Fagent-orchestrator --state all --search \"\u003Cerror-message>\"\ngh pr list --repo Untrivial-ai\u002Fagent-orchestrator --state all --search \"\u003Ckeywords>\"\n```\n\n### Duplicate found → comment on existing issue\n\n```bash\ngh issue comment \u003Cnumber> --repo Untrivial-ai\u002Fagent-orchestrator --body \"$(cat \u003C\u003C'EOF'\n## New Report\n**Reported by:** @\u003Creporter> in [chat](\u003Curl>)\n**Date:** \u003CYYYY-MM-DD> | **Checkout:** `\u003Ccommit-hash>`\n\u003Ccontext, differences from original, screenshots>\nEOF\n)\"\n```\n\n### No duplicate → file new issue (next section)\n\n## 5. File New Issue\n\n### 5a. Pre-submission checklist\n\n- [ ] Reporter attribution correct (original reporter, not who tagged you)\n- [ ] Commit hash recorded\n- [ ] AO version recorded (`ao version`)\n- [ ] Reproduced against Agent Orchestrator (:3001 \u002F Go code path), not another AO install\n- [ ] Root cause confidence scored (see 5c)\n- [ ] Related issues cross-linked\n- [ ] Reproduction steps are concrete\n- [ ] Screenshots uploaded with real URLs (see 5b)\n\n### 5b. Upload screenshots\n\n**⛔ NEVER use placeholder URLs.** Upload BEFORE creating the issue.\n\n```bash\nSLUG=\"descriptive-slug\"\n# Create asset branch\ngh api -X POST repos\u002FUntrivial-ai\u002Fagent-orchestrator\u002Fgit\u002Frefs \\\n  -f ref=\"refs\u002Fheads\u002Fissue-assets-${SLUG}\" \\\n  -f sha=$(git rev-parse origin\u002Fmain)\n\n# Upload (portable base64)\nIMG_B64=$(base64 \u003C \u002Fpath\u002Fto\u002Fscreenshot.png | tr -d '\\n')\ngh api -X PUT \"repos\u002FUntrivial-ai\u002Fagent-orchestrator\u002Fcontents\u002F.issue-assets\u002F${SLUG}\u002Fname.png\" \\\n  -f message=\"chore: upload screenshot\" \\\n  -f content=\"$IMG_B64\" \\\n  -f branch=\"issue-assets-${SLUG}\"\n# Use: ![screenshot](https:\u002F\u002Fraw.githubusercontent.com\u002FUntrivial-ai\u002Fagent-orchestrator\u002Fissue-assets-\u003Cslug>\u002F.issue-assets\u002F\u003Cfile>)\n```\n\n### 5c. Create the issue\n\n```bash\ngh issue create --repo Untrivial-ai\u002Fagent-orchestrator --title \"\u003Ctitle>\" --body \"$(cat \u003C\u003C'EOF'\n## Bug\n\u003Csummary>\n\n**Source:** \u003Curl> | **Reported by:** @\u003Creporter> | **Analyzed against:** `\u003Chash>`\n**Confidence:** High\u002FMedium\u002FLow\n\n## Reproduction\n1. \u003Cstep>\n\n## Root Cause\n\u003Cfile paths, line numbers, explanation>\n\n## Fix\n\u003Csuggested approach>\n\n## Impact\n- \u003Ceffects>\nEOF\n)\"\n```\n\n### 5d. Label and prioritize\n\n**Check which labels actually exist first**, then apply only those:\n\n```bash\ngh label list --repo Untrivial-ai\u002Fagent-orchestrator          # source of truth — apply only these\ngh issue edit \u003Cnumber> --repo Untrivial-ai\u002Fagent-orchestrator --add-label \"bug\"\n```\n\nThe repo currently carries `bug`, `enhancement`, `priority: critical\u002Fhigh\u002Fmedium\u002Flow`,\nlane labels (`daemon`, `frontend`, `storage`, `coding-agents`, `lcm-sm`, `scm`,\n`core`, `port`, `adapter`, `domain`), and workflow labels (`needs-triage`,\n`needs-review`, `blocked`). **Do not invent labels** — if a priority or confidence\nlabel you want doesn't exist, **state it in the issue body instead** (e.g.\n\"**Priority:** high — core feature broken, no workaround\" \u002F \"**Confidence:** medium\").\n\n| Priority             | Criteria                            |\n| -------------------- | ----------------------------------- |\n| `priority: critical` | Data loss, security, system down    |\n| `priority: high`     | Core feature broken, no workaround  |\n| `priority: medium`   | Feature degraded, workaround exists |\n| `priority: low`      | Cosmetic, edge case                 |\n\n**Confidence scoring** (always state in the issue body):\n\n| Level      | Meaning                                                     |\n| ---------- | ----------------------------------------------------------- |\n| **High**   | Traced exact code path, specific lines, mechanism explained |\n| **Medium** | Strong hypothesis but unconfirmed                           |\n| **Low**    | Can't trace, multiple conflicting theories                  |\n\n### 5e. Cross-link related issues\n\nSearch by subsystem and add a `## Related` section to the issue body:\n\n```\n## Related\n- [#20](url) — stale session blocking ao start (same subsystem)\n- [#35](url) — same race condition\n```\n\n### 5f. Push a fix PR (always attempt)\n\nAgent Orchestrator is a Go repo — fixes go through a local branch, build, and `gh pr create`.\nThere is no remote-patch script.\n\n- **Unclear fix:** Don't push a guess. Document and flag in the issue.\n- **Trivial, verifiable fix** (you can build and test it yourself):\n\n  ```bash\n  git checkout -b fix\u002F\u003Cslug> origin\u002Fmain\n  # make the edit\n  cd backend && go build .\u002F... && go test .\u002F...   # must pass before pushing\n  git commit -am \"fix(\u003Cscope>): \u003Csummary>\n\n  Fixes #\u003Cn>\"\n  git push -u origin fix\u002F\u003Cslug>\n  gh pr create --repo Untrivial-ai\u002Fagent-orchestrator --fill \\\n    --title \"fix(\u003Cscope>): \u003Csummary>\" \\\n    --body \"Fixes #\u003Cn>\n\n  ## Summary\n  \u003Cwhat changed>\n\n  ## Test\n  cd backend && go build .\u002F... && go test .\u002F...\"\n  ```\n\n- **Non-trivial fix** (broad change, needs iteration, or you can't fully verify):\n  spawn an Agent Orchestrator worker session to do the work in its own worktree instead of\n  pushing a guess:\n\n  ```bash\n  ao spawn --project agent-orchestrator --prompt \"Fix #\u003Cn>: \u003Cone-line problem statement>. \\\n  Root cause: \u003Cfile:line + mechanism>. Suggested approach: \u003Capproach>. \\\n  Build with 'cd backend && go build .\u002F... && go test .\u002F...' before opening a PR against Untrivial-ai\u002Fagent-orchestrator.\"\n  ```\n\n  Note the issue with which path you took (PR or spawned worker).\n\n### 5g. Report back\n\nIssue URL, PR URL (if created) or spawned worker session ID, labels applied (and\nany priority\u002Fconfidence stated in the body), root cause summary.\n\n---\n\n## Appendix\n\n### A. Subsystem Quick Reference\n\n| Subsystem                       | Collect                                   | Key files                                                                  |\n| ------------------------------- | ----------------------------------------- | -------------------------------------------------------------------------- |\n| **CLI** (`ao start\u002Fstop\u002Fspawn`) | Version, install method, OS, which binary | `backend\u002Finternal\u002Fcli\u002F`, `backend\u002Fcmd\u002Fao\u002Fmain.go`                          |\n| **Daemon \u002F HTTP API**           | `ao status`, port, daemon.log             | `backend\u002Finternal\u002Fdaemon\u002Fdaemon.go`, `backend\u002Finternal\u002Fhttpd\u002Fcontrollers\u002F` |\n| **Sessions \u002F Lifecycle**        | Session ID, spawn config, runtime, state  | `backend\u002Finternal\u002Fsession_manager\u002Fmanager.go`                              |\n| **Runtime (Zellij)**            | Zellij version, `zellij list-sessions`    | `backend\u002Finternal\u002Fadapters\u002Fruntime\u002F`                                       |\n| **Terminal mux**                | Runtime type, shell, attach behavior      | `backend\u002Finternal\u002Fterminal\u002F`                                               |\n| **Agent harness**               | Harness name + version                    | `backend\u002Finternal\u002Fadapters\u002Fagent\u002F\u003Charness>\u002F`                               |\n| **Storage**                     | DB state, migrations                      | `backend\u002Finternal\u002Fstorage\u002Fsqlite\u002F`, `~\u002F.ao\u002Fdata\u002Fao.db`                     |\n| **Hooks**                       | Hook event, agent, payload                | `backend\u002Finternal\u002Fcli\u002Fhooks.go`                                            |\n| **Frontend (Electron\u002FReact)**   | Screenshot, viewport, daemon connectivity | `frontend\u002Fsrc\u002F`                                                            |\n\n**Misrouting patterns:**\n\n- Terminal bugs → Zellij runtime adapter vs the terminal mux vs the Electron xterm\n  surface. Trace where bytes flow (daemon → mux → frontend).\n- \"Session stuck\" → lifecycle\u002Fsession-manager state vs agent harness process vs\n  Zellij runtime connection.\n- \"Config not saving\" → config loading (`backend\u002Finternal\u002Fconfig\u002Fconfig.go`) vs\n  project registration vs SQLite write (`~\u002F.ao\u002Fdata\u002Fao.db`).\n- \"Command does nothing \u002F wrong port\" → you're on the wrong `ao` binary (:3000 vs\n  :3001). Re-check `which -a ao` and `ao status`.\n\n### B. Remote Code Inspection (no local clone)\n\n```bash\ngh api repos\u002FUntrivial-ai\u002Fagent-orchestrator\u002Fgit\u002Ftrees\u002Fmain?recursive=1 --jq '.tree[].path'    # list files\ngh api repos\u002FUntrivial-ai\u002Fagent-orchestrator\u002Fcontents\u002F{path} --jq '.content' | python3 -c \"import base64,sys; sys.stdout.buffer.write(base64.b64decode(sys.stdin.read()))\"  # read file\ngh search code \"term\" --repo Untrivial-ai\u002Fagent-orchestrator --json path --jq '.[].path'        # search code\ngh api \"repos\u002FUntrivial-ai\u002Fagent-orchestrator\u002Fcommits?path={path}&per_page=10\" --jq '.[] | \"\\(.sha[0:8]) \\(.commit.message | split(\"\\n\")[0])\"'  # file history\n```\n\n### C. Build \u002F Version Diagnostics\n\nAgent Orchestrator is built from source, not published to npm. Pin the binary under test\nand reproduce against a known build:\n\n```bash\ncd backend && go build -o \u002Ftmp\u002Fao .\u002Fcmd\u002Fao    # build the binary under test\n\u002Ftmp\u002Fao version                               # record version\u002Fcommit\ngo version                                    # toolchain (build issues are often here)\ngit log --oneline origin\u002Fmain -1              # the commit you're analyzing against\n```\n\nTo bisect a regression, build `ao` at two commits and compare behavior:\n\n```bash\ngit stash; git checkout \u003Cgood-sha>; (cd backend && go build -o \u002Ftmp\u002Fao-good .\u002Fcmd\u002Fao)\ngit checkout \u003Cbad-sha>;             (cd backend && go build -o \u002Ftmp\u002Fao-bad  .\u002Fcmd\u002Fao)\ngit checkout - ; git stash pop\n# run the repro against \u002Ftmp\u002Fao-good vs \u002Ftmp\u002Fao-bad\n```\n\n## Formatting Rules\n\n- **Linkify all issue\u002FPR refs:** `[#123](https:\u002F\u002Fgithub.com\u002FUntrivial-ai\u002Fagent-orchestrator\u002Fissues\u002F123)`, `[PR #456](url)`. Never bare `#123`.\n\n## Pitfalls\n\n- **Wrong `ao` binary.** A bare `ao` may be a different AO install (old npm build on\n  :3000). Always pin an Agent Orchestrator binary and confirm `ao status` shows port **3001**.\n- **Verify the bug reproduces against Agent Orchestrator (:3001 \u002F Go code path) before\n  filing** — symptoms first seen in another AO install may not reproduce here.\n- **Reporter ≠ person who tagged you.** Always attribute to the original reporter.\n- **Record the commit hash** you analyzed — code changes fast.\n- **GitHub issue is mandatory** — every triaged bug gets one, even if fix is trivial.\n- **Only apply labels that exist** (`gh label list --repo Untrivial-ai\u002Fagent-orchestrator`).\n  State priority\u002Fconfidence in the body when no matching label exists.\n- **Build before you push.** `cd backend && go build .\u002F... && go test .\u002F...` must\n  pass; never open a PR with an unverified Go change.\n- **`gh api --jq .content` truncates large files** (>~100KB). Use local git instead.\n- **Don't invent Go file paths.** Grep the repo to confirm a path before citing it\n  in an issue.\n","# Bug Triage Skill\n\nTriage bugs into well-structured GitHub issues on the Agent Orchestrator repo.\n\n> **Agent Orchestrator is Go + Electron.** The backend is a Go daemon (`backend\u002F`)\n> exposing a loopback HTTP API on `127.0.0.1:3001`; the frontend is an Electron +\n> React supervisor (`frontend\u002F`). There is **no** pm2\u002Ftmux\u002FNode runtime here —\n> the daemon owns lifecycle and sessions run under the **Zellij** runtime\n> adapter. Triage against _this_ stack, not the old TypeScript agent-orchestrator.\n\n## ⚠️ Which `ao` are you running?\n\n**`Agent Orchestrator` ships no `ao` on your PATH.** A bare `ao` very likely resolves to a\n**different** AO install — e.g. an old npm build at `~\u002F.nvm\u002F...\u002Fbin\u002Fao` that talks\nto port **:3000**. Triaging with the wrong binary produces bugs that don't exist\nin Agent Orchestrator (and miss ones that do).\n\nBefore any diagnostics:\n\n```bash\nwhich -a ao                      # see every ao on PATH — expect surprises\nao status 2>\u002Fdev\u002Fnull            # if this shows port 3000, it is NOT Agent Orchestrator\n```\n\nUse an Agent Orchestrator binary explicitly:\n\n```bash\n# Option A — build from this repo (preferred during triage)\ncd backend && go build -o \u002Ftmp\u002Fao .\u002Fcmd\u002Fao\n\u002Ftmp\u002Fao status                   # must report port: 3001\n\n# Option B — the packaged app's bundled daemon\n\"\u002FApplications\u002FAgent Orchestrator.app\u002FContents\u002FResources\u002Fdaemon\u002Fao\" status\n```\n\n**Confirm `ao status` reports `port: 3001` before trusting any output.** Throughout\nthis skill, `ao` means _your verified Agent Orchestrator binary_ (`\u002Ftmp\u002Fao` or the bundled\none), never a bare PATH lookup.\n\n> Note: spawned sessions get a PATH pin so the _session's_ `ao` resolves to the\n> daemon's own executable (see `hookPATH` in\n> `backend\u002Finternal\u002Fsession_manager\u002Fmanager.go`). That pin only applies inside\n> sessions — your interactive shell is still on its own PATH, so pin it yourself.\n\n## 1. Pre-flight\n\n- **Pull latest code:** `git pull origin main`. Stale code = bad triage.\n- **Target repo:** Always file on **`Untrivial-ai\u002Fagent-orchestrator`** (the current product repo, not\n  a fork). Agent Orchestrator is the product, not a thin fork of upstream.\n- **Verify your binary:** confirm `ao status` shows port **3001** (see warning above).\n- **Record source:** chat URL, reporter name, attachments.\n\n## 2. Gather Context\n\n### 2a. Extract the report\n\n| Source                   | How to gather                                                                                                                        |\n| ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------ |\n| **Discord\u002FSlack thread** | Read full thread. Extract: reporter name, original description (the thread starter, not whoever tagged you), screenshots, follow-ups |\n| **GitHub issue**         | `gh issue view \u003Cnumber> --repo Untrivial-ai\u002Fagent-orchestrator --json body,comments`                                                             |\n| **Live observation**     | Pull live state via the daemon: `ao status`, `ao session ls`, `ao session get \u003Cid>`                                                  |\n\n### 2b. Minimum viable report gate\n\nBefore tracing code, verify the report has enough substance:\n\n**Required (ALL):** what happened, where (page\u002Fcommand\u002Ffeature), when (after upgrade? first time?)\n\n**Required (2 of 4):** OS\u002Fshell, AO version (`ao version`), reproducibility (consistent vs intermittent), reproduction steps\n\nIf insufficient, ask:\n\n> \"I'd like to triage this but need more info: (1) **What happened?** (error\u002Fbehavior), (2) **Where?** (page\u002Fcommand), (3) **When did it start?**, (4) **How to reproduce?**\"\n\n### 2c. Local diagnostics (if bug is on same machine)\n\nGather everything yourself before asking the reporter. Use your **verified**\nAgent Orchestrator binary (`\u002Ftmp\u002Fao` here) for every `ao` call:\n\n```bash\n# Environment\n\u002Ftmp\u002Fao version && go version && echo $SHELL && uname -a\nwhich -a ao                                         # confirm no rogue ao shadows the build\ncat ~\u002F.ao\u002Frunning.json                              # PID + port handshake (expect port 3001)\n\n# Daemon health\n\u002Ftmp\u002Fao status                                      # daemon up? port? health\u002Fready probes\n\u002Ftmp\u002Fao doctor                                      # local health checks\nlsof -i :3001                                       # who's bound to the daemon port\ntail -n 100 ~\u002F.ao\u002Fdaemon.log                        # daemon log\n\n# Sessions & runtime\n\u002Ftmp\u002Fao session ls                                  # all sessions and their state\n\u002Ftmp\u002Fao session get \u003Cid>                            # one session: spawn config, runtime, lifecycle\nzellij list-sessions                                # Zellij runtime sessions backing terminals\n\n# Durable state (SQLite at ~\u002F.ao\u002Fdata)\nsqlite3 ~\u002F.ao\u002Fdata\u002Fao.db '.tables'                  # inspect schema\u002Frows if state looks wrong\n```\n\nThe daemon owns lifecycle, sessions, storage, and the terminal mux; structured\nstate lives in `~\u002F.ao\u002Fdata\u002Fao.db` (WAL: `ao.db-wal`, `ao.db-shm`). The PID+port\nhandshake is `~\u002F.ao\u002Frunning.json`.\n\n**Try the reproduction steps.** Running the actual command against the daemon on\n:3001 is worth 100 lines of code tracing.\n\n## 3. Investigate\n\n### 3a. Trace the code path\n\n**Always trace the actual code** — don't surface-level diagnose. A symptom that\nlooks like a simple `ao stop` issue is often a lifecycle\u002Fsession-manager problem\none layer down. Agent Orchestrator's layers:\n\n- CLI (Cobra, thin client over daemon HTTP): `backend\u002Finternal\u002Fcli\u002F`, entrypoint\n  `backend\u002Fcmd\u002Fao\u002Fmain.go`\n- Daemon (loopback HTTP on :3001): `backend\u002Finternal\u002Fdaemon\u002Fdaemon.go`,\n  controllers under `backend\u002Finternal\u002Fhttpd\u002Fcontrollers\u002F`\n- Sessions & lifecycle: `backend\u002Finternal\u002Fsession_manager\u002Fmanager.go`\n- Runtime adapter (Zellij): `backend\u002Finternal\u002Fadapters\u002Fruntime\u002F`\n- Agent harness adapters: `backend\u002Finternal\u002Fadapters\u002Fagent\u002F\u003Charness>\u002F`\n- Terminal mux: `backend\u002Finternal\u002Fterminal\u002F`\n- Agent hooks: `backend\u002Finternal\u002Fcli\u002Fhooks.go`\n\n```bash\ngit fetch origin main && git log --oneline origin\u002Fmain -5   # current HEAD\n# Record the commit hash you're analyzing against\n```\n\n**Git archaeology** — find which commits introduced\u002Fremoved specific code:\n\n```bash\ngit log --oneline -S 'exact-string' -- \u003Cfile>\ngit show \u003Csha> -- \u003Cfile> | grep -B 5 -A 10 'pattern'\n```\n\n**Research dependencies** (Zellij, the agent harness binary, Electron, React, the\nSQLite driver) — check installed vs latest version, search their issue trackers,\ncheck changelogs. Root cause is sometimes in a dependency, not Agent Orchestrator.\n\n### 3b. Cross-platform check\n\nAO targets **macOS, Linux, and Windows**. If env info indicates Windows (or is\nunknown), check for these patterns:\n\n- **Path separators** — hardcoded `\u002F` or `\\`; use `filepath.Join`, not string concat\n- **Shell syntax** — PowerShell lacks `&&`, `$VAR`, `$(cat ...)`, `\u002Fdev\u002Fnull`, here-docs\n- **`runtime.GOOS == \"windows\"` scattered inline** — centralize platform checks\n- **Process-tree kills** — POSIX process groups vs Windows job objects\n- **`localhost`** — Windows resolves to `::1` first; the daemon binds the explicit\n  loopback host (see `config.LoopbackHost`) to avoid IPv4\u002FIPv6 stalls\n- **Case-insensitive filesystems** — don't compare paths with raw `==`\n- **PATH \u002F binary resolution** — `.exe`\u002F`PATHEXT` lookup, the session PATH pin\n  (`hookPATH` in `backend\u002Finternal\u002Fsession_manager\u002Fmanager.go`)\n\nKey files: `backend\u002Finternal\u002Fconfig\u002Fconfig.go`, `backend\u002Finternal\u002Fsession_manager\u002Fmanager.go`,\n`backend\u002Finternal\u002Fadapters\u002Fruntime\u002F`, `backend\u002Finternal\u002Fterminal\u002F`.\n\n### 3c. Stop-and-ask triggers\n\nStop and ask for more info if:\n\n- **3 failed hypotheses** — traced 3 code paths, none explain it\n- **Root cause is a dependency** — file with the dependency reference, don't guess a local fix\n- **UI-only bug** and you can't screenshot — ask reporter to describe\n- **Can't reproduce** — ask for different config\u002Fsequence\n\n## 4. Search for Duplicates\n\nSearch with multiple strategies, always using `--state all` (closed bugs regress):\n\n```bash\ngh issue list --repo Untrivial-ai\u002Fagent-orchestrator --state all --search \"\u003Csymptom>\"\ngh issue list --repo Untrivial-ai\u002Fagent-orchestrator --state all --search \"\u003Ccomponent-name>\"\ngh issue list --repo Untrivial-ai\u002Fagent-orchestrator --state all --search \"\u003Cerror-message>\"\ngh pr list --repo Untrivial-ai\u002Fagent-orchestrator --state all --search \"\u003Ckeywords>\"\n```\n\n### Duplicate found → comment on existing issue\n\n```bash\ngh issue comment \u003Cnumber> --repo Untrivial-ai\u002Fagent-orchestrator --body \"$(cat \u003C\u003C'EOF'\n## New Report\n**Reported by:** @\u003Creporter> in [chat](\u003Curl>)\n**Date:** \u003CYYYY-MM-DD> | **Checkout:** `\u003Ccommit-hash>`\n\u003Ccontext, differences from original, screenshots>\nEOF\n)\"\n```\n\n### No duplicate → file new issue (next section)\n\n## 5. File New Issue\n\n### 5a. Pre-submission checklist\n\n- [ ] Reporter attribution correct (original reporter, not who tagged you)\n- [ ] Commit hash recorded\n- [ ] AO version recorded (`ao version`)\n- [ ] Reproduced against Agent Orchestrator (:3001 \u002F Go code path), not another AO install\n- [ ] Root cause confidence scored (see 5c)\n- [ ] Related issues cross-linked\n- [ ] Reproduction steps are concrete\n- [ ] Screenshots uploaded with real URLs (see 5b)\n\n### 5b. Upload screenshots\n\n**⛔ NEVER use placeholder URLs.** Upload BEFORE creating the issue.\n\n```bash\nSLUG=\"descriptive-slug\"\n# Create asset branch\ngh api -X POST repos\u002FUntrivial-ai\u002Fagent-orchestrator\u002Fgit\u002Frefs \\\n  -f ref=\"refs\u002Fheads\u002Fissue-assets-${SLUG}\" \\\n  -f sha=$(git rev-parse origin\u002Fmain)\n\n# Upload (portable base64)\nIMG_B64=$(base64 \u003C \u002Fpath\u002Fto\u002Fscreenshot.png | tr -d '\\n')\ngh api -X PUT \"repos\u002FUntrivial-ai\u002Fagent-orchestrator\u002Fcontents\u002F.issue-assets\u002F${SLUG}\u002Fname.png\" \\\n  -f message=\"chore: upload screenshot\" \\\n  -f content=\"$IMG_B64\" \\\n  -f branch=\"issue-assets-${SLUG}\"\n# Use: ![screenshot](https:\u002F\u002Fraw.githubusercontent.com\u002FUntrivial-ai\u002Fagent-orchestrator\u002Fissue-assets-\u003Cslug>\u002F.issue-assets\u002F\u003Cfile>)\n```\n\n### 5c. Create the issue\n\n```bash\ngh issue create --repo Untrivial-ai\u002Fagent-orchestrator --title \"\u003Ctitle>\" --body \"$(cat \u003C\u003C'EOF'\n## Bug\n\u003Csummary>\n\n**Source:** \u003Curl> | **Reported by:** @\u003Creporter> | **Analyzed against:** `\u003Chash>`\n**Confidence:** High\u002FMedium\u002FLow\n\n## Reproduction\n1. \u003Cstep>\n\n## Root Cause\n\u003Cfile paths, line numbers, explanation>\n\n## Fix\n\u003Csuggested approach>\n\n## Impact\n- \u003Ceffects>\nEOF\n)\"\n```\n\n### 5d. Label and prioritize\n\n**Check which labels actually exist first**, then apply only those:\n\n```bash\ngh label list --repo Untrivial-ai\u002Fagent-orchestrator          # source of truth — apply only these\ngh issue edit \u003Cnumber> --repo Untrivial-ai\u002Fagent-orchestrator --add-label \"bug\"\n```\n\nThe repo currently carries `bug`, `enhancement`, `priority: critical\u002Fhigh\u002Fmedium\u002Flow`,\nlane labels (`daemon`, `frontend`, `storage`, `coding-agents`, `lcm-sm`, `scm`,\n`core`, `port`, `adapter`, `domain`), and workflow labels (`needs-triage`,\n`needs-review`, `blocked`). **Do not invent labels** — if a priority or confidence\nlabel you want doesn't exist, **state it in the issue body instead** (e.g.\n\"**Priority:** high — core feature broken, no workaround\" \u002F \"**Confidence:** medium\").\n\n| Priority             | Criteria                            |\n| -------------------- | ----------------------------------- |\n| `priority: critical` | Data loss, security, system down    |\n| `priority: high`     | Core feature broken, no workaround  |\n| `priority: medium`   | Feature degraded, workaround exists |\n| `priority: low`      | Cosmetic, edge case                 |\n\n**Confidence scoring** (always state in the issue body):\n\n| Level      | Meaning                                                     |\n| ---------- | ----------------------------------------------------------- |\n| **High**   | Traced exact code path, specific lines, mechanism explained |\n| **Medium** | Strong hypothesis but unconfirmed                           |\n| **Low**    | Can't trace, multiple conflicting theories                  |\n\n### 5e. Cross-link related issues\n\nSearch by subsystem and add a `## Related` section to the issue body:\n\n```\n## Related\n- [#20](url) — stale session blocking ao start (same subsystem)\n- [#35](url) — same race condition\n```\n\n### 5f. Push a fix PR (always attempt)\n\nAgent Orchestrator is a Go repo — fixes go through a local branch, build, and `gh pr create`.\nThere is no remote-patch script.\n\n- **Unclear fix:** Don't push a guess. Document and flag in the issue.\n- **Trivial, verifiable fix** (you can build and test it yourself):\n\n  ```bash\n  git checkout -b fix\u002F\u003Cslug> origin\u002Fmain\n  # make the edit\n  cd backend && go build .\u002F... && go test .\u002F...   # must pass before pushing\n  git commit -am \"fix(\u003Cscope>): \u003Csummary>\n\n  Fixes #\u003Cn>\"\n  git push -u origin fix\u002F\u003Cslug>\n  gh pr create --repo Untrivial-ai\u002Fagent-orchestrator --fill \\\n    --title \"fix(\u003Cscope>): \u003Csummary>\" \\\n    --body \"Fixes #\u003Cn>\n\n  ## Summary\n  \u003Cwhat changed>\n\n  ## Test\n  cd backend && go build .\u002F... && go test .\u002F...\"\n  ```\n\n- **Non-trivial fix** (broad change, needs iteration, or you can't fully verify):\n  spawn an Agent Orchestrator worker session to do the work in its own worktree instead of\n  pushing a guess:\n\n  ```bash\n  ao spawn --project agent-orchestrator --prompt \"Fix #\u003Cn>: \u003Cone-line problem statement>. \\\n  Root cause: \u003Cfile:line + mechanism>. Suggested approach: \u003Capproach>. \\\n  Build with 'cd backend && go build .\u002F... && go test .\u002F...' before opening a PR against Untrivial-ai\u002Fagent-orchestrator.\"\n  ```\n\n  Note the issue with which path you took (PR or spawned worker).\n\n### 5g. Report back\n\nIssue URL, PR URL (if created) or spawned worker session ID, labels applied (and\nany priority\u002Fconfidence stated in the body), root cause summary.\n\n---\n\n## Appendix\n\n### A. Subsystem Quick Reference\n\n| Subsystem                       | Collect                                   | Key files                                                                  |\n| ------------------------------- | ----------------------------------------- | -------------------------------------------------------------------------- |\n| **CLI** (`ao start\u002Fstop\u002Fspawn`) | Version, install method, OS, which binary | `backend\u002Finternal\u002Fcli\u002F`, `backend\u002Fcmd\u002Fao\u002Fmain.go`                          |\n| **Daemon \u002F HTTP API**           | `ao status`, port, daemon.log             | `backend\u002Finternal\u002Fdaemon\u002Fdaemon.go`, `backend\u002Finternal\u002Fhttpd\u002Fcontrollers\u002F` |\n| **Sessions \u002F Lifecycle**        | Session ID, spawn config, runtime, state  | `backend\u002Finternal\u002Fsession_manager\u002Fmanager.go`                              |\n| **Runtime (Zellij)**            | Zellij version, `zellij list-sessions`    | `backend\u002Finternal\u002Fadapters\u002Fruntime\u002F`                                       |\n| **Terminal mux**                | Runtime type, shell, attach behavior      | `backend\u002Finternal\u002Fterminal\u002F`                                               |\n| **Agent harness**               | Harness name + version                    | `backend\u002Finternal\u002Fadapters\u002Fagent\u002F\u003Charness>\u002F`                               |\n| **Storage**                     | DB state, migrations                      | `backend\u002Finternal\u002Fstorage\u002Fsqlite\u002F`, `~\u002F.ao\u002Fdata\u002Fao.db`                     |\n| **Hooks**                       | Hook event, agent, payload                | `backend\u002Finternal\u002Fcli\u002Fhooks.go`                                            |\n| **Frontend (Electron\u002FReact)**   | Screenshot, viewport, daemon connectivity | `frontend\u002Fsrc\u002F`                                                            |\n\n**Misrouting patterns:**\n\n- Terminal bugs → Zellij runtime adapter vs the terminal mux vs the Electron xterm\n  surface. Trace where bytes flow (daemon → mux → frontend).\n- \"Session stuck\" → lifecycle\u002Fsession-manager state vs agent harness process vs\n  Zellij runtime connection.\n- \"Config not saving\" → config loading (`backend\u002Finternal\u002Fconfig\u002Fconfig.go`) vs\n  project registration vs SQLite write (`~\u002F.ao\u002Fdata\u002Fao.db`).\n- \"Command does nothing \u002F wrong port\" → you're on the wrong `ao` binary (:3000 vs\n  :3001). Re-check `which -a ao` and `ao status`.\n\n### B. Remote Code Inspection (no local clone)\n\n```bash\ngh api repos\u002FUntrivial-ai\u002Fagent-orchestrator\u002Fgit\u002Ftrees\u002Fmain?recursive=1 --jq '.tree[].path'    # list files\ngh api repos\u002FUntrivial-ai\u002Fagent-orchestrator\u002Fcontents\u002F{path} --jq '.content' | python3 -c \"import base64,sys; sys.stdout.buffer.write(base64.b64decode(sys.stdin.read()))\"  # read file\ngh search code \"term\" --repo Untrivial-ai\u002Fagent-orchestrator --json path --jq '.[].path'        # search code\ngh api \"repos\u002FUntrivial-ai\u002Fagent-orchestrator\u002Fcommits?path={path}&per_page=10\" --jq '.[] | \"\\(.sha[0:8]) \\(.commit.message | split(\"\\n\")[0])\"'  # file history\n```\n\n### C. Build \u002F Version Diagnostics\n\nAgent Orchestrator is built from source, not published to npm. Pin the binary under test\nand reproduce against a known build:\n\n```bash\ncd backend && go build -o \u002Ftmp\u002Fao .\u002Fcmd\u002Fao    # build the binary under test\n\u002Ftmp\u002Fao version                               # record version\u002Fcommit\ngo version                                    # toolchain (build issues are often here)\ngit log --oneline origin\u002Fmain -1              # the commit you're analyzing against\n```\n\nTo bisect a regression, build `ao` at two commits and compare behavior:\n\n```bash\ngit stash; git checkout \u003Cgood-sha>; (cd backend && go build -o \u002Ftmp\u002Fao-good .\u002Fcmd\u002Fao)\ngit checkout \u003Cbad-sha>;             (cd backend && go build -o \u002Ftmp\u002Fao-bad  .\u002Fcmd\u002Fao)\ngit checkout - ; git stash pop\n# run the repro against \u002Ftmp\u002Fao-good vs \u002Ftmp\u002Fao-bad\n```\n\n## Formatting Rules\n\n- **Linkify all issue\u002FPR refs:** `[#123](https:\u002F\u002Fgithub.com\u002FUntrivial-ai\u002Fagent-orchestrator\u002Fissues\u002F123)`, `[PR #456](url)`. Never bare `#123`.\n\n## Pitfalls\n\n- **Wrong `ao` binary.** A bare `ao` may be a different AO install (old npm build on\n  :3000). Always pin an Agent Orchestrator binary and confirm `ao status` shows port **3001**.\n- **Verify the bug reproduces against Agent Orchestrator (:3001 \u002F Go code path) before\n  filing** — symptoms first seen in another AO install may not reproduce here.\n- **Reporter ≠ person who tagged you.** Always attribute to the original reporter.\n- **Record the commit hash** you analyzed — code changes fast.\n- **GitHub issue is mandatory** — every triaged bug gets one, even if fix is trivial.\n- **Only apply labels that exist** (`gh label list --repo Untrivial-ai\u002Fagent-orchestrator`).\n  State priority\u002Fconfidence in the body when no matching label exists.\n- **Build before you push.** `cd backend && go build .\u002F... && go test .\u002F...` must\n  pass; never open a PR with an unverified Go change.\n- **`gh api --jq .content` truncates large files** (>~100KB). Use local git instead.\n- **Don't invent Go file paths.** Grep the repo to confirm a path before citing it\n  in an issue.\n",{"name":5,"trigger":24,"description":7},"User reports a bug, or asks to triage\u002Ffile an issue for a reported problem.","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fbug-triage-agent-orchestrator",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill bug-triage",{"tool":39,"command":40},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill bug-triage",{"tool":42,"command":43},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill bug-triage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fbug-triage-agent-orchestrator\u002FSKILL.md",true,[],[48,56,61,68,75,82],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":55},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":57,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":55},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":55},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":55},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":55},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":55},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]