[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77N05QRGB93R92J71569ACF":3,"skill-same:01M77N05QRGB93R92J71569ACF":48},{"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":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M77N05QRGB93R92J71569ACF","convert-prompt-to-saill",null,"Convert a natural-language prompt into a SAILL agent-team flow — roles with model groups, control-flow flags (parallel\u002Fwait\u002FLoop\u002Fif needed\u002Fif asked\u002Fask user), boxes for sub-teams and nesting, and -context- for run-time values. Use when the user types \u002Fconvert-prompt-to-saill, says \"turn this into SAILL\", \"convert my prompt to SAILL\", or \"express this as an agent team \u002F SAILL flow\".","HorizonBrute\u002FStandardized_AI_Looping_Language-SAILL","HorizonBrute","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F276460073?v=4","01M77MZSN5TNRPH1XW0XH3BTHZ","Brian","01M77MZSNYAYQG6JKD0YQ9GAWN",1,"MIT","https:\u002F\u002Fgithub.com\u002FHorizonBrute\u002FStandardized_AI_Looping_Language-SAILL\u002Fblob\u002Fmain\u002Fskills\u002Fconvert-prompt-to-saill\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\r\nname: convert-prompt-to-saill\r\ndescription: Convert a natural-language prompt into a SAILL agent-team flow — roles with model groups, control-flow flags (parallel\u002Fwait\u002FLoop\u002Fif needed\u002Fif asked\u002Fask user), boxes for sub-teams and nesting, and -context- for run-time values. Use when the user types \u002Fconvert-prompt-to-saill, says \"turn this into SAILL\", \"convert my prompt to SAILL\", or \"express this as an agent team \u002F SAILL flow\".\r\ntools: Read, Bash\r\n---\r\n\r\n# Skill: \u002Fconvert-prompt-to-saill\r\n\r\n**Model preference:** `#midcost` (per `horizon_aios_model_prefs.md`; overridable by a prompt directive).\r\n\r\nTurn \"here's my prompt\" into its **SAILL** form — the standard, shareable agent-team notation\r\n(roles + model groups + flags + boxes + loops + `-context-`). The deliverable is the compact,\r\nportable representation behind a plain-English request, which the user can then run, save as a\r\nteam, or share. Authoritative grammar: `documentation\u002Fsystem\u002Fagent_teams.md` (SAILL, §8) and the\r\nflag catalog `$HORIZON_ETC\u002Fagent_team_flags.md`.\r\n\r\n---\r\n\r\n## When to invoke\r\n\r\n`\u002Fconvert-prompt-to-saill \u003Cprompt>`, or the user asks to turn a prompt into SAILL \u002F express\r\nwork as an agent team.\r\n\r\n---\r\n\r\n## Step 1 — Load the vocabulary (do not invent flags)\r\n\r\n1.1 Recognized flags: `python $HORIZON_BIN\u002Fresolve_agent_teams.py --flags`.\r\n1.2 Existing teams (reuse one if it fits): `python $HORIZON_BIN\u002Fresolve_agent_teams.py --json`.\r\nUse only flags in the registry and `#groups` defined in `horizon_aios_model_prefs.md`.\r\n\r\n---\r\n\r\n## Step 2 — Analyze the prompt\r\n\r\nDecompose the prompt into a flow:\r\n1. **Roles** — the distinct units of work; for each, a short charter (what it does).\r\n2. **Order** — sequential vs concurrent; mark concurrency with `parallel` + a following `wait`.\r\n3. **Iteration** — \"until it passes \u002F retry\" → a `**Loop:**` back to a named role, with a cap.\r\n4. **Gates** — \"ask me \u002F approve first\" → `ask user`; \"only if needed\" → `if needed`; \"only if I ask\" → `if asked`.\r\n5. **Sub-agents \u002F nesting** — group related roles in a box `[ … ]`; name it for an ephemeral sub-team `Name[ … ]`; nest as deep as the prompt implies.\r\n6. **Context values** — anything left to runtime (a scope, a pass condition, a cap) → `-context-` \u002F `-context-\u003Cname>`.\r\n\r\n---\r\n\r\n## Step 3 — Map to SAILL\r\n\r\n3.1 If the prompt matches a shipped team (e.g. \"investigate and fix X\"), reuse it by name and\r\nadd only the prompt's specifics (scope, flags) — do not reinvent.\r\n\r\n3.2 Otherwise compose roles. Assign each a `#group` by the kind of work (mirror\r\n`horizon_aios_model_prefs.md` Task-Class Routing): security \u002F architecture \u002F review → `#highcap`;\r\nresearch \u002F exploration → `#investigate`; mechanical \u002F edits \u002F summarizing → `#lowcost`;\r\ndebugging \u002F coding → `#debug`; otherwise → `#midcost`.\r\n\r\n3.3 Apply the flags, boxes, loops, and `-context-` from Step 2. Prefer named loop targets and\r\nthe most one-line-readable form that stays faithful.\r\n\r\n---\r\n\r\n## Step 4 — Output\r\n\r\n4.1 The **SAILL block** — either the `agent_teams.md` role format (`### Name` + numbered roles)\r\nor a one-line box expression, whichever is clearer for this flow.\r\n\r\n4.2 A short **gloss**: map each role \u002F flag back to the phrase in the prompt it came from.\r\n\r\n4.3 Call out any `-context-` placeholders and what fills them at run time.\r\n\r\n---\r\n\r\n## Step 5 — Offer next steps\r\n\r\nOffer to **save** it as a reusable team (`\u002Fagent-teams`), **run** it (\"send this team …\"), or\r\n**test** it (`\u002Ftest-agent-teams \u003Cname>`). Do NOT execute the work here — this skill only converts.\r\n\r\n---\r\n\r\n## Notes for the executing agent\r\n\r\n1. Use ONLY flags from the registry and `#groups` from model-prefs — never invent vocabulary.\r\n   If the prompt needs a new one, offer `\u002Fagent-teams` (add a flag) or `\u002Fmodel-prefs` (add a group).\r\n2. SAILL governs control flow; a role's *work* is charter prose (§1.2) — keep \"run skill X\" \u002F\r\n   \"scope to Y\" in the charter or as `-context-`, never as a flag.\r\n3. Keep the output terse and human-readable — the value of SAILL is a compact, shareable form.\r\n4. This converts only; it never runs the flow.\r\n","# Skill: \u002Fconvert-prompt-to-saill\r\n\r\n**Model preference:** `#midcost` (per `horizon_aios_model_prefs.md`; overridable by a prompt directive).\r\n\r\nTurn \"here's my prompt\" into its **SAILL** form — the standard, shareable agent-team notation\r\n(roles + model groups + flags + boxes + loops + `-context-`). The deliverable is the compact,\r\nportable representation behind a plain-English request, which the user can then run, save as a\r\nteam, or share. Authoritative grammar: `documentation\u002Fsystem\u002Fagent_teams.md` (SAILL, §8) and the\r\nflag catalog `$HORIZON_ETC\u002Fagent_team_flags.md`.\r\n\r\n---\r\n\r\n## When to invoke\r\n\r\n`\u002Fconvert-prompt-to-saill \u003Cprompt>`, or the user asks to turn a prompt into SAILL \u002F express\r\nwork as an agent team.\r\n\r\n---\r\n\r\n## Step 1 — Load the vocabulary (do not invent flags)\r\n\r\n1.1 Recognized flags: `python $HORIZON_BIN\u002Fresolve_agent_teams.py --flags`.\r\n1.2 Existing teams (reuse one if it fits): `python $HORIZON_BIN\u002Fresolve_agent_teams.py --json`.\r\nUse only flags in the registry and `#groups` defined in `horizon_aios_model_prefs.md`.\r\n\r\n---\r\n\r\n## Step 2 — Analyze the prompt\r\n\r\nDecompose the prompt into a flow:\r\n1. **Roles** — the distinct units of work; for each, a short charter (what it does).\r\n2. **Order** — sequential vs concurrent; mark concurrency with `parallel` + a following `wait`.\r\n3. **Iteration** — \"until it passes \u002F retry\" → a `**Loop:**` back to a named role, with a cap.\r\n4. **Gates** — \"ask me \u002F approve first\" → `ask user`; \"only if needed\" → `if needed`; \"only if I ask\" → `if asked`.\r\n5. **Sub-agents \u002F nesting** — group related roles in a box `[ … ]`; name it for an ephemeral sub-team `Name[ … ]`; nest as deep as the prompt implies.\r\n6. **Context values** — anything left to runtime (a scope, a pass condition, a cap) → `-context-` \u002F `-context-\u003Cname>`.\r\n\r\n---\r\n\r\n## Step 3 — Map to SAILL\r\n\r\n3.1 If the prompt matches a shipped team (e.g. \"investigate and fix X\"), reuse it by name and\r\nadd only the prompt's specifics (scope, flags) — do not reinvent.\r\n\r\n3.2 Otherwise compose roles. Assign each a `#group` by the kind of work (mirror\r\n`horizon_aios_model_prefs.md` Task-Class Routing): security \u002F architecture \u002F review → `#highcap`;\r\nresearch \u002F exploration → `#investigate`; mechanical \u002F edits \u002F summarizing → `#lowcost`;\r\ndebugging \u002F coding → `#debug`; otherwise → `#midcost`.\r\n\r\n3.3 Apply the flags, boxes, loops, and `-context-` from Step 2. Prefer named loop targets and\r\nthe most one-line-readable form that stays faithful.\r\n\r\n---\r\n\r\n## Step 4 — Output\r\n\r\n4.1 The **SAILL block** — either the `agent_teams.md` role format (`### Name` + numbered roles)\r\nor a one-line box expression, whichever is clearer for this flow.\r\n\r\n4.2 A short **gloss**: map each role \u002F flag back to the phrase in the prompt it came from.\r\n\r\n4.3 Call out any `-context-` placeholders and what fills them at run time.\r\n\r\n---\r\n\r\n## Step 5 — Offer next steps\r\n\r\nOffer to **save** it as a reusable team (`\u002Fagent-teams`), **run** it (\"send this team …\"), or\r\n**test** it (`\u002Ftest-agent-teams \u003Cname>`). Do NOT execute the work here — this skill only converts.\r\n\r\n---\r\n\r\n## Notes for the executing agent\r\n\r\n1. Use ONLY flags from the registry and `#groups` from model-prefs — never invent vocabulary.\r\n   If the prompt needs a new one, offer `\u002Fagent-teams` (add a flag) or `\u002Fmodel-prefs` (add a group).\r\n2. SAILL governs control flow; a role's *work* is charter prose (§1.2) — keep \"run skill X\" \u002F\r\n   \"scope to Y\" in the charter or as `-context-`, never as a flag.\r\n3. Keep the output terse and human-readable — the value of SAILL is a compact, shareable form.\r\n4. This converts only; it never runs the flow.\r\n",{"name":5,"tools":24,"description":7},"Read, Bash","main","8a4ca12d361bc175421fec529d1253b0fd095053","skills\u002Fconvert-prompt-to-saill",0,"https:\u002F\u002Fgithub.com\u002FHorizonBrute\u002FStandardized_AI_Looping_Language-SAILL","https:\u002F\u002Fhorizonbrute.github.io\u002FStandardized_AI_Looping_Language-SAILL\u002F","https:\u002F\u002Fgithub.com\u002FHorizonBrute","Telecom, ICS\u002FSCADA, Systems ,Network, Cloud, Blue Team, Red Team - 25 Years of Deep engineering expertise across many domains.  Adapting to the Agentic AI Age.","2026-07-06 03:41:04",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add HorizonBrute\u002FStandardized_AI_Looping_Language-SAILL --skill convert-prompt-to-saill",{"tool":40,"command":41},"bunx","bunx skills add HorizonBrute\u002FStandardized_AI_Looping_Language-SAILL --skill convert-prompt-to-saill",{"tool":43,"command":44},"pnpm","pnpm dlx skills add HorizonBrute\u002FStandardized_AI_Looping_Language-SAILL --skill convert-prompt-to-saill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHorizonBrute\u002FStandardized_AI_Looping_Language-SAILL\u002Fblob\u002Fmain\u002Fskills\u002Fconvert-prompt-to-saill\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M77N1KBR2TAJZC5HGJ473W9G","try-my-prompt","Take a natural-language prompt and return two outputs — an agent_teams.md SAILL entry and a terse one-line invocation — by invoking \u002Fconvert-prompt-to-saill and formatting the result.","https:\u002F\u002Fgithub.com\u002FHorizonBrute\u002FStandardized_AI_Looping_Language-SAILL\u002Fblob\u002Fmain\u002Fskills\u002Ftry-my-prompt\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M77N1G1W9WCHB0ABBDG9VTEZ","test_saill_in_skill","Proof-of-concept SAILL-in-skill. Replaces a wordy dirtree-check skill with a tight SAILL block. Audits tested_implementations nonce coverage via the Nonce Trace Audit team.","https:\u002F\u002Fgithub.com\u002FHorizonBrute\u002FStandardized_AI_Looping_Language-SAILL\u002Fblob\u002Fmain\u002Fskills\u002Ftest_saill_in_skill\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M77N1AG3VQB8CF6T3E40J6MX","test-agent-teams","End-to-end self-test of the Agent Teams system — walk every defined team (or one named team) and spawn each role so it echoes a self-generated nonce, its role, what it was told to do (its charter), and the model it actually ran as. Use when the user types \u002Ftest-agent-teams --all-teams (all) or \u002Ftest-agent-teams \u003Cteam-name> (one team), says \"test the agent teams\", \"run the agent-team self-test\", or wants to verify team resolution + model routing. The skill generates its own nonce.","https:\u002F\u002Fgithub.com\u002FHorizonBrute\u002FStandardized_AI_Looping_Language-SAILL\u002Fblob\u002Fmain\u002Fskills\u002Ftest-agent-teams\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M77N144ZFHBAZ2SQHMAWCBHG","saill-to-english","Translate a SAILL agent-team definition into plain English — render every primitive, loop, box, flag, and -context- placeholder as natural language a non-technical reader can follow. Use when the user types \u002Fsaill-to-english, says \"translate this SAILL\", \"explain this team definition\", \"what does this loop do\", or \"describe this in plain English\".","https:\u002F\u002Fgithub.com\u002FHorizonBrute\u002FStandardized_AI_Looping_Language-SAILL\u002Fblob\u002Fmain\u002Fskills\u002Fsaill-to-english\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M77N0YMTQ74XENKMQ6D0CPN0","model-prefs","Configure or inspect the in-context model-preference layer — model groups (incl. local\u002FBYO models), per-session slots, and task-class routing — by editing the gitignored extend file. Use when the user types \u002Fmodel-prefs, asks to \"set up model groups\", \"define","https:\u002F\u002Fgithub.com\u002FHorizonBrute\u002FStandardized_AI_Looping_Language-SAILL\u002Fblob\u002Fmain\u002Fskills\u002Fmodel-prefs\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M77N0TQ2P0K01Q5GAJYVM8CV","model-prefs-test","Test which model the model-preference config actually resolves to per group, and (in live mode) spawn small test agents by group name to confirm the spawn honors it. Use when the user types \u002Fmodel-prefs-test, or says \"test my model prefs\", \"check which model","https:\u002F\u002Fgithub.com\u002FHorizonBrute\u002FStandardized_AI_Looping_Language-SAILL\u002Fblob\u002Fmain\u002Fskills\u002Fmodel-prefs-test\u002FSKILL.md",[],[]]