Vss Add Nest Module

What it does

When your agent uses it

• Asked to add a new service/module to pipeline-manager
• Extend the VSS orchestrator
• Add a new endpoint/queue/event to pipeline-manager
• Scaffold a NestJS module the repo way for the video-search-and-summarization sample app

Example prompts

• “s pipeline-manager using the repo”
• “Use the vss-add-nest-module skill to scaffold and wires a new NestJS service/module for the Video Search & Summarization sample app's…”
• “/vss-add-nest-module”

Requirements

• Node.js

Workflow steps

11 steps, taken from the step headings in SKILL.md.

1. 1Match the repo layout
2. 2Create model/DTO files first
3. 3Add TypeORM only if the feature persists data
4. 4Keep controllers thin and Swagger-tagged
5. 5Use DI through modules, not ad hoc construction
6. 6Add events using the central enums
7. 7Use the repo queue pattern for background work
8. 8Send UI updates through SocketEvent + EventsGateway
9. 9Read configuration through ConfigService
10. 10Register the module in root wiring
11. 11Validate

What it can do on your machine

Read from SKILL.md and the folder at commit cdf860c. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (TypeScript, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • npm
  • bash

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vss Add Nest Module loads about 2.5k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 102 tokens; SKILL.md has 666 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~102

When it runs · the whole SKILL.md, loaded when a task matches

~2.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~5.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from open-edge-platform/edge-ai-libraries at commit cdf860c, republished under its Apache-2.0 licence (© open-edge-platform). 666 words, ~2,458 tokens.

name

vss-add-nest-module

description

Scaffolds and wires a new NestJS service/module for the Video Search & Summarization sample app's pipeline-manager using the repo's real conventions. Use when asked to add a new service/module to pipeline-manager, extend the VSS orchestrator, add a new endpoint/queue/event to pipeline-manager, or scaffold a NestJS module the repo way for the video-search-and-summarization sample app.

# SKILL_DIR is THIS skill's own directory (shown to you when the skill loads);
# in-repo it is .github/skills/vss-add-nest-module. Works the same if the skill is installed standalone.
SKILL_DIR=".github/skills/vss-add-nest-module"
APP_ROOT="$(bash "$SKILL_DIR/scripts/vss-bootstrap.sh")"
cd "$APP_ROOT"

src/<feature>/
  <feature>.module.ts
  controllers/<feature>.controller.ts
  services/<feature>.service.ts
  services/<feature>-db.service.ts        # only when TypeORM-backed
  queues/<feature>-queue.service.ts       # only when tick/event queued
  models/<feature>.model.ts
  models/<feature>.entity.ts              # only when persisted

// summary/summary.module.ts
@Module({
  imports: [VideoUploadModule, StateManagerModule],
  controllers: [SummaryController],
  providers: [SummaryService],
})
export class SummaryModule {}

// search/search.module.ts
@Module({
  providers: [SearchStateService, SearchDbService, SearchShimService],
  controllers: [SearchController],
  imports: [HttpModule, TypeOrmModule.forFeature([SearchEntity]), VideoUploadModule],
  exports: [],
})
export class SearchModule {}

export class SearchQueryDTO {
  @ApiProperty({ description: 'Search query string', example: 'person walking' })
  query: string;

  @ApiPropertyOptional({ description: 'Comma-separated tags to filter by' })
  tags?: string;
}

@Entity('search')
export class SearchEntity {
  @PrimaryGeneratedColumn()
  dbId?: number;

  @Column({ unique: true })
  queryId: string;

  @Column('jsonb', { nullable: true })
  results: SearchResult[];
}

@Injectable()
export class SearchDbService {
  constructor(
    @InjectRepository(SearchEntity)
    private searchRepo: Repository<SearchEntity>,
  ) {}

  async read(queryId: string): Promise<SearchEntity | null> {
    const search = await this.searchRepo.findOne({ where: { queryId } });
    return search ?? null;
  }
}

@ApiTags('Search')
@Controller('search')
export class SearchController {
  constructor(private $search: SearchStateService) {}

  @Post('')
  @ApiOperation({ summary: 'Add a new search query' })
  @ApiBody({ type: SearchQueryDTO })
  async addQuery(@Body() reqBody: SearchQueryDTO) {
    return await this.$search.newQuery(reqBody.query);
  }
}

EventEmitterModule.forRoot({ delimiter: '.', maxListeners: 5 })

this.$emitter.emit(SearchEvents.RUN_QUERY, res.queryId);

@OnEvent(SearchEvents.RUN_QUERY)
async reRunQuery(queryId: string) { ... }

@Injectable()
export class SummaryQueueService {
  waiting: SummaryQueueItem[] = [];
  processing: SummaryQueueItem[] = [];

  @OnEvent(PipelineEvents.SUMMARY_TRIGGER)
  streamTrigger({ stateId }: PipelineDTOBase) {
    this.waiting.push({ stateId, taskType: 'videoSummary' });
  }

  @OnEvent(AppEvents.FAST_TICK)
  processQueue() {
    if (this.waiting.length > 0 && this.$inferenceCount.hasLlmSlots()) {
      const queueItem = this.waiting.shift()!;
      this.processing.push(queueItem);
      this.startVideoSummary(queueItem);
    }
  }
}

@OnEvent(SocketEvent.SEARCH_UPDATE)
searchUpdate(payload: SearchQuery) {
  this.server.emit('search:update', payload);
}

constructor(private $config: ConfigService) {}

const endPoint: string = this.$config.get('search.endpoint')!;
const maxConcurrent = this.$config.get<number>('openai.vlmCaptioning.concurrent')!;

import { NewFeatureModule } from './new-feature/new-feature.module';
import { NewFeatureEntity } from './new-feature/models/new-feature.entity';

@Module({
  imports: [
    // existing imports...
    TypeOrmModule.forRoot({
      // existing options...
      entities: [StateEntity, VideoEntity, SearchEntity, TagEntity, NewFeatureEntity],
    }),
    NewFeatureModule,
  ],
})
export class AppModule {}

npm run build
npm test -- --runInBand
npm run lint

© open-edge-platform, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 22 other files (scripts, references, assets) in sample-applications/video-search-and-summarization/.github/skills/vss-add-nest-module of open-edge-platform/edge-ai-libraries.

• SKILL.md
• BENCHMARK.md
• assets/module-template/controllers/example.controller.ts
• assets/module-template/example.module.ts
• assets/module-template/models/example.entity.ts
• assets/module-template/models/example.model.ts
• assets/module-template/queues/example-queue.service.ts
• assets/module-template/services/example-db.service.ts
• assets/module-template/services/example.service.ts
• evals/evals.json
• evals/trigger-evals.json
• example-prompts/01-scaffold-basic-module.md
• example-prompts/02-add-endpoint-existing-style.md
• … and 10 more

Open the folder on GitHubat commit cdf860c