[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73NRH88ECP9C82CWHRQ4AC4":3,"skill-same:01M73NRH88ECP9C82CWHRQ4AC4":60},{"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":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M73NRH88ECP9C82CWHRQ4AC4","grilling",null,"Shared interview engine for \u002Fbrainstorm, \u002Fprd, and grill-me. Asks only the open frontier of a question set, looks up facts instead of asking them, and returns a question count. Engine only; not invoked on its own.","indigoai-us\u002Fhq-core","indigoai-us","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F122242446?v=4","01M71DTQ5NGD10GT1Z7E6XKWC5","HQ","01M71DTQ6BKSYYBNC9RAKT3YDK",95,"MIT","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgrilling\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: grilling\ndescription: Shared interview engine for \u002Fbrainstorm, \u002Fprd, and grill-me. Asks only the open frontier of a question set, looks up facts instead of asking them, and returns a question count. Engine only; not invoked on its own.\nuser-invocable: false\nallowed-tools: Read, Grep, Glob, AskUserQuestion, Task, Bash(bash .claude\u002Fskills\u002Fgrilling\u002Ffrontier.sh:*), Bash(bash .claude\u002Fskills\u002F_shared\u002Fjournal.sh:*), Bash\n---\n\n# Grilling Engine\n\nEngine skill. Caller skills (\u002Fbrainstorm, \u002Fprd, grill-me) load this file and run it with an input contract. Users do not run it directly. If a user types `\u002Fgrilling`, tell them to use \u002Fbrainstorm, \u002Fprd, or grill-me instead.\n\nPattern source: mattpocock\u002Fskills `skills\u002Fproductivity\u002Fgrilling` (design tree, frontier rounds, facts are the agent's job). HQ changes the default: one question per AskUserQuestion call, with rounds available only on request.\n\n## Input contract\n\n| Input | Required | Meaning |\n|-------|----------|---------|\n| question_set | yes | Path to a question-set file. Format: `.claude\u002Fskills\u002F_shared\u002Fquestions\u002FFORMAT.md`. |\n| known_facts | no | Map of question id to answer, already settled by the caller (from the brief, a brainstorm, the board, or earlier answers). These ids are never asked. |\n| mode | no | `one-at-a-time` (default) or `rounds`. |\n| max_questions | no | Upper bound on questions put to the user. Default: no limit. When reached, remaining decisions take their recommended option and are logged as assumed. |\n\n`mode: rounds` is set only when the user explicitly asks for rounds in this session or the caller received a `--rounds` argument. Never infer it from the size of the set, the user's tone, or time pressure.\n\n## Helper\n\n`.claude\u002Fskills\u002Fgrilling\u002Ffrontier.sh` parses the set and computes the frontier. Use it rather than computing dependencies by hand.\n\n```bash\nbash .claude\u002Fskills\u002Fgrilling\u002Ffrontier.sh frontier \u003Cquestion_set> --known \u003Cids> --answered \u003Cids>\nbash .claude\u002Fskills\u002Fgrilling\u002Ffrontier.sh count \u003Cquestion_set> --known \u003Cids>\n```\n\n`frontier` prints the open decision ids in file order. `count` validates the set and prints the count object for a full run. Exit 2 means the set is malformed or has a dependency cycle; stop and report the error to the caller.\n\n## Procedure\n\n1. **Validate.** Run `frontier.sh count` with the known ids. On exit 2, return the error to the caller without asking anything.\n2. **Resolve facts.** For every `kind: fact` question whose `depends_on` are resolved, find the answer yourself: caller research, the company board, repo files, or a Task subagent lookup. Never put a fact question to the user. A pending lookup blocks only the questions that depend on it; keep asking the rest of the frontier.\n3. **Compute the frontier.** Run `frontier.sh frontier` with known ids plus everything answered so far. A question whose dependency is still open waits for a later pass.\n4. **Ask.**\n   - **one-at-a-time (default):** one AskUserQuestion call per frontier question. Offer 2 to 4 options from the question's `options`. When research or known facts support the `recommended` option, put it first and append ` (Recommended)` to its label. Wait for the answer before the next call.\n   - **rounds:** present the whole frontier as one numbered block, then wait for the reply.\n\n     ```\n     Q1 - \u003Cquestion text>\n     Options: A) \u003Copt> B) \u003Copt> C) \u003Copt>\n     Recommended: A) \u003Copt>\n\n     Q2 - ...\n     ```\n\n     Word each question so \"yes\" accepts the recommendation. Accept shorthand replies: `yes` or `y` (accept all recommendations), `1A 2C`, `2: \u003Cfree text>`, or `all recommended except 3B`. Questions not mentioned in a reply take the recommendation only when the reply was `yes`; otherwise ask about them again in the next round.\n5. **Record.** After each answer, append it to the active journal:\n\n   ```bash\n   bash .claude\u002Fskills\u002F_shared\u002Fjournal.sh append \u003Cproject_dir> decisions \"\u003Cquestion id>: \u003Canswer>\"\n   ```\n\n   Facts found in step 2 go under `findings` with their id and source.\n6. **Repeat** steps 2 to 5 until the frontier is empty or `max_questions` is reached.\n7. **Return** the answers map and the count object to the caller.\n\n## Headless\n\nWhen `CLAUDE_HEADLESS=1`, do not call AskUserQuestion. Take the recommended option for each decision, log it under `decisions` with the suffix `(assumed, headless)`, and count it under `asked`.\n\n## Count object\n\n```json\n{\"asked\": 7, \"skipped_known\": 3, \"skipped_fact\": 2,\n \"by_tier\": {\"strategic\": 1, \"architecture\": 3, \"quality\": 3}}\n```\n\n- `asked`: decisions put to the user (or assumed under headless or `max_questions`).\n- `skipped_known`: ids supplied in `known_facts`.\n- `skipped_fact`: fact questions resolved by lookup.\n- `by_tier`: `asked` split by tier.\n\nTest: `bash core\u002Fscripts\u002Ftests\u002Fgrilling-count.test.sh`.\n","# Grilling Engine\n\nEngine skill. Caller skills (\u002Fbrainstorm, \u002Fprd, grill-me) load this file and run it with an input contract. Users do not run it directly. If a user types `\u002Fgrilling`, tell them to use \u002Fbrainstorm, \u002Fprd, or grill-me instead.\n\nPattern source: mattpocock\u002Fskills `skills\u002Fproductivity\u002Fgrilling` (design tree, frontier rounds, facts are the agent's job). HQ changes the default: one question per AskUserQuestion call, with rounds available only on request.\n\n## Input contract\n\n| Input | Required | Meaning |\n|-------|----------|---------|\n| question_set | yes | Path to a question-set file. Format: `.claude\u002Fskills\u002F_shared\u002Fquestions\u002FFORMAT.md`. |\n| known_facts | no | Map of question id to answer, already settled by the caller (from the brief, a brainstorm, the board, or earlier answers). These ids are never asked. |\n| mode | no | `one-at-a-time` (default) or `rounds`. |\n| max_questions | no | Upper bound on questions put to the user. Default: no limit. When reached, remaining decisions take their recommended option and are logged as assumed. |\n\n`mode: rounds` is set only when the user explicitly asks for rounds in this session or the caller received a `--rounds` argument. Never infer it from the size of the set, the user's tone, or time pressure.\n\n## Helper\n\n`.claude\u002Fskills\u002Fgrilling\u002Ffrontier.sh` parses the set and computes the frontier. Use it rather than computing dependencies by hand.\n\n```bash\nbash .claude\u002Fskills\u002Fgrilling\u002Ffrontier.sh frontier \u003Cquestion_set> --known \u003Cids> --answered \u003Cids>\nbash .claude\u002Fskills\u002Fgrilling\u002Ffrontier.sh count \u003Cquestion_set> --known \u003Cids>\n```\n\n`frontier` prints the open decision ids in file order. `count` validates the set and prints the count object for a full run. Exit 2 means the set is malformed or has a dependency cycle; stop and report the error to the caller.\n\n## Procedure\n\n1. **Validate.** Run `frontier.sh count` with the known ids. On exit 2, return the error to the caller without asking anything.\n2. **Resolve facts.** For every `kind: fact` question whose `depends_on` are resolved, find the answer yourself: caller research, the company board, repo files, or a Task subagent lookup. Never put a fact question to the user. A pending lookup blocks only the questions that depend on it; keep asking the rest of the frontier.\n3. **Compute the frontier.** Run `frontier.sh frontier` with known ids plus everything answered so far. A question whose dependency is still open waits for a later pass.\n4. **Ask.**\n   - **one-at-a-time (default):** one AskUserQuestion call per frontier question. Offer 2 to 4 options from the question's `options`. When research or known facts support the `recommended` option, put it first and append ` (Recommended)` to its label. Wait for the answer before the next call.\n   - **rounds:** present the whole frontier as one numbered block, then wait for the reply.\n\n     ```\n     Q1 - \u003Cquestion text>\n     Options: A) \u003Copt> B) \u003Copt> C) \u003Copt>\n     Recommended: A) \u003Copt>\n\n     Q2 - ...\n     ```\n\n     Word each question so \"yes\" accepts the recommendation. Accept shorthand replies: `yes` or `y` (accept all recommendations), `1A 2C`, `2: \u003Cfree text>`, or `all recommended except 3B`. Questions not mentioned in a reply take the recommendation only when the reply was `yes`; otherwise ask about them again in the next round.\n5. **Record.** After each answer, append it to the active journal:\n\n   ```bash\n   bash .claude\u002Fskills\u002F_shared\u002Fjournal.sh append \u003Cproject_dir> decisions \"\u003Cquestion id>: \u003Canswer>\"\n   ```\n\n   Facts found in step 2 go under `findings` with their id and source.\n6. **Repeat** steps 2 to 5 until the frontier is empty or `max_questions` is reached.\n7. **Return** the answers map and the count object to the caller.\n\n## Headless\n\nWhen `CLAUDE_HEADLESS=1`, do not call AskUserQuestion. Take the recommended option for each decision, log it under `decisions` with the suffix `(assumed, headless)`, and count it under `asked`.\n\n## Count object\n\n```json\n{\"asked\": 7, \"skipped_known\": 3, \"skipped_fact\": 2,\n \"by_tier\": {\"strategic\": 1, \"architecture\": 3, \"quality\": 3}}\n```\n\n- `asked`: decisions put to the user (or assumed under headless or `max_questions`).\n- `skipped_known`: ids supplied in `known_facts`.\n- `skipped_fact`: fact questions resolved by lookup.\n- `by_tier`: `asked` split by tier.\n\nTest: `bash core\u002Fscripts\u002Ftests\u002Fgrilling-count.test.sh`.\n",{"name":5,"description":7,"allowed-tools":24,"user-invocable":20},"Read, Grep, Glob, AskUserQuestion, Task, Bash(bash .claude\u002Fskills\u002Fgrilling\u002Ffrontier.sh:*), Bash(bash .claude\u002Fskills\u002F_shared\u002Fjournal.sh:*), Bash","main","205cf61728a27ef15e9153aa38df5856fc8d82f5",".claude\u002Fskills\u002Fgrilling",18,"https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core","https:\u002F\u002Fgithub.com\u002Findigoai-us","https:\u002F\u002Fhqforwork.com\u002F","The AI Context Layer for Teams","2026-11-12 06:53:38",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add indigoai-us\u002Fhq-core --skill grilling",{"tool":40,"command":41},"bunx","bunx skills add indigoai-us\u002Fhq-core --skill grilling",{"tool":43,"command":44},"pnpm","pnpm dlx skills add indigoai-us\u002Fhq-core --skill grilling","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgrilling\u002FSKILL.md",true,[48,54],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"agents\u002Fopenai.yaml","REFERENCE","参考文档",131,"https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgrilling\u002Fagents\u002Fopenai.yaml",{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"frontier.sh","SCRIPT","脚本",4694,"https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgrilling\u002Ffrontier.sh",[61,68,75,82,89,96],{"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":19},"01M73NTNKZ3T2KJNDP2ZF23645","job","Deprecated alias for \u002Fschedule — Outpost recurring agent jobs. Prefer \u002Fschedule.","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fjob\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":19},"01M73NTE0H9DQTT6DNHDKRWTXW","import-claude","Deprecated alias for \u002Fimport-context — bootstrap HQ from your prior AI footprint (Claude Code, Codex, Grok, claude.ai history plus on-disk artifacts).","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimport-claude\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":19},"01M73NT67433KKX96CCJWDQQ0X","hq-whoami","Show current HQ Cognito identity and session expiry.","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhq-whoami\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":19},"01M73NT17SVXZV2QPT14C2RPJP","hq-share","Share HQ vault paths through single-use links or direct ACL grants.","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhq-share\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M73NSXYFMD7EHGT8TFDZA3C8","hq-secrets","Use HQ CLI secrets safely through env injection or one-off exec.","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhq-secrets\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M73NSWCXJK29Q8CNG8AS3ZZQ","hq-logout","Sign out of HQ Cognito and clear local tokens.","https:\u002F\u002Fgithub.com\u002Findigoai-us\u002Fhq-core\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhq-logout\u002FSKILL.md",[],[]]