[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78CFSMY9R221PP9HCJ86GD1":3,"skill-same:01M78CFSMY9R221PP9HCJ86GD1":118},{"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},"01M78CFSMY9R221PP9HCJ86GD1","agent-core-dev",null,"Use when developing in packages\u002Fagent-core-v2 (the DI × Scope agent engine) — adding or modifying a domain Service, choosing a LifecycleScope, wiring DI dependencies, splitting a domain across scopes, owning or migrating a config section, gating behavior behind an experimental flag, raising coded errors, working on the permission system, writing DI\u002FScope tests, porting business logic from agent-core (v1) to v2, triaging a main-branch commit against v2, or exposing a v2 domain over server-v2 while keeping the \u002Fapi\u002Fv1 wire contract compatible with released clients. Self-contained guide organized by development stage (orient → design → implement → test → verify) plus align workflows for v1→v2 migration, main-branch commit triage, and server-v2 wire exposure; each file carries the rules, examples, and red lines for its step.","NitrogenT7\u002Fkimi-code-security","NitrogenT7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F289338396?v=4","01M78CFQ0EEM77XTKQSACG4MCE","01M78CFQ17MCHBS0YCKT2SCBYN",19,"MIT","https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agent-core-dev\ndescription: Use when developing in packages\u002Fagent-core-v2 (the DI × Scope agent engine) — adding or modifying a domain Service, choosing a LifecycleScope, wiring DI dependencies, splitting a domain across scopes, owning or migrating a config section, gating behavior behind an experimental flag, raising coded errors, working on the permission system, writing DI\u002FScope tests, porting business logic from agent-core (v1) to v2, triaging a main-branch commit against v2, or exposing a v2 domain over server-v2 while keeping the \u002Fapi\u002Fv1 wire contract compatible with released clients. Self-contained guide organized by development stage (orient → design → implement → test → verify) plus align workflows for v1→v2 migration, main-branch commit triage, and server-v2 wire exposure; each file carries the rules, examples, and red lines for its step.\n---\n\n# agent-core-dev\n\n> Develop `packages\u002Fagent-core-v2` by lifecycle stage. This skill is **self-contained**: every rule, recipe, and red line lives in the stage files below — it does not delegate to `packages\u002Fagent-core-v2\u002Fdocs\u002F`.\n\n`agent-core-v2` is the new agent engine built on the **DI × Scope** architecture (a port of `packages\u002Fagent-core`). Everything resolves through the container: a service declares an **identity**, its **dependencies**, and a **lifetime**; the container decides construction, singleton-per-scope, ordering, and disposal. The stage files restate the rules in imperative form so you can work without reading the source docs.\n\n## Lifecycle at a glance\n\n```text\nOrient → Design → Implement → Test → Verify\n  │        │          │          │        │\n  │        │          │          │        └─ lint:domain · typecheck · test · dep graph · red lines\n  │        │          │          └─ test.md\n  │        │          └─ implement.md (+ errors.md · flags.md · permission.md)\n  │        └─ design.md\n  └─ orient.md\n```\n\nStages are ordered but not strictly linear: a test failure (stage 4) that reveals a wrong scope sends you back to design (stage 2); a `CyclicDependencyError` sends you to `design.md` §dependency-direction and `implement.md` §cycles.\n\n## Workflows\n\nEnd-to-end procedures that span the stages. Reach for these before reading the stage files individually.\n\n- [Align (port `agent-core` → `agent-core-v2`)](align.md): split a v1 class into semantic units, fix each unit's domain \u002F scope \u002F Service \u002F dependencies, then migrate the logic and tests. Use when the task is \"move feature X from v1 to v2\" or \"port `IXxxService` to v2\".\n- [Commit align (triage a `main` commit against v2)](commit-align.md): given one `main` commit hash + a short note, find the v1 logic it changed, check whether v2 already has the corresponding implementation, bucket it (aligned \u002F partial \u002F missing \u002F not-applicable), and recommend a minimal fix. Use in the `kimi-code-v2`-catching-up-to-`main` phase, for one commit at a time; escalate to [align.md](align.md) if the gap is a whole domain.\n- [Server align (expose `agent-core-v2` over `server-v2`)](server-align.md): wire a v2 domain into `packages\u002Fkap-server` over `\u002Fapi\u002Fv2` (native) and `\u002Fapi\u002Fv1` (v1-compatible mirror), keep the wire schema byte-compatible with the established v1 contract by sharing the `@moonshot-ai\u002Fprotocol` schema, and isolate v1-only behavior in a `\u003Cdomain>Legacy` edge adapter instead of distorting the native v2 Service. Use when the task is \"expose the new v2 Service on the server\", \"add a route to the `\u002Fapi\u002Fv1` surface\", or \"keep server-v2 wire-compatible with released v1 clients\".\n\n## Stages\n\n- [Stage 1 — Orient](orient.md): the DI black box (identity \u002F dependencies \u002F lifetime), the four `LifecycleScope` tiers and visibility, and the file-header comment convention. Read before touching business code.\n- [Stage 2 — Design a service](design.md): pick a scope, split a domain across scopes, choose a calling style (direct call vs event vs hook), and direct dependencies. Decide *where things live and who knows whom* before coding.\n  - Topic: [Domain boundaries vs Scope](domain-boundaries.md) — keep `session` \u002F `agent` \u002F `turn` from becoming god objects; data-ownership test and their split conclusions.\n  - Topic: [Persistence layering](persistence.md) — the three-layer `Store → Storage → backend` model, naming Stores by access pattern, and which layer business code should depend on.\n  - Topic: [Edge exposure — `resource:action` + WS events](edge-exposure.md) — which Services are exposed over `\u002Fapi\u002Fv2` (per-scope action map) and which events stream over WS; what to wrap in a facade.\n- [Stage 3 — Implement](implement.md): the standard Service recipe and the DI building blocks — interface + identity, constructor injection, scoped registration, `Disposable`, eager vs delayed, `invokeFunction`, `createInstance`, child scopes, and the cycle-refactor playbook.\n  - Topic: [Service authoring](service-authoring.md) — file layout, naming, contract vs impl contents, interface style, constructor\u002Ffield conventions, events, multi-Service domains, comment rules.\n  - Topic: [Config](config.md) — the section-registry model, App vs Session split, owning a config section, the TOML format, and the env overlay.\n  - Topic: [Errors](errors.md) — co-located `XxxError`, the central code registry, wire serialization, boundary translation.\n  - Topic: [Flags](flags.md) — `registerFlagDefinition`, `IFlagService.enabled(id)`, the `[experimental]` config section, resolution precedence.\n  - Topic: [Permission](permission.md) — composable chain-of-responsibility kernel, policy registry + composer, `modes`\u002F`agentTypes` metadata, `resolveExecution`\u002F`accesses`.\n  - Topic: [Telemetry](telemetry.md) — emitting events via `ITelemetryService`, context propagation, and appender destinations (`ConsoleAppender` \u002F `CloudAppender`).\n- [Stage 4 — Test](test.md): resolve the system under test by interface, pick `TestInstantiationService` vs `createScopedTestHost`, shared stubs, service groups, teardown.\n- [Stage 5 — Verify & submit](verify.md): `lint:domain`, `typecheck`, `test`, and the pre-submit checklist.\n\n## How to use this skill\n\nJump to the stage you are in and read that one file; each is self-contained and ends with its own red lines. Skim the global red lines below before submitting — they catch most mistakes across every stage. The repo's source of truth remains the code in `packages\u002Fagent-core-v2\u002Fsrc\u002F`; this skill codifies the same rules so you do not have to re-derive them.\n\n## Global red lines\n\nInvariants that hold across every stage. Each is expanded in the stage file noted.\n\n1. No `new` on a class whose constructor carries `@IService` deps — inject with `@IX` or `accessor.get(IX)`. (implement.md)\n2. `@IX` decorates constructor parameters only; parameter order depends on construction (static-first for `createInstance`, `@IX`-first for scoped services). (service-authoring.md)\n3. Both interface and impl carry `_serviceBrand`; the `createDecorator` name is globally unique. (implement.md)\n4. Parent scope never depends on child scope — short-lived may inject long-lived, never the reverse. (orient.md)\n5. No cyclic dependencies — refactor (extract a third Service \u002F use an event \u002F re-scope); do not break the cycle with `Delayed`. (design.md, implement.md)\n6. `ServicesAccessor` is valid only during `invokeFunction` — never stash it for async use. (implement.md)\n7. Scope follows state identity — no `Map\u003CsessionId, …>` at `App` to fake per-session state. (design.md)\n8. Foundational layers never know upstream ones; business code never depends on the edge layer (`gateway`\u002F`rpc`). (design.md)\n9. Throw coded errors; register codes centrally; branch on `code` across the wire, never `instanceof`. (errors.md)\n10. Gate unreleased behavior behind a flag contributed via `registerFlagDefinition` and resolved through `IFlagService.enabled(id)`; no ad-hoc env toggles. (flags.md)\n11. Tests resolve the SUT by interface; shared stubs live under `test\u002F`, never `src\u002F`. (test.md)\n12. Config is the preference registry: only preferences that are persistable, schema'd, and user\u002Foperator-facing go in `IConfigService`. Domain-specific config (including env-only operational toggles) goes through `registerSection` + `envOverlay`. Facts → `IBootstrapService` (kept domain-agnostic — never add cron\u002Fflags\u002Fmodel state); session state → Session scope; constants → code. Business domains never call `IBootstrapService.getEnv()` directly. (config.md)\n","# agent-core-dev\n\n> Develop `packages\u002Fagent-core-v2` by lifecycle stage. This skill is **self-contained**: every rule, recipe, and red line lives in the stage files below — it does not delegate to `packages\u002Fagent-core-v2\u002Fdocs\u002F`.\n\n`agent-core-v2` is the new agent engine built on the **DI × Scope** architecture (a port of `packages\u002Fagent-core`). Everything resolves through the container: a service declares an **identity**, its **dependencies**, and a **lifetime**; the container decides construction, singleton-per-scope, ordering, and disposal. The stage files restate the rules in imperative form so you can work without reading the source docs.\n\n## Lifecycle at a glance\n\n```text\nOrient → Design → Implement → Test → Verify\n  │        │          │          │        │\n  │        │          │          │        └─ lint:domain · typecheck · test · dep graph · red lines\n  │        │          │          └─ test.md\n  │        │          └─ implement.md (+ errors.md · flags.md · permission.md)\n  │        └─ design.md\n  └─ orient.md\n```\n\nStages are ordered but not strictly linear: a test failure (stage 4) that reveals a wrong scope sends you back to design (stage 2); a `CyclicDependencyError` sends you to `design.md` §dependency-direction and `implement.md` §cycles.\n\n## Workflows\n\nEnd-to-end procedures that span the stages. Reach for these before reading the stage files individually.\n\n- [Align (port `agent-core` → `agent-core-v2`)](align.md): split a v1 class into semantic units, fix each unit's domain \u002F scope \u002F Service \u002F dependencies, then migrate the logic and tests. Use when the task is \"move feature X from v1 to v2\" or \"port `IXxxService` to v2\".\n- [Commit align (triage a `main` commit against v2)](commit-align.md): given one `main` commit hash + a short note, find the v1 logic it changed, check whether v2 already has the corresponding implementation, bucket it (aligned \u002F partial \u002F missing \u002F not-applicable), and recommend a minimal fix. Use in the `kimi-code-v2`-catching-up-to-`main` phase, for one commit at a time; escalate to [align.md](align.md) if the gap is a whole domain.\n- [Server align (expose `agent-core-v2` over `server-v2`)](server-align.md): wire a v2 domain into `packages\u002Fkap-server` over `\u002Fapi\u002Fv2` (native) and `\u002Fapi\u002Fv1` (v1-compatible mirror), keep the wire schema byte-compatible with the established v1 contract by sharing the `@moonshot-ai\u002Fprotocol` schema, and isolate v1-only behavior in a `\u003Cdomain>Legacy` edge adapter instead of distorting the native v2 Service. Use when the task is \"expose the new v2 Service on the server\", \"add a route to the `\u002Fapi\u002Fv1` surface\", or \"keep server-v2 wire-compatible with released v1 clients\".\n\n## Stages\n\n- [Stage 1 — Orient](orient.md): the DI black box (identity \u002F dependencies \u002F lifetime), the four `LifecycleScope` tiers and visibility, and the file-header comment convention. Read before touching business code.\n- [Stage 2 — Design a service](design.md): pick a scope, split a domain across scopes, choose a calling style (direct call vs event vs hook), and direct dependencies. Decide *where things live and who knows whom* before coding.\n  - Topic: [Domain boundaries vs Scope](domain-boundaries.md) — keep `session` \u002F `agent` \u002F `turn` from becoming god objects; data-ownership test and their split conclusions.\n  - Topic: [Persistence layering](persistence.md) — the three-layer `Store → Storage → backend` model, naming Stores by access pattern, and which layer business code should depend on.\n  - Topic: [Edge exposure — `resource:action` + WS events](edge-exposure.md) — which Services are exposed over `\u002Fapi\u002Fv2` (per-scope action map) and which events stream over WS; what to wrap in a facade.\n- [Stage 3 — Implement](implement.md): the standard Service recipe and the DI building blocks — interface + identity, constructor injection, scoped registration, `Disposable`, eager vs delayed, `invokeFunction`, `createInstance`, child scopes, and the cycle-refactor playbook.\n  - Topic: [Service authoring](service-authoring.md) — file layout, naming, contract vs impl contents, interface style, constructor\u002Ffield conventions, events, multi-Service domains, comment rules.\n  - Topic: [Config](config.md) — the section-registry model, App vs Session split, owning a config section, the TOML format, and the env overlay.\n  - Topic: [Errors](errors.md) — co-located `XxxError`, the central code registry, wire serialization, boundary translation.\n  - Topic: [Flags](flags.md) — `registerFlagDefinition`, `IFlagService.enabled(id)`, the `[experimental]` config section, resolution precedence.\n  - Topic: [Permission](permission.md) — composable chain-of-responsibility kernel, policy registry + composer, `modes`\u002F`agentTypes` metadata, `resolveExecution`\u002F`accesses`.\n  - Topic: [Telemetry](telemetry.md) — emitting events via `ITelemetryService`, context propagation, and appender destinations (`ConsoleAppender` \u002F `CloudAppender`).\n- [Stage 4 — Test](test.md): resolve the system under test by interface, pick `TestInstantiationService` vs `createScopedTestHost`, shared stubs, service groups, teardown.\n- [Stage 5 — Verify & submit](verify.md): `lint:domain`, `typecheck`, `test`, and the pre-submit checklist.\n\n## How to use this skill\n\nJump to the stage you are in and read that one file; each is self-contained and ends with its own red lines. Skim the global red lines below before submitting — they catch most mistakes across every stage. The repo's source of truth remains the code in `packages\u002Fagent-core-v2\u002Fsrc\u002F`; this skill codifies the same rules so you do not have to re-derive them.\n\n## Global red lines\n\nInvariants that hold across every stage. Each is expanded in the stage file noted.\n\n1. No `new` on a class whose constructor carries `@IService` deps — inject with `@IX` or `accessor.get(IX)`. (implement.md)\n2. `@IX` decorates constructor parameters only; parameter order depends on construction (static-first for `createInstance`, `@IX`-first for scoped services). (service-authoring.md)\n3. Both interface and impl carry `_serviceBrand`; the `createDecorator` name is globally unique. (implement.md)\n4. Parent scope never depends on child scope — short-lived may inject long-lived, never the reverse. (orient.md)\n5. No cyclic dependencies — refactor (extract a third Service \u002F use an event \u002F re-scope); do not break the cycle with `Delayed`. (design.md, implement.md)\n6. `ServicesAccessor` is valid only during `invokeFunction` — never stash it for async use. (implement.md)\n7. Scope follows state identity — no `Map\u003CsessionId, …>` at `App` to fake per-session state. (design.md)\n8. Foundational layers never know upstream ones; business code never depends on the edge layer (`gateway`\u002F`rpc`). (design.md)\n9. Throw coded errors; register codes centrally; branch on `code` across the wire, never `instanceof`. (errors.md)\n10. Gate unreleased behavior behind a flag contributed via `registerFlagDefinition` and resolved through `IFlagService.enabled(id)`; no ad-hoc env toggles. (flags.md)\n11. Tests resolve the SUT by interface; shared stubs live under `test\u002F`, never `src\u002F`. (test.md)\n12. Config is the preference registry: only preferences that are persistable, schema'd, and user\u002Foperator-facing go in `IConfigService`. Domain-specific config (including env-only operational toggles) goes through `registerSection` + `envOverlay`. Facts → `IBootstrapService` (kept domain-agnostic — never add cron\u002Fflags\u002Fmodel state); session state → Session scope; constants → code. Business domains never call `IBootstrapService.getEnv()` directly. (config.md)\n",{"name":5,"description":7},"main","cac122702fd7c1bb910d4331d42d31f4d65ef199",".agents\u002Fskills\u002Fagent-core-dev",1,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security","https:\u002F\u002Fgithub.com\u002FNitrogenT7","2026-09-23 16:08:07",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add NitrogenT7\u002Fkimi-code-security --skill agent-core-dev",{"tool":36,"command":37},"bunx","bunx skills add NitrogenT7\u002Fkimi-code-security --skill agent-core-dev",{"tool":39,"command":40},"pnpm","pnpm dlx skills add NitrogenT7\u002Fkimi-code-security --skill agent-core-dev","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002FSKILL.md",true,[44,50,54,58,62,66,70,74,78,82,86,90,94,98,102,106,110,114],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"align.md","REFERENCE","参考文档",15144,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Falign.md",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"close-vs-dispose.md",6171,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Fclose-vs-dispose.md",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"commit-align.md",6213,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Fcommit-align.md",{"path":59,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":60,"sourceHtmlUrl":61},"config.md",19042,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Fconfig.md",{"path":63,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":64,"sourceHtmlUrl":65},"design.md",17414,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Fdesign.md",{"path":67,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":68,"sourceHtmlUrl":69},"domain-boundaries.md",10702,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Fdomain-boundaries.md",{"path":71,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":72,"sourceHtmlUrl":73},"edge-exposure.md",10201,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Fedge-exposure.md",{"path":75,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":76,"sourceHtmlUrl":77},"errors.md",4703,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Ferrors.md",{"path":79,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":80,"sourceHtmlUrl":81},"flags.md",7130,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Fflags.md",{"path":83,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":84,"sourceHtmlUrl":85},"implement.md",13469,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Fimplement.md",{"path":87,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":88,"sourceHtmlUrl":89},"orient.md",5833,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Forient.md",{"path":91,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":92,"sourceHtmlUrl":93},"permission.md",12997,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Fpermission.md",{"path":95,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":96,"sourceHtmlUrl":97},"persistence.md",13034,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Fpersistence.md",{"path":99,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":100,"sourceHtmlUrl":101},"server-align.md",18795,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Fserver-align.md",{"path":103,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":104,"sourceHtmlUrl":105},"service-authoring.md",18708,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Fservice-authoring.md",{"path":107,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":108,"sourceHtmlUrl":109},"telemetry.md",6664,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Ftelemetry.md",{"path":111,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":112,"sourceHtmlUrl":113},"test.md",14232,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Ftest.md",{"path":115,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":116,"sourceHtmlUrl":117},"verify.md",2312,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagent-core-dev\u002Fverify.md",[119,126,133,140,146,153],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":18},"01M78CM022SAPQANCX0CYBBZD8","kimi-webbridge","Kimi WebBridge lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login sessions. Use this skill whenever the user wants to interact with websites, automate browser tasks, scrape web content, or perform any action requiring a real browser. Also use when the user mentions \"browser\", \"webpage\", \"open URL\", \"screenshot\", or asks to read\u002Finteract with any website. Use even for simple-sounding browser requests — the daemon handles all complexity.","https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002Fplugins\u002Fofficial\u002Fkimi-webbridge\u002Fskills\u002Fkimi-webbridge\u002FSKILL.md",[],[],{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":18},"01M78CKTEFA3QGTBQ3XYAKMCRK","kimi-datasource","Universal data-source assistant for stocks (Wind, S&P, SEC EDGAR), macro (World Bank, IMF, FRED, NBS), Chinese government data and standards (GB\u002FHB\u002FDB\u002FTT), corporate, academic, legal, WHO\u002FFAO\u002FOECD and other IGO data, financial news (Xinhua, Caixin).\nThis plugin exposes tools via MCP server `plugin-kimi-datasource_data`; call them in the flow `mcp__plugin-kimi-datasource_data__get_data_source_desc` → `mcp__plugin-kimi-datasource_data__call_data_source_tool`.","https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002Fplugins\u002Fofficial\u002Fkimi-datasource\u002FSKILL.md",[],[],{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":18},"01M78CKSF8Q6FGM97MJ7ZD095K","golden-skill","Golden fixture skill","https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002Fpackages\u002Fmigration-legacy\u002Ftest\u002Ffixtures\u002Fgolden\u002F.kimi\u002Fskills\u002Fgolden-skill\u002FSKILL.md",[],[],{"skillNo":141,"name":142,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":18},"01M78CKRHACG31TNA9266YY8YR","tools","https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002Fpackages\u002Fagent-core-v2\u002Fsrc\u002Ffeatures\u002Fskill\u002Ftools\u002Fskill.md",[],[],{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":18},"01M78CKNZ2549R5P70N4JMT1FT","review","Analyze the available skill set and recommend candidate groups that could be consolidated into sub-skill bundles. Read-only — proposes a plan, does not move files.","https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002Fpackages\u002Fagent-core-v2\u002Fsrc\u002Ffeatures\u002Fskill\u002Fcatalog\u002Fbuiltin\u002Fsub-skill\u002Freview\u002FSKILL.md",[],[],{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":18},"01M78CKKHZZHB0BEY72HXGTJE6","consolidate","Apply an approved sub-skill grouping by moving user-specified skills into a parent bundle, with timestamped backups of every modified directory.","https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002Fpackages\u002Fagent-core-v2\u002Fsrc\u002Ffeatures\u002Fskill\u002Fcatalog\u002Fbuiltin\u002Fsub-skill\u002Fconsolidate\u002FSKILL.md",[],[]]