[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74FGYA4EAVMWA1NT90AP3N6":3,"skill-same:01M74FGYA4EAVMWA1NT90AP3N6":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M74FGYA4EAVMWA1NT90AP3N6","test-runner-discovery",null,"Reads the manifests and lockfiles to decide whether a project's test runner has a parallel mode with its prerequisite installed, and emits a JSON record that paqad-ai checks record-runner validates. Use when checks run reported that the parallel mode is unknown.","Eliyce\u002Fpaqad-ai","Eliyce","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F173689792?v=4","01M74F7NHRXY2FW9KM93WHKHST","01M74F7NJDEWZ2XM9CQV70T3JK",8,"MIT","https:\u002F\u002Fgithub.com\u002FEliyce\u002Fpaqad-ai\u002Fblob\u002Fmain\u002Fruntime\u002Fbase\u002Fskills\u002Ftest-runner-discovery\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: test-runner-discovery\ndescription: \"Reads the manifests and lockfiles to decide whether a project's test runner has a parallel mode with its prerequisite installed, and emits a JSON record that paqad-ai checks record-runner validates. Use when checks run reported that the parallel mode is unknown.\"\nmetadata:\n  model_tier: fast\n  cacheable: 'false'\n  output_format: json\n  paqad-meta: skill.meta.yaml\n---\n\n## What It Does\n\nDecides how the project's own test runner parallelizes when paqad's script detection could not\n(`checks plan` printed `test: sequential (unknown)`). It reads the project's manifests and lockfiles,\nidentifies the runner the project's test script invokes, and decides whether a parallel mode exists\n**and its prerequisite is installed**: never assuming, never installing anything. It emits a small\nJSON record; the `paqad-ai checks record-runner` verb validates and stores it.\n\n## Use This When\n\n- A feature-development `checks run` reported `test ran sequentially: parallel mode unknown`, and you\n  want the next run to be fast. Run this once; the recorded decision makes every later run fast.\n\nDo **not** run this when `checks plan` already shows `parallel`, `native`, or a concrete\n`sequential (\u003Creason>)`: the script has already decided.\n\n## Inputs\n\n- `project_root`: the project to inspect.\n- `test_command`: the project's `commands.test`, the base the parallel command builds on.\n- Read `references\u002Fallowed-flags.md` for the exact tokens a `test_parallel` may add.\n\n## Procedure\n\n1. Read the ecosystem manifest and lockfile: `composer.json`\u002F`composer.lock`, `package.json` and its\n   lockfile, `pyproject.toml`\u002F`requirements*.txt`\u002F`poetry.lock`\u002F`uv.lock`, `Gemfile.lock`,\n   `build.gradle(.kts)`, `go.mod`, `Cargo.toml`, `pubspec.yaml`.\n2. Identify the runner the project's own test script invokes (mocha, tap, ava, …).\n3. Decide whether a parallel mode exists AND its prerequisite is present in the lockfile. If the\n   prerequisite is missing, the mode is `unavailable`: never propose installing it.\n4. When `available`, build `test_parallel` from `test_command` by adding only tokens listed in\n   `references\u002Fallowed-flags.md`, with `\u003Cprocesses>` exactly once. Never add any other token.\n5. Write `\u003Cscratch>\u002Ftest-runner.json` (see Output Contract) and hand it to the pipeline:\n   `paqad-ai checks record-runner \u003Cscratch>\u002Ftest-runner.json`. That verb runs the deterministic\n   guard and rejects anything outside the allowlist: do not re-implement that check here.\n\n## Output Contract\n\nA JSON object with exactly these keys:\n\n```json\n{\n  \"schema_version\": 1,\n  \"runner_id\": \"mocha\",\n  \"parallel\": \"available\",\n  \"reason\": null,\n  \"test_parallel\": \"pnpm test -- --parallel --jobs=\u003Cprocesses>\",\n  \"single_test_selector\": \"file\",\n  \"evidence\": [\"package.json\", \"pnpm-lock.yaml\"]\n}\n```\n\n- `parallel` is one of `available`, `unavailable`, `native`.\n- `test_parallel` is required when `available`, and must start with the project's own runner\n  invocation, then add only allowlisted tokens with `\u003Cprocesses>` exactly once.\n- `reason` is a short sentence when `unavailable`\u002F`unknown`, else `null`.\n- `evidence` is a non-empty list of files you read that exist under the project.\n\n## Escalate \u002F Stop Conditions\n\n- Emit `parallel: \"unavailable\"` with a plain `reason` when no parallel mode exists or its\n  prerequisite is missing. Never propose installing a package.\n\n## Resources\n\n- `references\u002Fallowed-flags.md`: the exact argv tokens a `test_parallel` may add.\n- `agents\u002Fopenai.yaml`: the agent interface metadata.\n","## What It Does\n\nDecides how the project's own test runner parallelizes when paqad's script detection could not\n(`checks plan` printed `test: sequential (unknown)`). It reads the project's manifests and lockfiles,\nidentifies the runner the project's test script invokes, and decides whether a parallel mode exists\n**and its prerequisite is installed**: never assuming, never installing anything. It emits a small\nJSON record; the `paqad-ai checks record-runner` verb validates and stores it.\n\n## Use This When\n\n- A feature-development `checks run` reported `test ran sequentially: parallel mode unknown`, and you\n  want the next run to be fast. Run this once; the recorded decision makes every later run fast.\n\nDo **not** run this when `checks plan` already shows `parallel`, `native`, or a concrete\n`sequential (\u003Creason>)`: the script has already decided.\n\n## Inputs\n\n- `project_root`: the project to inspect.\n- `test_command`: the project's `commands.test`, the base the parallel command builds on.\n- Read `references\u002Fallowed-flags.md` for the exact tokens a `test_parallel` may add.\n\n## Procedure\n\n1. Read the ecosystem manifest and lockfile: `composer.json`\u002F`composer.lock`, `package.json` and its\n   lockfile, `pyproject.toml`\u002F`requirements*.txt`\u002F`poetry.lock`\u002F`uv.lock`, `Gemfile.lock`,\n   `build.gradle(.kts)`, `go.mod`, `Cargo.toml`, `pubspec.yaml`.\n2. Identify the runner the project's own test script invokes (mocha, tap, ava, …).\n3. Decide whether a parallel mode exists AND its prerequisite is present in the lockfile. If the\n   prerequisite is missing, the mode is `unavailable`: never propose installing it.\n4. When `available`, build `test_parallel` from `test_command` by adding only tokens listed in\n   `references\u002Fallowed-flags.md`, with `\u003Cprocesses>` exactly once. Never add any other token.\n5. Write `\u003Cscratch>\u002Ftest-runner.json` (see Output Contract) and hand it to the pipeline:\n   `paqad-ai checks record-runner \u003Cscratch>\u002Ftest-runner.json`. That verb runs the deterministic\n   guard and rejects anything outside the allowlist: do not re-implement that check here.\n\n## Output Contract\n\nA JSON object with exactly these keys:\n\n```json\n{\n  \"schema_version\": 1,\n  \"runner_id\": \"mocha\",\n  \"parallel\": \"available\",\n  \"reason\": null,\n  \"test_parallel\": \"pnpm test -- --parallel --jobs=\u003Cprocesses>\",\n  \"single_test_selector\": \"file\",\n  \"evidence\": [\"package.json\", \"pnpm-lock.yaml\"]\n}\n```\n\n- `parallel` is one of `available`, `unavailable`, `native`.\n- `test_parallel` is required when `available`, and must start with the project's own runner\n  invocation, then add only allowlisted tokens with `\u003Cprocesses>` exactly once.\n- `reason` is a short sentence when `unavailable`\u002F`unknown`, else `null`.\n- `evidence` is a non-empty list of files you read that exist under the project.\n\n## Escalate \u002F Stop Conditions\n\n- Emit `parallel: \"unavailable\"` with a plain `reason` when no parallel mode exists or its\n  prerequisite is missing. Never propose installing a package.\n\n## Resources\n\n- `references\u002Fallowed-flags.md`: the exact argv tokens a `test_parallel` may add.\n- `agents\u002Fopenai.yaml`: the agent interface metadata.\n",{"name":5,"metadata":23,"description":7},{"cacheable":24,"model_tier":25,"paqad-meta":26,"output_format":27},"false","fast","skill.meta.yaml","json","main","793418e848ae0410573905284b68adcab385230e","runtime\u002Fbase\u002Fskills\u002Ftest-runner-discovery",0,"https:\u002F\u002Fgithub.com\u002FEliyce\u002Fpaqad-ai","https:\u002F\u002Fpaqad.ai","https:\u002F\u002Fgithub.com\u002FEliyce","https:\u002F\u002Feliyce.com\u002F","AI delivery you can review. Dutch software company building software and AI agents. Makers of Paqad, the open-source AI delivery framework.","2026-11-13 04:41:45",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add Eliyce\u002Fpaqad-ai --skill test-runner-discovery",{"tool":44,"command":45},"bunx","bunx skills add Eliyce\u002Fpaqad-ai --skill test-runner-discovery",{"tool":47,"command":48},"pnpm","pnpm dlx skills add Eliyce\u002Fpaqad-ai --skill test-runner-discovery","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FEliyce\u002Fpaqad-ai\u002Fblob\u002Fmain\u002Fruntime\u002Fbase\u002Fskills\u002Ftest-runner-discovery\u002FSKILL.md",true,[52,58,62],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"agents\u002Fopenai.yaml","REFERENCE","参考文档",164,"https:\u002F\u002Fgithub.com\u002FEliyce\u002Fpaqad-ai\u002Fblob\u002Fmain\u002Fruntime\u002Fbase\u002Fskills\u002Ftest-runner-discovery\u002Fagents\u002Fopenai.yaml",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fallowed-flags.md",1997,"https:\u002F\u002Fgithub.com\u002FEliyce\u002Fpaqad-ai\u002Fblob\u002Fmain\u002Fruntime\u002Fbase\u002Fskills\u002Ftest-runner-discovery\u002Freferences\u002Fallowed-flags.md",{"path":26,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":63,"sourceHtmlUrl":64},351,"https:\u002F\u002Fgithub.com\u002FEliyce\u002Fpaqad-ai\u002Fblob\u002Fmain\u002Fruntime\u002Fbase\u002Fskills\u002Ftest-runner-discovery\u002Fskill.meta.yaml",[66,73,80,85,92,99],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M74FSCKQP6TACC8X8AZ19F4V","sample-skill","Sample bundled skill fixture","https:\u002F\u002Fgithub.com\u002FEliyce\u002Fpaqad-ai\u002Fblob\u002Fmain\u002Ftests\u002Funit\u002Fadapters\u002Ffixtures\u002Fsample-skill\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M74FSAQ6C28V4G3322XGMARB","processing-invoices","Turns a supplier invoice into one ledger line. Use when a supplier invoice arrives and needs booking.","https:\u002F\u002Fgithub.com\u002FEliyce\u002Fpaqad-ai\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fauthoring\u002Fnpm-project\u002Fskill\u002FSKILL.md",[],[],{"skillNo":81,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M74FS914YQKWQNHC58MEG1N8","https:\u002F\u002Fgithub.com\u002FEliyce\u002Fpaqad-ai\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fauthoring\u002Flaravel-project\u002Fskill\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M74FS356J9QP10A362QRVCPZ","understand-idea","Chat and Claude Code: Step 1 of the discover journey: clarifies the goal, who benefits, success and constraints into the idea block. Use when the journey directs it to step 1, not directly.","https:\u002F\u002Fgithub.com\u002FEliyce\u002Fpaqad-ai\u002Fblob\u002Fmain\u002Fruntime\u002Fclaude-plugin\u002Fskills\u002Funderstand-idea\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M74FRSWEMB7KNVW0TP8P3JKB","size-work","Chat and Claude Code: Suggest a size for a ticket from comparable finished work, as a labelled suggestion the team still owns. Use it when someone asks \"how big is this?\", \"roughly how much work is ABC-12?\", or wants a backlog item sized. It finds the team's sizing scale at first use, picks two to five of the closest finished tickets with links, and gives a size or range with the drivers behind it and a confidence of low, medium or high, lowered and explained when the area's documents are template text. Every result is labelled a suggested size, never a date or a commitment. It writes nothing into the size field unless the user says \"set it\", and it refuses to overwrite an existing size unless the user asks to replace it. Produces the sizing block of the record.","https:\u002F\u002Fgithub.com\u002FEliyce\u002Fpaqad-ai\u002Fblob\u002Fmain\u002Fruntime\u002Fclaude-plugin\u002Fskills\u002Fsize-work\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":18},"01M74FR9A9VPHW1NFAFYZMXE2H","refine-ticket","Chat and Claude Code: Improve one or more existing tracker tickets without losing the author's intent. Use it when someone wants a ticket read, diagnosed and tidied up (\"this ticket is vague\", \"fix up ABC-12\", \"split this, it's too big\"). It reads each ticket in full and snapshots it with its last-updated time, says what is wrong with evidence, and proposes a field-by-field before and after change set limited to summary, description, labels, parent, links and new child tickets on a split. It writes nothing until an explicit \"apply it\" bound to that exact change set, re-checks the ticket for conflicting edits just before writing, never replaces rich descriptions with plain text, never deletes or closes a ticket, and reads each ticket back after applying. Produces the existing and changes blocks of the record.","https:\u002F\u002Fgithub.com\u002FEliyce\u002Fpaqad-ai\u002Fblob\u002Fmain\u002Fruntime\u002Fclaude-plugin\u002Fskills\u002Frefine-ticket\u002FSKILL.md",[],[]]