Menu
Skills neste repositório
O SkillsMP coletou 355 skills de grahama1970/agent-stack-public. Abra uma skill para revisar a origem e os detalhes.
grahama1970/agent-stack-publicMostrando 40 de 355 skills coletadas.
Live evidence case pipeline viewer with NVIS sentence markup and agent chat well. Shows gates firing, entity grounding, QRA evidence, and verdicts in real-time. Chat well connects to /subagent-service for human-agent course correction.
Idioma do texto original: inglês
NIST OSCAL JSON export of compliance evidence from ArangoDB graph
Idioma do texto original: inglês
Extract framework control references from documents and create graph edges to sparta_controls. Supports NIST, CWE, ATT&CK, SPARTA, D3FEND, ISO. 3-tier extraction: regex → RapidFuzz → classifier (future).
Idioma do texto original: inglês
Extract control IDs, domain phrases, taxonomy tags, and relationship data from question text. Composes /memory (ArangoDB recall to load sparta_controls vocabulary). Returns structured EntityExtractionResult that defines the shape of evidence cases,…
Idioma do texto original: inglês
Extract structured JSON from HTML using Schematron3B, deterministic table extraction, and Vision-based media OCR.
Idioma do texto original: inglês
Self-improving PDF extraction engine. Rust-native via pdf_oxide. Replaces PyMuPDF (AGPL) with MIT-licensed extraction: text, blocks, sections, tables, figures, profiling, engineering detection. Shadow-LEGO cascade for automatic quality improvement via…
Idioma do texto original: inglês
Composable PDF table extraction skill. Hybrid Rust+compiled-Python architecture replacing Camelot. Rust hotspots (image processing, geometry) via PyO3, compiled Python parsers (lattice, stream, network, hybrid), pdf_oxide for text extraction, polars for…
Idioma do texto original: inglês
Persona-driven datalake quality assessment with Margaret Chen (Pratt & Whitney) and Jennifer Cheung (NIWC Pacific). Dynamic annealing thresholds, batch review, and /ask consult integration.
Idioma do texto original: inglês
Extract one local document through the canonical Extractor application command. Use when the user says "extract this", "extract pdf", "convert to markdown", "parse this file", "process document", or provides a document.
Idioma do texto original: inglês
Stage cleaned chapter text and extract quote-grounded minimal fact/QRA candidates from source text or primary/context chunks, with streaming model calls, retries, validation, and durable artifacts.
Idioma do texto original: inglês
Fetch web pages, PDFs, and documents with automatic fallbacks and content extraction. Use when user says "fetch this URL", "download this page", "crawl this website", "extract content from", "get the PDF", or provides URLs needing retrieval.
Idioma do texto original: inglês
Iterative visualization development lab for /create-figure. Compose novel D3 visualizations from primitives (marks, scales, encodings), test rendering, evaluate against user intent, and promote successful compositions to /create-figure as first-class…
Idioma do texto original: inglês
Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values, it does not implement it. Use when the user asks "what could be animated here?" or wants to "make this…
Idioma do texto original: inglês
Generate adversarial PDF content that breaks extractors. Creates false-positive tables, malformed tables, cursed text, and layout traps. Extensible registry for adding new edge cases discovered from real-world PDFs.
Idioma do texto original: inglês
Convert natural language requests into verifiable formal specs using interview loops.
Idioma do texto original: inglês
Ensure movie subtitles exist and are verified on disk. Use when the user says get subtitles, download subtitles, verify English SRT, ask Bazarr for subtitles, ensure movie subtitles, or find subtitle-backed movie candidates.
Idioma do texto original: inglês
Deep GitHub repository and code search. For implementation research, uses the sibling brave-search skill to discover candidates, ranks them by requested criteria, stars, and relevance, clones the leaders to /tmp, verifies a detected entry point, then locates…
Idioma do texto original: inglês
Read-only goal-drift auditor. Holds each project's immutable goal as a typed record derived only from real human prompts, inspects what the project actually produced (tickets first, then artifacts, commits, and absences), and labels every action SERVES_GOAL,…
Idioma do texto original: inglês
Turn vague, drifting, long-running, overnight, or repeatedly failing work into a proof-driven Codex goal with one primary proof command or artifact, explicit completion criteria, a bounded retry limit, operational status snapshots, and fail-closed stop…
Idioma do texto original: inglês
Enforce a deterministic pre-plan self-improvement loop before /plan. Use when a task needs proof that the agent read the relevant files, resolved confusion through /interview or /dogpile, and can show a transparent understanding report before creating an…
Idioma do texto original: inglês
Benchmark and compare small GPTs for task-specific inference. Tests base, fine-tuned, and prompted models against shared eval datasets. Finds minimum viable model, compares fine-tuned vs prompted, and generates reports.
Idioma do texto original: inglês
Ground architecture recommendations in source evidence before advising. Use when a user asks for architecture recommendations, refactor options, system design critique, migration plans, cross-module tradeoffs, asks whether enough files have been read to…
Idioma do texto original: inglês
Handoff skill to assess project state and provide context for a new agent. Uses /assess logic to identify doc-code gaps, broken features, and next steps.
Idioma do texto original: inglês
Persona humming pipeline. Downloads songs, separates vocals, converts to persona voice via RVC, and caches for playback during idle conversation. Orchestrates: /ingest-youtube, /create-stems, /learn-artist, /create-music.
Idioma do texto original: inglês
Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not…
Idioma do texto original: inglês
Process audiobooks from the inbox: transcribe to text and organize audio for voice training. Part of Horus's learning pipeline.
Idioma do texto original: inglês
Manage book library via Readarr, search for books, and monitor downloads. Handles service health checks and API interactions. Part of Horus's learning pipeline.
Idioma do texto original: inglês
Ingest codebases into /memory for knowledge extraction and CWE scanning. Phase 1 extracts functional knowledge (module docstrings, function signatures, class hierarchies, markdown docs) via Python AST. Phase 2 scans for CWE mappings via /taxonomy. Designed to…
Idioma do texto original: inglês
Single-command compliance document ingestion pipeline. Chains extractor → cui-marker → doc2qra → taxonomy → memory for defense/compliance PDFs. Handles NIST, CMMC, DISA STIG, and ITAR documents end-to-end.
Idioma do texto original: inglês
Single-command document ingestion pipeline. Chains extractor → cui-marker → doc2qra → taxonomy → memory for PDFs and documents. Handles compliance, research, and general documents end-to-end.
Idioma do texto original: inglês
Ingest Kindle books and highlights into the library pipeline. Parses My Clippings.txt, converts .epub/.mobi/.azw3 to text, and outputs to ~/clawd/library/books/ for downstream QRA extraction.
Idioma do texto original: inglês
Locate NZBGeek releases with subtitle-rich movie files, auto-tag rage/anger/humor cues, and emit PersonaPlex-ready JSON for Horus Theory-of-Mind benchmarks.
Idioma do texto original: inglês
Thin wrapper around the SPARTA pipeline project (79K LOC Python). Runs pipeline steps, checks status, runs tests, launches Explorer UX. The real code lives at ~/workspace/experiments/sparta/src/sparta/pipeline/ — this skill is an interface, not a…
Idioma do texto original: inglês
Training-only datalake corpus acquisition and coverage balancer. Assesses sector/file-type coverage, plans gap-filling URL manifests, and runs fetcher downloads into approved training corpus roots.
Idioma do texto original: inglês
Ingest an entire website into /memory as a RAG resource. Chains /fetcher (crawl + render JS pages) → /extractor (structured extraction) → /doc2qra (extract QRAs) → /taxonomy (bridge tags) → /memory (store). Supports image download and local file output.
Idioma do texto original: inglês
Extract transcripts from YouTube videos. Use when user says "get transcript", "transcribe this video", "what does this YouTube video say", "extract captions", "youtube transcript", or provides a YouTube URL and wants the text content.
Idioma do texto original: inglês
Ingest YouTube and YouTube Music watch history from Google Takeout exports. Builds music taste profile for Horus persona with /memory integration.
Idioma do texto original: inglês
Intent classification and mapping for natural language commands. Uses unsloth/transformers for ML-based intent detection with ArangoDB storage.
Idioma do texto original: inglês
Structured human-agent Q&A via HTML or TUI forms. Wizard-style interface with tabbed navigation, numbered options with descriptions, automatic "Other" option, and image support. Mirrors Claude Code's AskUserQuestion UX.
Idioma do texto original: inglês
Retrieval-augmented Lean4 proof generation with self-improving lab. Queries 94k+ exemplars from DeepSeek-Prover V1+V2, uses hybrid search (BM25 + semantic + graph), generates via Claude, compiles via lean-interact (20 parallel silos), retries on failure. Lab…
Idioma do texto original: inglês