[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M786MSXTG9PYQN3TB4FN04C5":3,"skill-same:01M786MSXTG9PYQN3TB4FN04C5":104},{"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":31,"commitSha":32,"skillDirectory":5,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":49},"01M786MSXTG9PYQN3TB4FN04C5","api-design",null,"MANDATORY skill for Google AIP API resource design and compliance. Covers resources, operations, fields, design patterns, compatibility, polish, and proto API structure. For Buf lint and proto schema style, use the protobuf-lang skill.","kalaverin\u002Fskills","kalaverin","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6841312?v=4","01M786EMXK5R6A138KWFAS33T1","Alex Kalaverin","01M786EMYBQEDP3548REZHRX2Q",1,"BSD-3-Clause","https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: api-design\ndescription: MANDATORY skill for Google AIP API resource design and compliance. Covers resources, operations, fields, design patterns, compatibility, polish, and proto API structure. For Buf lint and proto schema style, use the protobuf-lang skill.\nruntime: true\ntriggers:\n  request: \"openapi, swagger, graphql, grpc, rest, api design, fastapi, flask\"\nrequires:\n  - frontmatter-protocol\n  - read-for-comments\nversion: 0.1.0\n---\n\n# SKILL: Strict API Design & Compliance (Google AIP)\n\nYou are an expert API Architect. **This document is a binding rule set, not a recommendation.**\nEvery directive in this guide MUST be followed unless it explicitly uses **SHOULD** or **MAY**. The key words \"MUST\", \"MUST NOT\", \"REQUIRED\", \"SHALL\", \"SHALL NOT\", \"SHOULD\", \"SHOULD NOT\", \"RECOMMENDED\", \"NOT RECOMMENDED\", \"MAY\", and \"OPTIONAL\" in this document are to be interpreted as described in BCP 14 [RFC2119] [RFC8174] when they appear in all capitals or in bold markup.\n\n## 1. Compliance and Default Rules\n\n* **Default Rule:** Unless a section, paragraph, or sentence explicitly uses **SHOULD** or **MAY**, every statement is to be treated as **MUST**. You MUST NOT apply external style preferences or general API-design heuristics in place of the rules documented here.\n* **Deviation Justification:** If you deviate from any MUST directive, you MUST explicitly justify the deviation in your output.\n* **Skill Boundary:** This skill enforces Google AIP resource-design rules (resources, operations, fields, patterns, compatibility, polish, and proto API structure). For Buf lint and proto schema style, consult the `protobuf-lang` skill.\n* **RFC Verbs:** For precise semantics of requirement-level verbs, consult the `read-for-comments` skill.\n\n## 2. Reference Corpus and Lazy-Load Protocol (CRITICAL)\n\nThe `references\u002F` corpus is extremely large (7,300+ lines across 11 files). You **MUST NOT** read reference files in full, load them into context indiscriminately, or summarize the collection. Every reference file opens with YAML frontmatter — a `subject` line (file-level coarse router) plus an `index` of decision cards (each card is the selection gate for ONE body section) — and every routable body section is addressed by a `[ref: #\u003Canchor>]` marker. You MUST route through the frontmatter, never through full-body reads.\n\n### 2.1 The Two-Command Routing Funnel\n\nThe canonical two-command funnel (Command 1 — subject map; Command 2 — full frontmatter of shortlisted files) lives in `frontmatter-protocol` `[ref: #lazy-load-routing]`; run it exactly as specified there, **from the skill directory** (the directory containing this SKILL.md) so that the relative `references\u002F` path resolves. If the session working directory is fixed elsewhere, prefix every `references\u002F` path with the skill directory path.\n\n### 2.2 Semantic Routing Rules\n\nRouting is **semantic and context-aware**, never substring\u002Fkeyword matching:\n\n1. Shortlist candidate files from the subject map using `subject` plus the request **plus inferred session work** (the artifact you are about to produce, the questions the problem implies). Shortlist generously — when uncertain, expand the file list and re-run Command 2.\n2. Within shortlisted frontmatter, read **every** card and match `what`\u002F`use_when`\u002F`avoid_when` semantically (OR semantics within and across files). Mark each matching card's `anchor`.\n3. **Deduplicate** anchors: several cards MAY share one anchor (convergence); load the shared section once.\n4. Routing stays in the **main agent**: inferred session context cannot be serialized to a subagent without loss. Subagents receive already-selected material.\n5. Cross-references inside card fields point to better alternatives: `(sibling card)` = another card for the same anchor in the same file; `(\u003CNN>_\u003Cname> › \u003Ctopic>)` = a section in the named corpus file (e.g. `(07_design_patterns › soft delete)`).\n\n### 2.3 Bounded Section Extraction (MANDATORY)\n\nExtract sections per the canonical loader mechanics in `frontmatter-protocol` `[ref: #lazy-load-routing]` — bounded extraction from the target marker to the next marker, never a blind fixed window like `rg -A 100` (it truncates large sections and over-reads small ones). The exact command and the marker-listing recipe live there, not here.\n\n**Frontmatter extraction warning:** match delimiters as anchored whole lines (`^---\\s*$`; in awk: `^---[ \\t]*$`). Never split on the bare substring `---` — bodies legitimately contain `---` inside code, and a naive split truncates the frontmatter with false YAML errors.\n\n### 2.4 Frontmatter Schema Notes\n\n- Top-level keys: `subject`, `index`, `aips` (skill-extra, below). Cards carry exactly `{anchor, what, problem, use_when, avoid_when, expected}`.\n- `aips` — **api-design skill-extra field** (declared per the lazyload standard's skill-extra mechanism, `frontmatter-protocol\u002Freferences\u002Flazyload.md`): a sorted list of the AIP numbers covered by the file, mechanically cross-checked against body section headings. Use it for coarse filtering when the request cites an AIP number directly.\n- `avoid_when` and `expected` are empty only for pure lookup sections (Glossary, RFC verbs) that have no anti-pattern and no success state.\n- The normative frontmatter schema, card semantics, and conformance checklist live in `frontmatter-protocol\u002Freferences\u002Flazyload.md`; api-design presentation choices live in `prompts\u002FREFERENCE_STANDARD_ADDENDUM.md`.\n\n## 3. Master Execution Workflow\n\n1. **Analyze Design Task:** Identify the API component (resource, method, field, relationship, error model, etc.) you are creating or reviewing.\n2. **Route via the Funnel:** Run Command 1, shortlist generously, run Command 2, and select cards semantically (§2.2). Load `references\u002Frfc_verbs.md` (anchor `rfc-verbs`) first if any requirement-level verb is ambiguous.\n3. **Extract Rules:** For each selected anchor, run the bounded extraction (§2.3) and read only that section. Do not load full reference files into context.\n4. **Apply Rules:** Draft or review routes, resource names, request\u002Fresponse shapes, field semantics, and error behavior so that every element complies with the extracted AIP section.\n5. **Proto Review (if applicable):** If the change touches `.proto` files, invoke the `protobuf-lang` skill for Buf lint and proto schema style. Do not duplicate those rules here.\n6. **Verify:**\n   - Confirm every route, method, field, and resource mentioned in the design complies with the extracted AIP section.\n   - Confirm no contradictions exist between referenced sections.\n   - Confirm any `.proto` changes were reviewed with `protobuf-lang`.\n   - Confirm no unmodified files were changed.\n","# SKILL: Strict API Design & Compliance (Google AIP)\n\nYou are an expert API Architect. **This document is a binding rule set, not a recommendation.**\nEvery directive in this guide MUST be followed unless it explicitly uses **SHOULD** or **MAY**. The key words \"MUST\", \"MUST NOT\", \"REQUIRED\", \"SHALL\", \"SHALL NOT\", \"SHOULD\", \"SHOULD NOT\", \"RECOMMENDED\", \"NOT RECOMMENDED\", \"MAY\", and \"OPTIONAL\" in this document are to be interpreted as described in BCP 14 [RFC2119] [RFC8174] when they appear in all capitals or in bold markup.\n\n## 1. Compliance and Default Rules\n\n* **Default Rule:** Unless a section, paragraph, or sentence explicitly uses **SHOULD** or **MAY**, every statement is to be treated as **MUST**. You MUST NOT apply external style preferences or general API-design heuristics in place of the rules documented here.\n* **Deviation Justification:** If you deviate from any MUST directive, you MUST explicitly justify the deviation in your output.\n* **Skill Boundary:** This skill enforces Google AIP resource-design rules (resources, operations, fields, patterns, compatibility, polish, and proto API structure). For Buf lint and proto schema style, consult the `protobuf-lang` skill.\n* **RFC Verbs:** For precise semantics of requirement-level verbs, consult the `read-for-comments` skill.\n\n## 2. Reference Corpus and Lazy-Load Protocol (CRITICAL)\n\nThe `references\u002F` corpus is extremely large (7,300+ lines across 11 files). You **MUST NOT** read reference files in full, load them into context indiscriminately, or summarize the collection. Every reference file opens with YAML frontmatter — a `subject` line (file-level coarse router) plus an `index` of decision cards (each card is the selection gate for ONE body section) — and every routable body section is addressed by a `[ref: #\u003Canchor>]` marker. You MUST route through the frontmatter, never through full-body reads.\n\n### 2.1 The Two-Command Routing Funnel\n\nThe canonical two-command funnel (Command 1 — subject map; Command 2 — full frontmatter of shortlisted files) lives in `frontmatter-protocol` `[ref: #lazy-load-routing]`; run it exactly as specified there, **from the skill directory** (the directory containing this SKILL.md) so that the relative `references\u002F` path resolves. If the session working directory is fixed elsewhere, prefix every `references\u002F` path with the skill directory path.\n\n### 2.2 Semantic Routing Rules\n\nRouting is **semantic and context-aware**, never substring\u002Fkeyword matching:\n\n1. Shortlist candidate files from the subject map using `subject` plus the request **plus inferred session work** (the artifact you are about to produce, the questions the problem implies). Shortlist generously — when uncertain, expand the file list and re-run Command 2.\n2. Within shortlisted frontmatter, read **every** card and match `what`\u002F`use_when`\u002F`avoid_when` semantically (OR semantics within and across files). Mark each matching card's `anchor`.\n3. **Deduplicate** anchors: several cards MAY share one anchor (convergence); load the shared section once.\n4. Routing stays in the **main agent**: inferred session context cannot be serialized to a subagent without loss. Subagents receive already-selected material.\n5. Cross-references inside card fields point to better alternatives: `(sibling card)` = another card for the same anchor in the same file; `(\u003CNN>_\u003Cname> › \u003Ctopic>)` = a section in the named corpus file (e.g. `(07_design_patterns › soft delete)`).\n\n### 2.3 Bounded Section Extraction (MANDATORY)\n\nExtract sections per the canonical loader mechanics in `frontmatter-protocol` `[ref: #lazy-load-routing]` — bounded extraction from the target marker to the next marker, never a blind fixed window like `rg -A 100` (it truncates large sections and over-reads small ones). The exact command and the marker-listing recipe live there, not here.\n\n**Frontmatter extraction warning:** match delimiters as anchored whole lines (`^---\\s*$`; in awk: `^---[ \\t]*$`). Never split on the bare substring `---` — bodies legitimately contain `---` inside code, and a naive split truncates the frontmatter with false YAML errors.\n\n### 2.4 Frontmatter Schema Notes\n\n- Top-level keys: `subject`, `index`, `aips` (skill-extra, below). Cards carry exactly `{anchor, what, problem, use_when, avoid_when, expected}`.\n- `aips` — **api-design skill-extra field** (declared per the lazyload standard's skill-extra mechanism, `frontmatter-protocol\u002Freferences\u002Flazyload.md`): a sorted list of the AIP numbers covered by the file, mechanically cross-checked against body section headings. Use it for coarse filtering when the request cites an AIP number directly.\n- `avoid_when` and `expected` are empty only for pure lookup sections (Glossary, RFC verbs) that have no anti-pattern and no success state.\n- The normative frontmatter schema, card semantics, and conformance checklist live in `frontmatter-protocol\u002Freferences\u002Flazyload.md`; api-design presentation choices live in `prompts\u002FREFERENCE_STANDARD_ADDENDUM.md`.\n\n## 3. Master Execution Workflow\n\n1. **Analyze Design Task:** Identify the API component (resource, method, field, relationship, error model, etc.) you are creating or reviewing.\n2. **Route via the Funnel:** Run Command 1, shortlist generously, run Command 2, and select cards semantically (§2.2). Load `references\u002Frfc_verbs.md` (anchor `rfc-verbs`) first if any requirement-level verb is ambiguous.\n3. **Extract Rules:** For each selected anchor, run the bounded extraction (§2.3) and read only that section. Do not load full reference files into context.\n4. **Apply Rules:** Draft or review routes, resource names, request\u002Fresponse shapes, field semantics, and error behavior so that every element complies with the extracted AIP section.\n5. **Proto Review (if applicable):** If the change touches `.proto` files, invoke the `protobuf-lang` skill for Buf lint and proto schema style. Do not duplicate those rules here.\n6. **Verify:**\n   - Confirm every route, method, field, and resource mentioned in the design complies with the extracted AIP section.\n   - Confirm no contradictions exist between referenced sections.\n   - Confirm any `.proto` changes were reviewed with `protobuf-lang`.\n   - Confirm no unmodified files were changed.\n",{"name":5,"runtime":24,"version":25,"requires":26,"triggers":29,"description":7},true,"0.1.0",[27,28],"frontmatter-protocol","read-for-comments",{"request":30},"openapi, swagger, graphql, grpc, rest, api design, fastapi, flask","main","7da8c355f6e99dcb88d8bb9f6ff27b3cb35bae47",0,"https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkalaverin","2026-11-15 01:37:57",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":24},[39,42,45],{"tool":40,"command":41},"npx","npx skills add kalaverin\u002Fskills --skill api-design",{"tool":43,"command":44},"bunx","bunx skills add kalaverin\u002Fskills --skill api-design",{"tool":46,"command":47},"pnpm","pnpm dlx skills add kalaverin\u002Fskills --skill api-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002FSKILL.md",[50,56,60,64,68,72,76,80,84,88,92,96,100],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"prompts\u002FREFERENCE_STANDARD_ADDENDUM.md","REFERENCE","参考文档",5408,"https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002Fprompts\u002FREFERENCE_STANDARD_ADDENDUM.md",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"README.md",3603,"https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002FREADME.md",{"path":61,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002F01_foundation_and_process.md",37150,"https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002Freferences\u002F01_foundation_and_process.md",{"path":65,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002F02_design_review.md",16560,"https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002Freferences\u002F02_design_review.md",{"path":69,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002F03_api_concepts.md",9009,"https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002Freferences\u002F03_api_concepts.md",{"path":73,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002F04_resource_design.md",84791,"https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002Freferences\u002F04_resource_design.md",{"path":77,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002F05_operations.md",115550,"https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002Freferences\u002F05_operations.md",{"path":81,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002F06_fields.md",89375,"https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002Freferences\u002F06_fields.md",{"path":85,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002F07_design_patterns.md",132352,"https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002Freferences\u002F07_design_patterns.md",{"path":89,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002F08_compatibility_and_versioning.md",35971,"https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002Freferences\u002F08_compatibility_and_versioning.md",{"path":93,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002F09_polish.md",54190,"https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002Freferences\u002F09_polish.md",{"path":97,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002F10_protocol_buffers.md",21936,"https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002Freferences\u002F10_protocol_buffers.md",{"path":101,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Frfc_verbs.md",3608,"https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fapi-design\u002Freferences\u002Frfc_verbs.md",[105,112,119,126,132,139],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M786R9KK7RP1J8EB7X9TC9KR","todo-protocol","Mandatory protocol for using the SetTodoList tool. Governs when to create a todo list, how to update it without violating immutability rules, how to synchronize item status after every tool call, and the forbidden mutations. Always active.","https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Ftodo-protocol\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":19},"01M786QZTC43FBK3A251NTY62Y","subagents-protocol","Mandatory protocol for delegating work to built-in subagents (coder, explore, plan), also called our bots by users. Always active. Owns the context-hygiene delegation test (material vs answer, cost balance, warm-instance reuse), launch parameters (mandatory explicit `model`), the single-source model-selection table, answer budgets, degradation handling, the launch checklist, and the role library for delegated review\u002Faudit with intent routing (`references\u002Froles.md`).","https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fsubagents-protocol\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":19},"01M786QSXFDM550NCC4PQXN26X","serena-protocol","MANDATORY skill for Serena (MCP) memory, knowledge base, and symbolic code exploration operations. Use whenever the agent needs to: read or write Serena memories, mutate or persist memory, explore code via symbolic MCP tools, resolve contradictions in stored knowledge, or follow memory metadata, naming, and routing conventions.","https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fserena-protocol\u002FSKILL.md",[],[],{"skillNo":127,"name":28,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":19},"01M786QMXA58XD5DJZ2AZER5ZP","Mandatory local standards library and archive. Before fetching any standard from the internet, the agent MUST check the Serena `standard\u002F` archive and this skill's `references\u002F` seed; after ANY standard-body download, the agent MUST archive it per the event-bound Archival Rule. Governs standard lookup, fetch, archival, and the family and full-body rules.","https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fread-for-comments\u002FSKILL.md",[],[],{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":19},"01M786QD59A2R2JK1NJTK7MADP","python-lang","MANDATORY skill for Python code. Use when writing, editing, refactoring, or reviewing Python files, modules, packages, classes, functions, type annotations, imports, exceptions, comprehensions, decorators, or docstrings. Enforces Google Python Style Guide and a mandatory, unconditional Ruff format+check pipeline scoped strictly to the agent's own changes.","https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fpython-lang\u002FSKILL.md",[],[],{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":19},"01M786Q683RHDC93NWABY7XKQN","preflight-checklist","Mandatory session-initialization closer and Startup Gate audit. Always loaded. Runs EXACTLY ONCE at session start, after all skill loading completes: verifies Startup Gate completion with evidence (mirror sync, forced import, discovery, activation, memory priming, MCP declaration, think block), runs dynamic session checks derived from the active skill set (mode states, delegation readiness), and reports a compact evidence-backed verdict table to the user before the first task output. Any FAIL is fixed before proceeding.","https:\u002F\u002Fgithub.com\u002Fkalaverin\u002Fskills\u002Fblob\u002Fmain\u002Fpreflight-checklist\u002FSKILL.md",[],[]]