[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DJM03F46C72EKVPXCASEYS":3,"skill-same:01M7DJM03F46C72EKVPXCASEYS":44},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7DJM03F46C72EKVPXCASEYS","preflight",null,"Select and run the existing SemEngine verification gates for a concrete diff and record their evidence. Use before implementation pushes or when assessing local readiness.","C360Studio\u002Fsemengine","C360Studio","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F107274645?v=4","01M6NQ809JZG513TZ7FJX8SAKQ","Complete 360 Studio","01M7DJK5W1EEP4D1Z9F5WVJG1T",0,"MIT","https:\u002F\u002Fgithub.com\u002FC360Studio\u002Fsemengine\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpreflight\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: preflight\ndescription: >-\n  Select and run the existing SemEngine verification gates for a concrete diff and record their evidence.\n  Use before implementation pushes or when assessing local readiness.\n---\n\n# Verify a SemEngine change\n\nThe [shared protocol](..\u002F..\u002Fprotocol.md) owns claims and landing. Read it first. This skill selects existing checks and\nrecords evidence; it grants no merge, tag or cleanup authority.\n\n## 1. Establish the diff and its owner\n\nWork in the claim's worktree. Verify its branch, HEAD, dirty\u002Funtracked files, upstream and PR target before\nchoosing checks. Compare the committed diff against the actual PR base, including a non-default target in a\nstack; also inspect the staged and unstaged work. Do not assume the discovery checkout's local `main` is current.\nBefore every commit or push, verify the branch still matches the claimed PR head.\n\n## 2. Select the existing gates\n\nOne Task entrypoint serves local work and CI. `task --list` shows what exists; inspect the `Taskfile.yml` and the\nworkflows under `.github\u002F` when exact coverage matters. A task name or old successful log does not prove parity\nwith current CI.\n\n| Task | What it does |\n| --- | --- |\n| `task fmt` | Formats Go sources; the only task here that changes files |\n| `task fmt:check` | Fails if any Go source needs formatting; writes nothing |\n| `task doctor` | Reports tool versions and Docker reachability against their pins; starts no workloads |\n| `task ateam:doctor` | `ateam doctor --check` with the session variables unset: agent-setup files, skills and adapters, hooks, MCP, review policy, `AGENTS.md` size and rule-row parity; warnings do not fail it |\n| `task spec:check` | Validates all OpenSpec changes and specs strictly, and fails on a `Hold:` written outside every task |\n| `task spec:queue` | Shows each in-flight OpenSpec change with its holds and blocking conditions |\n| `task docs:check` | Lints Markdown with `markdownlint-cli2` |\n| `task tidy:check` | Fails if `go.mod` or `go.sum` are not tidy |\n| `task build` | Builds all packages |\n| `task vet` | `go vet` |\n| `task lint` | Pinned `revive` |\n| `task vuln` | Pinned `govulncheck`; review findings against reachable behavior |\n| `task cleanup-roots:check` | Fails if a test stops, closes, or terminates under `context.Background()` or `TODO()` |\n| `task ledger:check` | Validates `docs\u002Fadmission-ledger.yaml` against its schema |\n| `task test:unit` | Unit tests once with the race detector at one CPU; every package except the three tool packages (`toolcheck`, `mutcheck`, `pindiff`) |\n| `task test:tools` | The tool packages once with the race detector at one CPU; `task test:tools:changed` runs the same only when a file under their trigger paths (`scripts\u002F`, `internal\u002Fharness\u002F`, `.github\u002F`, `Taskfile.yml`, `go.mod`, `go.sum` and the others in `toolcheck\u002Fdoc.go`) changed against the base, and says so when it skips |\n| `task test:integration` | Docker-backed tests: plain `go test -tags=integration` with pinned flags (race detector, two packages at a time, shuffled, 10-minute timeout) and the coverage profile `task cover:check` reads; runs only packages that have an `integration`-tagged test; `-- \u003Cpkgs>` to focus |\n| `task cover:check` | Fails below 80% coverage on each target in `scripts\u002Fcover-check.sh` (16 today: the harness's `natsfixture`, `lifecycletest`, `probe`, and each ported package on the SETUP 03B critical list, `setup-03b-contract-boundary` `design.md` D10); a package on that list joins when it is ported |\n| `task test:repeat` | Unit tests (not the tool packages, not the repository guards in `internal\u002Fharness\u002Fcontract`) five times at one CPU without the race detector, in shuffled order; `-- \u003Cpkgs>` to focus |\n| `task mutate:check -- -pkg … -test … -file … -mutant … -expect …` | Run by hand: applies one wrong change to a Go source file through `go test -overlay` and prints detection, survivor, invalid or inconclusive (the `mutation-check` spec); fails unless the verdict is detection; writes nothing in the repository |\n| `task merge:check -- \u003Cn>` | `ateam review gate` run via `scripts\u002Fateam`, the pin (`task tools:ateam` installs it; `docs\u002Ftesting.md`): fails while the rules on `main` do not require an up-to-date head, while PR `n` is a code pull request, not a draft, without `implemented-by:` and `reviewed-by:` lines naming a not-weaker other agent and an approving review record at its head, or while an open `class:flake` issue is not closed by PR `n`; reads GitHub |\n| `task verify` | `ateam:doctor` first, then the checks above except `doctor`, `fmt`, `spec:queue`, `mutate:check`, `merge:check`, cheapest first with `test:tools:changed` after `test:unit` and `test:repeat` last; prints each step's time; fails on tracked-file change; `task verify -- checks` and `task verify -- integration` run the two halves CI runs as separate jobs (`integration`: `ateam:doctor`, `test:integration`, `cover:check`; `checks`: the rest) |\n\nCI has two workflows: in `ci.yml`, the jobs `checks` and `integration` run the two halves of `task verify` in parallel\nand `required` fails if either failed, is missing, or was skipped or cancelled; `merge-check.yml` runs\n`scripts\u002Fmerge-check.sh` for a pull request that is not a draft, from the base commit, on every push, ready and\ndescription edit. `task verify` needs a reachable Docker daemon for `test:integration`; a daemon that is not reachable\nis a failing gate, never a skipped one. A consumer lane joins `task verify` when its workload exists; until then no task\nfor it exists, and a missing lane is not a passing one.\n\nSelect by what the diff changes:\n\n- **Documentation or skill instructions only:** `task fmt:check`, `task docs:check`, and `git diff --check`; add\n  `task spec:check` when `openspec\u002F` changed.\n- **Agent setup (`AGENTS.md`, `CLAUDE.md`, `.agents\u002F`, `.claude\u002F`, `.codex\u002F`, `.gemini\u002F`):** `task ateam:doctor` and\n  `task test:unit` (`TestAgentSetupParity`).\n- **An OpenSpec change:** `task spec:check`, then read `task spec:queue` in this worktree.\n- **Go behavior:** `task test:unit` (plus `task test:tools` when `scripts\u002F`,\n  `internal\u002Fharness\u002F`, `.github\u002F` or `Taskfile.yml` changed), `task vet`, `task lint`, `task build`; focused tests first\n  during iteration.\n- **Docker-backed behavior (`internal\u002Fharness\u002Fnatsfixture`, any `*_integration_test.go`):**\n  `task test:integration -- \u003Cpkgs>` to focus, then `task cover:check`, which reads the profile of the last passing\n  integration run and refuses one taken on a different tree. A plain `go test -tags integration` run is fine while\n  iterating. The NATS image is the one line in `internal\u002Fharness\u002Fnatsfixture\u002Fnats-image`; to try another, edit that\n  line in a branch.\n- **`docs\u002Fadmission-ledger.yaml`:** `task ledger:check`.\n- **Dependencies or `go.mod`:** `task tidy:check` and `task vuln` in addition to the Go gates.\n- **Before any implementation push:** `task verify`.\n- **Immediately before merging:** `task merge:check -- \u003Cn>`, in a shell where `GITHUB_ACTIONS` is not set. It sees a\n  flake filed, a closing line removed, or a review record posted, since the pull request's last `Merge check` run.\n\nDo not hand-run a narrower command in place of a gate CI runs: the task owns flags and pins.\n\n## 3. Protect shared test infrastructure\n\nSerialize heavy work on a shared host. Docker inspection is diagnostic:\ncontainer age, a timeout signature, or a name pattern does not establish that a resource is abandoned or that a\nfailure is infrastructure-only. Preserve other sessions' resources. Cleanup is limited to an identified completed or\nabandoned run this session is authorized to clean up; host-wide pruning and stopping an unknown port holder are not\npreflight steps.\n\n## 4. Record Evidence and remaining gates\n\nRecord the tested HEAD (or dirty snapshot), exact command, exit status, assertions\u002Ftests actually exercised,\nand log\u002Fartifact location. A log under a path git ignores (such as `coverage\u002F`) is on this host only: say so,\nand put the output a reader needs in the PR. Separate failure, skip, no selected tests and compilation-only results.\nWhen the implementation changes, older green results remain evidence for the older revision. Preserve the command's\nfailure status when filtering output; do not infer success from a quiet log.\n\nResolve failures from evidence; a successful re-run is not a fix for a flake. A red that your diff does not explain\nis filed as an issue before the next push, labelled `class:flake` when it is a test or check that passes and fails\non the same tree. A network fetch that did not answer is not a flake, and a local red whose `host:` line shows a\none-minute load average at or above twice the core count is a host-load suspect first: follow the protocol's \"Known\nflakes\" item for both. An\nopen flake is fixed; nothing else gets a pull request past it, and `Merge check` fails every pull request that does\nnot close it. Long or paid runs need the role contract's active progress\nchecks and bounded stopping behavior.\n\nAfter local verification, assess the PR's current-head hosted checks and the protocol's review\u002Farchive gates.\nLocal green is not merge authorization. Follow existing user authorization without asking for it again, while\npreserving all outstanding required gates.\n","# Verify a SemEngine change\n\nThe [shared protocol](..\u002F..\u002Fprotocol.md) owns claims and landing. Read it first. This skill selects existing checks and\nrecords evidence; it grants no merge, tag or cleanup authority.\n\n## 1. Establish the diff and its owner\n\nWork in the claim's worktree. Verify its branch, HEAD, dirty\u002Funtracked files, upstream and PR target before\nchoosing checks. Compare the committed diff against the actual PR base, including a non-default target in a\nstack; also inspect the staged and unstaged work. Do not assume the discovery checkout's local `main` is current.\nBefore every commit or push, verify the branch still matches the claimed PR head.\n\n## 2. Select the existing gates\n\nOne Task entrypoint serves local work and CI. `task --list` shows what exists; inspect the `Taskfile.yml` and the\nworkflows under `.github\u002F` when exact coverage matters. A task name or old successful log does not prove parity\nwith current CI.\n\n| Task | What it does |\n| --- | --- |\n| `task fmt` | Formats Go sources; the only task here that changes files |\n| `task fmt:check` | Fails if any Go source needs formatting; writes nothing |\n| `task doctor` | Reports tool versions and Docker reachability against their pins; starts no workloads |\n| `task ateam:doctor` | `ateam doctor --check` with the session variables unset: agent-setup files, skills and adapters, hooks, MCP, review policy, `AGENTS.md` size and rule-row parity; warnings do not fail it |\n| `task spec:check` | Validates all OpenSpec changes and specs strictly, and fails on a `Hold:` written outside every task |\n| `task spec:queue` | Shows each in-flight OpenSpec change with its holds and blocking conditions |\n| `task docs:check` | Lints Markdown with `markdownlint-cli2` |\n| `task tidy:check` | Fails if `go.mod` or `go.sum` are not tidy |\n| `task build` | Builds all packages |\n| `task vet` | `go vet` |\n| `task lint` | Pinned `revive` |\n| `task vuln` | Pinned `govulncheck`; review findings against reachable behavior |\n| `task cleanup-roots:check` | Fails if a test stops, closes, or terminates under `context.Background()` or `TODO()` |\n| `task ledger:check` | Validates `docs\u002Fadmission-ledger.yaml` against its schema |\n| `task test:unit` | Unit tests once with the race detector at one CPU; every package except the three tool packages (`toolcheck`, `mutcheck`, `pindiff`) |\n| `task test:tools` | The tool packages once with the race detector at one CPU; `task test:tools:changed` runs the same only when a file under their trigger paths (`scripts\u002F`, `internal\u002Fharness\u002F`, `.github\u002F`, `Taskfile.yml`, `go.mod`, `go.sum` and the others in `toolcheck\u002Fdoc.go`) changed against the base, and says so when it skips |\n| `task test:integration` | Docker-backed tests: plain `go test -tags=integration` with pinned flags (race detector, two packages at a time, shuffled, 10-minute timeout) and the coverage profile `task cover:check` reads; runs only packages that have an `integration`-tagged test; `-- \u003Cpkgs>` to focus |\n| `task cover:check` | Fails below 80% coverage on each target in `scripts\u002Fcover-check.sh` (16 today: the harness's `natsfixture`, `lifecycletest`, `probe`, and each ported package on the SETUP 03B critical list, `setup-03b-contract-boundary` `design.md` D10); a package on that list joins when it is ported |\n| `task test:repeat` | Unit tests (not the tool packages, not the repository guards in `internal\u002Fharness\u002Fcontract`) five times at one CPU without the race detector, in shuffled order; `-- \u003Cpkgs>` to focus |\n| `task mutate:check -- -pkg … -test … -file … -mutant … -expect …` | Run by hand: applies one wrong change to a Go source file through `go test -overlay` and prints detection, survivor, invalid or inconclusive (the `mutation-check` spec); fails unless the verdict is detection; writes nothing in the repository |\n| `task merge:check -- \u003Cn>` | `ateam review gate` run via `scripts\u002Fateam`, the pin (`task tools:ateam` installs it; `docs\u002Ftesting.md`): fails while the rules on `main` do not require an up-to-date head, while PR `n` is a code pull request, not a draft, without `implemented-by:` and `reviewed-by:` lines naming a not-weaker other agent and an approving review record at its head, or while an open `class:flake` issue is not closed by PR `n`; reads GitHub |\n| `task verify` | `ateam:doctor` first, then the checks above except `doctor`, `fmt`, `spec:queue`, `mutate:check`, `merge:check`, cheapest first with `test:tools:changed` after `test:unit` and `test:repeat` last; prints each step's time; fails on tracked-file change; `task verify -- checks` and `task verify -- integration` run the two halves CI runs as separate jobs (`integration`: `ateam:doctor`, `test:integration`, `cover:check`; `checks`: the rest) |\n\nCI has two workflows: in `ci.yml`, the jobs `checks` and `integration` run the two halves of `task verify` in parallel\nand `required` fails if either failed, is missing, or was skipped or cancelled; `merge-check.yml` runs\n`scripts\u002Fmerge-check.sh` for a pull request that is not a draft, from the base commit, on every push, ready and\ndescription edit. `task verify` needs a reachable Docker daemon for `test:integration`; a daemon that is not reachable\nis a failing gate, never a skipped one. A consumer lane joins `task verify` when its workload exists; until then no task\nfor it exists, and a missing lane is not a passing one.\n\nSelect by what the diff changes:\n\n- **Documentation or skill instructions only:** `task fmt:check`, `task docs:check`, and `git diff --check`; add\n  `task spec:check` when `openspec\u002F` changed.\n- **Agent setup (`AGENTS.md`, `CLAUDE.md`, `.agents\u002F`, `.claude\u002F`, `.codex\u002F`, `.gemini\u002F`):** `task ateam:doctor` and\n  `task test:unit` (`TestAgentSetupParity`).\n- **An OpenSpec change:** `task spec:check`, then read `task spec:queue` in this worktree.\n- **Go behavior:** `task test:unit` (plus `task test:tools` when `scripts\u002F`,\n  `internal\u002Fharness\u002F`, `.github\u002F` or `Taskfile.yml` changed), `task vet`, `task lint`, `task build`; focused tests first\n  during iteration.\n- **Docker-backed behavior (`internal\u002Fharness\u002Fnatsfixture`, any `*_integration_test.go`):**\n  `task test:integration -- \u003Cpkgs>` to focus, then `task cover:check`, which reads the profile of the last passing\n  integration run and refuses one taken on a different tree. A plain `go test -tags integration` run is fine while\n  iterating. The NATS image is the one line in `internal\u002Fharness\u002Fnatsfixture\u002Fnats-image`; to try another, edit that\n  line in a branch.\n- **`docs\u002Fadmission-ledger.yaml`:** `task ledger:check`.\n- **Dependencies or `go.mod`:** `task tidy:check` and `task vuln` in addition to the Go gates.\n- **Before any implementation push:** `task verify`.\n- **Immediately before merging:** `task merge:check -- \u003Cn>`, in a shell where `GITHUB_ACTIONS` is not set. It sees a\n  flake filed, a closing line removed, or a review record posted, since the pull request's last `Merge check` run.\n\nDo not hand-run a narrower command in place of a gate CI runs: the task owns flags and pins.\n\n## 3. Protect shared test infrastructure\n\nSerialize heavy work on a shared host. Docker inspection is diagnostic:\ncontainer age, a timeout signature, or a name pattern does not establish that a resource is abandoned or that a\nfailure is infrastructure-only. Preserve other sessions' resources. Cleanup is limited to an identified completed or\nabandoned run this session is authorized to clean up; host-wide pruning and stopping an unknown port holder are not\npreflight steps.\n\n## 4. Record Evidence and remaining gates\n\nRecord the tested HEAD (or dirty snapshot), exact command, exit status, assertions\u002Ftests actually exercised,\nand log\u002Fartifact location. A log under a path git ignores (such as `coverage\u002F`) is on this host only: say so,\nand put the output a reader needs in the PR. Separate failure, skip, no selected tests and compilation-only results.\nWhen the implementation changes, older green results remain evidence for the older revision. Preserve the command's\nfailure status when filtering output; do not infer success from a quiet log.\n\nResolve failures from evidence; a successful re-run is not a fix for a flake. A red that your diff does not explain\nis filed as an issue before the next push, labelled `class:flake` when it is a test or check that passes and fails\non the same tree. A network fetch that did not answer is not a flake, and a local red whose `host:` line shows a\none-minute load average at or above twice the core count is a host-load suspect first: follow the protocol's \"Known\nflakes\" item for both. An\nopen flake is fixed; nothing else gets a pull request past it, and `Merge check` fails every pull request that does\nnot close it. Long or paid runs need the role contract's active progress\nchecks and bounded stopping behavior.\n\nAfter local verification, assess the PR's current-head hosted checks and the protocol's review\u002Farchive gates.\nLocal green is not merge authorization. Follow existing user authorization without asking for it again, while\npreserving all outstanding required gates.\n",{"name":5,"description":7},"main","a8dd79128471bb120c59ffc1f2c5fdcc74d28c2b",".agents\u002Fskills\u002Fpreflight","https:\u002F\u002Fgithub.com\u002FC360Studio\u002Fsemengine","https:\u002F\u002Fgithub.com\u002FC360Studio","2026-11-15 06:29:50",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add C360Studio\u002Fsemengine --skill preflight",{"tool":36,"command":37},"bunx","bunx skills add C360Studio\u002Fsemengine --skill preflight",{"tool":39,"command":40},"pnpm","pnpm dlx skills add C360Studio\u002Fsemengine --skill preflight","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FC360Studio\u002Fsemengine\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpreflight\u002FSKILL.md",true,[],[45,52,59,66,72,79],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":19},"01M7DJNADQDES9RFB0RF39MARV","semengine-status","Report SemEngine Slice 04A package port progress, active PR claims, known flakes, and GitHub milestone\u002Fissue queue hygiene, and sync the GitHub Project v2 tracker. Use when asked for port status, auditing the issue queue, or updating the project board.","https:\u002F\u002Fgithub.com\u002FC360Studio\u002Fsemengine\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsemengine-status\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7DJN7JPA0M9VZZ5RRZ6XEMW","review-pr","Adapter for review-pr.","https:\u002F\u002Fgithub.com\u002FC360Studio\u002Fsemengine\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Freview-pr\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7DJN4VWVKR8B6Z7XVPKWGD8","query-pattern","Choose how code reads the graph: graph-ingest's declared request verbs, the typed exact-entity reader, or an owner's bucket access. Use when a component or a consumer needs to read entities.","https:\u002F\u002Fgithub.com\u002FC360Studio\u002Fsemengine\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fquery-pattern\u002FSKILL.md",[],[],{"skillNo":67,"name":5,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7DJN0VZEF1BYN6QCZDGRNF5","Select and run the existing SemEngine verification gates for a concrete diff before an implementation push or local-readiness assessment.","https:\u002F\u002Fgithub.com\u002FC360Studio\u002Fsemengine\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fpreflight\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7DJMZVCQQ7C0XBF8S65SAV2","ponytail","Adapter for ponytail.","https:\u002F\u002Fgithub.com\u002FC360Studio\u002Fsemengine\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fponytail\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7DJMYVPY0TAV1TBKSAP36ZZ","pickup","Adapter for pickup.","https:\u002F\u002Fgithub.com\u002FC360Studio\u002Fsemengine\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fpickup\u002FSKILL.md",[],[]]