[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7560GK1R43K7F0FNHTB0GHC":3,"skill-same:01M7560GK1R43K7F0FNHTB0GHC":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7560GK1R43K7F0FNHTB0GHC","clarify",null,"Full execution protocol for MODE: CLARIFY -- structured clarification funnel with critic review before surfacing user decisions.","AlexanderNarbaev\u002Fagi","AlexanderNarbaev","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F33544956?v=4","01M755ZKB1JJ26ZBNZSDJ4C0TV","01M755ZKBX072HZMHVQBWK7MK7",1,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002FAlexanderNarbaev\u002Fagi\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fclarify\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: clarify\ndescription: >\n  Full execution protocol for MODE: CLARIFY -- structured clarification funnel with critic review before surfacing user decisions.\n---\n\n# Clarify Protocol\n\nThis protocol is loaded on demand by the architect stub in src\u002Fagents\u002Farchitect.ts. The architect prompt keeps only activation, action, and hard safety constraints; the full execution details live here.\n\n### MODE: CLARIFY\nAmbiguous request → Run the clarification funnel\nClear request → MODE: DISCOVER\n\n### Clarification Funnel\n\nBefore surfacing any clarification question to the user, the architect MUST run this four-stage funnel. The goal is to limit unnecessary user interruption, not planning completeness.\n\n#### Stage 1: Inventory All Material Uncertainties\n\nIdentify ALL uncertainties that could affect:\n- Scope boundaries\n- User-visible behavior\n- Destructive behavior or data loss\n- Security\u002Fprivacy posture\n- Backward compatibility\n- Migrations or rollout strategy\n- Cost\u002Fperformance tradeoffs\n- Operational complexity\n- QA gate selection or enforcement strictness\n- Architecture choice among materially different paths\n- Dependency or platform assumptions\n\nThere is NO hard cap on the internal inventory. Record every material uncertainty found.\n\n#### Stage 2: Classify Each Uncertainty\n\nClassify each item as exactly one of:\n- `self_resolved`: answered from the user request, spec, plan, codebase reality check, `.swarm\u002Fcontext.md`, repo conventions, or an informed default. **If the default is not directly supported by user request, spec, or recorded context, classify as `user_decision` rather than `self_resolved`.**\n- `critic_resolved`: sent to Critic Sounding Board and resolved by the critic.\n- `research_needed`: needs SME\u002Fexplorer\u002Fdomain lookup before user escalation. **Important:** If research is ongoing, monitor the timeout configured in `.swarm\u002Fconfig.json` under `research_needed_timeout_ms` (default: 300000ms \u002F 5 minutes). If research does not complete before the timeout expires, automatically reclassify the item to `user_decision` with a note that research was incomplete, then surface it to the user. This prevents the clarification funnel from stalling while waiting for external research.\n- `user_decision`: only the user can decide because it affects product scope, risk tolerance, policy, budget, UX, rollout, or destructive behavior.\n- `deferred_nonblocking`: useful follow-up detail that does not block a correct initial plan and can be explicitly recorded as an assumption or follow-up.\n\n#### Stage 3: Consult Critic Sounding Board\n\nBefore asking the user any clarification question, the architect MUST consult `critic_sounding_board` with the candidate question set and context.\n\nFor each item classified as `research_needed` or `user_decision` in Stage 2, send it to the critic. The critic responds with a verdict from `SoundingBoardVerdict` (see `src\u002Fagents\u002Fcritic.ts`). The mapping between critic verdicts and funnel actions is:\n\n| Critic Verdict (SoundingBoardVerdict) | Funnel Action | Meaning |\n|---|---|---|\n| `UNNECESSARY` | DROP | Item is unnecessary or answerable from existing context |\n| `RESOLVE` | RESOLVE | Critic supplies the answer or recommended default |\n| `REPHRASE` | REPHRASE | Question is valid but should be clearer, narrower, or grouped |\n| `APPROVED` | ASK_USER | User decision is genuinely required |\n\n**Hard constraint:** Items in the Always-Surface Categories list (below) MUST NOT receive `UNNECESSARY`\u002F`DROP` from the critic — only `REPHRASE` or `APPROVED`\u002F`ASK_USER` are allowed. If the critic attempts to `UNNECESSARY`\u002F`DROP` an always-surface item, override to `APPROVED`\u002F`ASK_USER`.\n\n**Overconfidence guard:** If the critic attempts to self-resolve an item by supplying an answer (verdict `RESOLVE`) but the underlying default is not directly supported by user request, spec, or recorded context, the architect MUST classify the item as `user_decision` rather than `self_resolved`. Unsupported defaults must not be silently accepted.\n\nUpdate classifications based on critic response:\n- `UNNECESSARY`\u002F`DROP` → reclassify as `self_resolved` and record the reason.\n- `RESOLVE` → reclassify as `critic_resolved` and record the answer as an assumption.\n- `REPHRASE` → update the question wording and keep as candidate.\n- `APPROVED`\u002F`ASK_USER` → confirm as `user_decision`.\n\nRecord all resolved items as explicit assumptions before proceeding.\n\n#### Stage 4: Surface User Decision Packet\n\nIf any items remain classified as `user_decision` after Stage 3, present them as a structured decision packet — NOT as an arbitrary subset.\n\nThe packet MUST include for each decision:\n- Category grouping (scope, security, compatibility, performance, UX, rollout, QA policy)\n- Why the decision matters\n- Recommended default when safe\n- Options being weighed\n- Impact of accepting the default\n- Blocking vs optional marker\n\nThe architect MAY ask questions one at a time in interactive mode, but MUST preserve and report the full unresolved list. The architect MUST NOT drop unresolved decisions because of a session question cap.\n\n### Always-Surface Categories\n\nThe critic may improve wording or confirm prior context, but these categories MUST be surfaced to the user unless already explicitly answered by the user or by recorded context:\n- Scope boundaries: what is in or out\n- Data loss or destructive behavior\n- Security\u002Fprivacy risk tolerance\n- Backward compatibility or migration policy\n- Breaking changes to existing APIs, contracts, or interfaces\n- New dependency additions or version changes\n- Deprecation decisions for existing features or APIs\n- Cross-platform impact (Windows\u002FmacOS\u002FLinux differences)\n- Cost\u002Fperformance tradeoffs\n- User-visible behavior and UX choices\n- Release\u002Frollout strategy\n- Optional QA gates or stricter enforcement modes\n- Any choice that changes whether the work is advisory vs hard-blocking\n\n### Assumptions Recording\n\nAll items resolved in Stages 2-3 (self_resolved, critic_resolved, deferred_nonblocking) MUST be recorded as explicit assumptions in the spec, plan, or `.swarm\u002Fcontext.md`. Silently dropping resolved uncertainties is a protocol violation — every uncertainty that entered the funnel must have a recorded outcome.\n\n### Mechanical Enforcement of DROP Protection\n\n**Implementation Note:** The hard constraint against `DROP` on always-surface items (defined in Stage 3 of the clarification funnel) is currently enforced via skill instructions to the architect. A lightweight runtime enforcement mechanism is recommended: when processing the critic sounding board verdict response in `src\u002Fagents\u002Fcritic.ts`, validate that any items tagged as \"always-surface\" do not receive `UNNECESSARY`\u002F`DROP` verdicts. If a DROP verdict is encountered on an always-surface item, override it to `APPROVED`\u002F`ASK_USER` at the code level rather than relying solely on prompt-based enforcement.\n\nThis mechanical enforcement prevents the following failure mode: the architect prompt instructs the override, but due to parsing errors, context limits, or model behavior variance, the DROP verdict is mistakenly applied to an always-surface item and silently accepted. The validation should occur in the decision-packet assembly code (when building the final clarification packet to surface to the user) and should emit a warning log when an override is applied.\n","# Clarify Protocol\n\nThis protocol is loaded on demand by the architect stub in src\u002Fagents\u002Farchitect.ts. The architect prompt keeps only activation, action, and hard safety constraints; the full execution details live here.\n\n### MODE: CLARIFY\nAmbiguous request → Run the clarification funnel\nClear request → MODE: DISCOVER\n\n### Clarification Funnel\n\nBefore surfacing any clarification question to the user, the architect MUST run this four-stage funnel. The goal is to limit unnecessary user interruption, not planning completeness.\n\n#### Stage 1: Inventory All Material Uncertainties\n\nIdentify ALL uncertainties that could affect:\n- Scope boundaries\n- User-visible behavior\n- Destructive behavior or data loss\n- Security\u002Fprivacy posture\n- Backward compatibility\n- Migrations or rollout strategy\n- Cost\u002Fperformance tradeoffs\n- Operational complexity\n- QA gate selection or enforcement strictness\n- Architecture choice among materially different paths\n- Dependency or platform assumptions\n\nThere is NO hard cap on the internal inventory. Record every material uncertainty found.\n\n#### Stage 2: Classify Each Uncertainty\n\nClassify each item as exactly one of:\n- `self_resolved`: answered from the user request, spec, plan, codebase reality check, `.swarm\u002Fcontext.md`, repo conventions, or an informed default. **If the default is not directly supported by user request, spec, or recorded context, classify as `user_decision` rather than `self_resolved`.**\n- `critic_resolved`: sent to Critic Sounding Board and resolved by the critic.\n- `research_needed`: needs SME\u002Fexplorer\u002Fdomain lookup before user escalation. **Important:** If research is ongoing, monitor the timeout configured in `.swarm\u002Fconfig.json` under `research_needed_timeout_ms` (default: 300000ms \u002F 5 minutes). If research does not complete before the timeout expires, automatically reclassify the item to `user_decision` with a note that research was incomplete, then surface it to the user. This prevents the clarification funnel from stalling while waiting for external research.\n- `user_decision`: only the user can decide because it affects product scope, risk tolerance, policy, budget, UX, rollout, or destructive behavior.\n- `deferred_nonblocking`: useful follow-up detail that does not block a correct initial plan and can be explicitly recorded as an assumption or follow-up.\n\n#### Stage 3: Consult Critic Sounding Board\n\nBefore asking the user any clarification question, the architect MUST consult `critic_sounding_board` with the candidate question set and context.\n\nFor each item classified as `research_needed` or `user_decision` in Stage 2, send it to the critic. The critic responds with a verdict from `SoundingBoardVerdict` (see `src\u002Fagents\u002Fcritic.ts`). The mapping between critic verdicts and funnel actions is:\n\n| Critic Verdict (SoundingBoardVerdict) | Funnel Action | Meaning |\n|---|---|---|\n| `UNNECESSARY` | DROP | Item is unnecessary or answerable from existing context |\n| `RESOLVE` | RESOLVE | Critic supplies the answer or recommended default |\n| `REPHRASE` | REPHRASE | Question is valid but should be clearer, narrower, or grouped |\n| `APPROVED` | ASK_USER | User decision is genuinely required |\n\n**Hard constraint:** Items in the Always-Surface Categories list (below) MUST NOT receive `UNNECESSARY`\u002F`DROP` from the critic — only `REPHRASE` or `APPROVED`\u002F`ASK_USER` are allowed. If the critic attempts to `UNNECESSARY`\u002F`DROP` an always-surface item, override to `APPROVED`\u002F`ASK_USER`.\n\n**Overconfidence guard:** If the critic attempts to self-resolve an item by supplying an answer (verdict `RESOLVE`) but the underlying default is not directly supported by user request, spec, or recorded context, the architect MUST classify the item as `user_decision` rather than `self_resolved`. Unsupported defaults must not be silently accepted.\n\nUpdate classifications based on critic response:\n- `UNNECESSARY`\u002F`DROP` → reclassify as `self_resolved` and record the reason.\n- `RESOLVE` → reclassify as `critic_resolved` and record the answer as an assumption.\n- `REPHRASE` → update the question wording and keep as candidate.\n- `APPROVED`\u002F`ASK_USER` → confirm as `user_decision`.\n\nRecord all resolved items as explicit assumptions before proceeding.\n\n#### Stage 4: Surface User Decision Packet\n\nIf any items remain classified as `user_decision` after Stage 3, present them as a structured decision packet — NOT as an arbitrary subset.\n\nThe packet MUST include for each decision:\n- Category grouping (scope, security, compatibility, performance, UX, rollout, QA policy)\n- Why the decision matters\n- Recommended default when safe\n- Options being weighed\n- Impact of accepting the default\n- Blocking vs optional marker\n\nThe architect MAY ask questions one at a time in interactive mode, but MUST preserve and report the full unresolved list. The architect MUST NOT drop unresolved decisions because of a session question cap.\n\n### Always-Surface Categories\n\nThe critic may improve wording or confirm prior context, but these categories MUST be surfaced to the user unless already explicitly answered by the user or by recorded context:\n- Scope boundaries: what is in or out\n- Data loss or destructive behavior\n- Security\u002Fprivacy risk tolerance\n- Backward compatibility or migration policy\n- Breaking changes to existing APIs, contracts, or interfaces\n- New dependency additions or version changes\n- Deprecation decisions for existing features or APIs\n- Cross-platform impact (Windows\u002FmacOS\u002FLinux differences)\n- Cost\u002Fperformance tradeoffs\n- User-visible behavior and UX choices\n- Release\u002Frollout strategy\n- Optional QA gates or stricter enforcement modes\n- Any choice that changes whether the work is advisory vs hard-blocking\n\n### Assumptions Recording\n\nAll items resolved in Stages 2-3 (self_resolved, critic_resolved, deferred_nonblocking) MUST be recorded as explicit assumptions in the spec, plan, or `.swarm\u002Fcontext.md`. Silently dropping resolved uncertainties is a protocol violation — every uncertainty that entered the funnel must have a recorded outcome.\n\n### Mechanical Enforcement of DROP Protection\n\n**Implementation Note:** The hard constraint against `DROP` on always-surface items (defined in Stage 3 of the clarification funnel) is currently enforced via skill instructions to the architect. A lightweight runtime enforcement mechanism is recommended: when processing the critic sounding board verdict response in `src\u002Fagents\u002Fcritic.ts`, validate that any items tagged as \"always-surface\" do not receive `UNNECESSARY`\u002F`DROP` verdicts. If a DROP verdict is encountered on an always-surface item, override it to `APPROVED`\u002F`ASK_USER` at the code level rather than relying solely on prompt-based enforcement.\n\nThis mechanical enforcement prevents the following failure mode: the architect prompt instructs the override, but due to parsing errors, context limits, or model behavior variance, the DROP verdict is mistakenly applied to an always-surface item and silently accepted. The validation should occur in the decision-packet assembly code (when building the final clarification packet to surface to the user) and should emit a warning log when an override is applied.\n",{"name":5,"description":7},"main","7709dc9e5ebd3bd641124ad2a3f6bb053ac2dab6",".opencode\u002Fskills\u002Fclarify",0,"https:\u002F\u002Fgithub.com\u002FAlexanderNarbaev\u002Fagi","https:\u002F\u002Fgithub.com\u002FAlexanderNarbaev","2026-11-15 04:35:36",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add AlexanderNarbaev\u002Fagi --skill clarify",{"tool":36,"command":37},"bunx","bunx skills add AlexanderNarbaev\u002Fagi --skill clarify",{"tool":39,"command":40},"pnpm","pnpm dlx skills add AlexanderNarbaev\u002Fagi --skill clarify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAlexanderNarbaev\u002Fagi\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fclarify\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M76RZHYHMGE1WP9JBCMNA801","springboot-patterns","Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.","https:\u002F\u002Fgithub.com\u002FAlexanderNarbaev\u002Fagi\u002Fblob\u002Fmain\u002F.veai\u002Fskills\u002Fspringboot-patterns\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M76RZE6JNZH5HV7Q8JM7R0PN","search-first","Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.","https:\u002F\u002Fgithub.com\u002FAlexanderNarbaev\u002Fagi\u002Fblob\u002Fmain\u002F.veai\u002Fskills\u002Fsearch-first\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M76RZBV42EMQV77H7GMFY4AJ","scholar-evaluation","Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.","https:\u002F\u002Fgithub.com\u002FAlexanderNarbaev\u002Fagi\u002Fblob\u002Fmain\u002F.veai\u002Fskills\u002Fscholar-evaluation\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M76RZ97GC3XAY48H126C30PM","redis-patterns","Redis data structure patterns, caching strategies, distributed locks, rate limiting, pub\u002Fsub, and connection management for production applications.","https:\u002F\u002Fgithub.com\u002FAlexanderNarbaev\u002Fagi\u002Fblob\u002Fmain\u002F.veai\u002Fskills\u002Fredis-patterns\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M76RZ528FANTKX7Q9XR0CXM7","react-patterns","React 18\u002F19 patterns including hooks discipline, server\u002Fclient component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.","https:\u002F\u002Fgithub.com\u002FAlexanderNarbaev\u002Fagi\u002Fblob\u002Fmain\u002F.veai\u002Fskills\u002Freact-patterns\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M76RZ1244PZQRQV5HBQ4PVYQ","query-patterns","SQL patterns, relational database design, query optimization, transactions, analytics, and dialect-aware best practices.","https:\u002F\u002Fgithub.com\u002FAlexanderNarbaev\u002Fagi\u002Fblob\u002Fmain\u002F.veai\u002Fskills\u002Fquery-patterns\u002FSKILL.md",[],[]]