Loading...
Loading...
Found 2,753 Skills
Diseño de prompts para LLMs: system prompts, few-shot examples, chain-of-thought, RAG, structured outputs.
Use when you need legal PDF to markdown extraction plus clause chunking and embedding prep; pair with addon-rag-ingestion-pipeline and architect-python-uv-batch.
Unified YouTube script creation for cardiology channels in Hinglish. Uses the COMPLETE research-engine pipeline (channel scraping, comment analysis, narrative monitoring, gap finding, view prediction) combined with RAG + PubMed for evidence. Data-driven topic selection, 15-30 min educational videos with 6-point voice check.
Patterns for ingesting knowledge into vector databases and RAG systems
This skill should be used when the user asks to "deploy", "upload", "publish", or "pin" any files, folders, frontend projects, or static websites to IPFS. Also activates when user mentions "pinme", "IPFS", or wants to share files via decentralized storage.
Triggers on cluttered folders, file chaos, storage cleanup, or directory restructuring needs. TRIGGER WHEN: organizing messy folders (Downloads, Desktop, Documents), finding duplicate files, cleaning up old files, restructuring project directories, separating work from personal files, or automating file cleanup tasks DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.
Apply Bayesian averaging to rank items by combining observed ratings with prior expectations. Use this skill when the user needs to rank items with varying review counts, build a 'top rated' list that handles low-sample items fairly, or implement IMDB-style weighted rating — even if they say 'weighted average rating', 'IMDB formula', or 'ranking with prior'.
Retrieve time-windowed RSS evidence from SQLite and let the agent produce final summaries using RAG over selected records and fields. Use when generating daily, weekly, monthly, or custom-range AI tech digests directly in agent responses instead of fixed template reports.
Audits code for test quality and coverage issues — missing tests, test smells, poor test structure, mock abuse, coverage gaps, and fragile test data. Identifies weaknesses in the test suite and generates fix prompts. Trigger phrases: "test quality", "test audit", "test review", "coverage check", "missing tests", "test quality audit".
Cloudflare Vectorize vector database for semantic search and RAG. Use for vector indexes, embeddings, similarity search, or encountering dimension mismatches, filter errors.
Use when adding or updating Go CLI E2E coverage for one `tests/cli_e2e/{domain}` domain of the compiled `lark-cli`, especially when the work requires live `--help` or `schema` exploration, scenario-based `clie2e.RunCmd` workflows, and per-domain `coverage.md` maintenance.
Stage 1 spec compliance review. Triggers: /review stage 1. Verifies implementation matches design specification — functional completeness, TDD compliance, and test coverage. Do NOT use for code quality checks — use quality-review instead. Do NOT use for debugging.