287건 · 관련도순
Import any source into an Obsidian vault as well-linked atomic notes: social posts, Telegram HTML exports, ChatGPT JSON, voice-note transcripts, WhatsApp exports, Apple Notes, Notion dumps, pasted text, articles. Handles structure, frontmatter, provenance, dedup against existing notes and a closing RAG reindex. Triggers: "/obsidian-ingest", "import this into the vault", "file this".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Run an investor-outreach wave end to end: assemble the batch of targets, personalize pitches from real templates, send from the designated account, and log every touch in the CRM. Walks the exact checklist with rate limits and dedup against everyone already contacted. Triggers: "/notpeople-wave", "next outreach batch".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Watch a live lead funnel with a zero-token dispatcher and surface salient events as short advice: replied but no scheduling link, link sent with no booking in 24h, awaiting reply. Deduped so it never nags twice, and read-only. Triggers: "/cofounder-watch", "what does the cofounder see", "funnel signals".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Poll RSS, JSON APIs, and GitHub with watermark dedup.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Clean Desktop/DL: temp, MD5 dedupe, type-sort, undo.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Extrahiert aus einem Chatverlauf (aktuelle Session oder Transkript-Dateien) einen wiederverwendbaren Skill — oder verbessert einen sehr ähnlichen existierenden Skill, statt ein Duplikat zu erzeugen. Nutze diesen Skill bei „mach daraus einen Skill", „das sollten wir als Skill festhalten", „extrahiere Skills aus diesem/alten Chatverläufen", „diese Arbeitsweise wiederverwendbar machen", oder bei `/skill-extract`. Deckt auch Bulk-Läufe über viele alte Transkripte ab (mit Datenreduktion über Subagenten). Für wiederkehrende AUTOMATISIERUNGEN (Cron/Schedule/Loop) stattdessen den Schwester-Skill workflow-extract nutzen.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Ordnet freiwillig bereitgestellte Kontaktdaten datensparsam und erkennt mögliche Dubletten.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Dual-layer PR review tool (Raven's Verdict). Runs adversarial cynical review and edge case hunter in parallel, merges and deduplicates findings into professional engineering output. Use when user asks to 'review a PR' and provides a PR url or id.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Open-format data ingestion for NV oOS Pro toolkits — the reusable pattern behind the F&B data-ingestion track (Proposal 078). Covers structural (header) matching over filename mapping, the configurable table_map + header-matcher + name-guess resolution order and the slug-first regression, the multi-format loader (CSV/TSV/JSON/JSONL/XLSX/ODS/PDF/photo), the Observation + terminology-map layer (vitals/FHIR analogue) with raw preservation, dedupe/retention/out-of-band banding, complete-by-default/resumable (offset) imports, and the read-only ingest-review dashboard anatomy (edit_posts review vs manage_options write, dry-run-first). Use when adding or extending data ingestion to a toolkit, ingesting heterogeneous owner files, wiring XLSX/PDF/photo imports, building an ingest/review dashboard, or debugging partial/truncated imports.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Daily read-only triage of all open cvoya-com/spring-voyage issues: grouping/dedup/consolidation, milestone moves, attention/design/executable split, and prioritized parallel execution waves.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Operational guide for the NV oOS Model Foundry (Proposal 067) — the cluster fine-tuning flywheel. Phase 1 shipped: the Corpus Foundry (Pro addon, addons/pro/includes/model-foundry/) — consent-gated, deduplicated, PII-scrubbed corpus exporters (trajectory_v1, preference_v1, docs_v1) with deterministic holdout splits and R12 provenance manifests. Covers the governance contract, row schemas, output layout, filter seams, the registration pattern for foundry tool slices, how to add a new exporter, and the test/validation gates. Use when extending the Corpus Foundry, debugging corpus exports, wiring a new data source, or continuing Phases 2–6 (train-worker, registry/serving, eval gate, fleet sharing).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Audit server-side paid-media measurement including server-side tag management, platform conversion APIs, event taxonomy, browser/server deduplication, consent, hashing, data quality, observability, and privacy. Use for server-side tracking, sGTM, server-side tagging, CAPI, Events API, event_id, pixel debugging, first-party measurement, or conversion data loss.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Implements BLoC (v9.x) event-driven state management for Flutter with unidirectional data flow using the flutter_bloc package. Use when implementing Bloc/Cubit classes, mapping Events to States, consuming state with BlocBuilder/BlocListener/BlocConsumer, applying event transformers (restartable/droppable/sequential) for concurrency control, setting up BlocProvider/MultiBlocProvider DI, integrating Freezed for sealed union types and exhaustive pattern matching, or testing with blocTest. Ideal for enterprise apps requiring business logic separation, precise concurrency control (search debouncing, form deduplication), or event replay debugging.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Multi-source research synthesizer. Takes a question, runs 3-5 parallel web searches with varied phrasings, deduplicates, and returns a cited, concise answer. For Hebrew questions, searches in both Hebrew and English. Output is always under ~400 words.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Data Quality Specialist IA — Expert en qualité des données (profiling, cleaning, déduplication, validation de schéma, Great Expectations)
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Consolidate the five tdmcp surveyor reports into one prioritized FEATURE_BACKLOG.md — dedupe cross-surface overlaps, reconcile every candidate against the roadmap (NEW vs planned vs extension), rank by a selectable impact×effort weighting profile into P0/P1/P2 (high-confidence first), and emit per-surface tables + a recommended-next shortlist that hands straight to the build pipeline. Use when a td-synthesizer agent is consolidating surveys during the feature-discovery harness.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Run a security sweep over one repo: secrets, dependencies and the diff, a security review and a silent-failure hunt, one deduped and ranked findings report, issues filed for blocking findings only after GO, each one handed to pb-bug-fix. Use for "security sweep", "audit this repo", "check for leaked secrets and vulnerable deps".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
A skill for AI agents that want to produce better daily reports and discover more of what their users actually want. Scans source front pages, diffs them against yesterday, prescreens with a weighted profile, reviews with an LLM, deduplicates, publishes, and evolves the profile from user feedback. All decisions go to an append-only tape for audit and replay.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Manual testing + bug filing for Enterprise / SaaS products. Parses a Feishu test doc (scope + repo + bitable URL), observes staging via claude-in-chrome, captures DOM/console/network/screenshot evidence, then dual-tracks each finding — Feishu Bitable record (with attachments) + GitHub issue (<REPO>#<ISSUE_NUMBER> format — English-primary, Chinese collapsed, R2-hosted screenshots, matching type label). Enforces dedup across bitable + GitHub issues + PRs, and mandatory P0/P1/P2 priority prompt when unclear. Trigger whenever the user says "test and report", "test and report side-by-side", "start system testing", "experience staging", "collaborate on bug filing", "collect feedback", a shared Feishu testing doc, a bitable URL + finding, or any UX/bug needing both bitable + GitHub tracking. Do NOT use for writing product code, PR review, CI debugging, or general "how do I use this product" questions — those go to normal dev / PR-review / support flows.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Fan six specialist reviewers (general correctness, silent failures, type design, test gaps, comment accuracy, simplification) out over the current diff, a branch, or a PR in parallel, then merge their findings into one deduplicated, ranked report. Use for a thorough review before merging. Not for editing code or approving on someone's behalf.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Personal App-in-Skill voice-of-customer desk (Busabase App-in-Skill) aggregating user feedback from support email, Discord/Slack communities, X replies, app-store reviews, surveys, and interviews into clustered feature requests and a roadmap decision queue. Use when the user invokes $kelly-feedback or /kelly-feedback, or mentions user feedback, voice of customer, feature requests, roadmap decisions, feedback clustering, feedback triage, request dedupe, changelog replies, decline replies, or reviewing what users are asking for.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
How to author, edit, and adapt PostHog Signals scouts — the scheduled agents that scan a project and emit findings into the Signals inbox. Use when a user wants to customize a canonical scout for their own setup (narrow its scope, retune its thresholds, add disqualifiers), tweak a scout's schedule or dry-run posture, or write a brand-new scout from scratch for a specific use case (a custom event, a product surface no canonical scout covers). Covers the scout SKILL.md anatomy, the emit contract, the dedupe + scratchpad-memory conventions, the per-team skills-store path vs the canonical in-repo path, and the emit-and-inspect test loop (with dry-run as an optional safety net). Trigger on "write/edit/customize a signals scout", "new scout for X", "tune my scout schedule", "make a scout that watches <event>".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build training datasets for LLM specialization from production data, frontier model distillation, and synthetic bootstrapping. Use when formatting production logs into SFT data, distilling from frontier APIs, or preparing data for fine-tuning. Covers JSONL formatting, data quality validation, deduplication, and train/eval splitting.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.