Search: "turns"

Local document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; running OCR on scans; producing layout-preserved JSON for RAG; batch-ingesting folders of papers; or rendering pages to PNG for multimodal agents. Distinguishing capabilities are spatial text boxes, Markdown, page raster output, and local parsing with optional custom HTTP OCR.

Hunts for the other instances of a bug already found — the variants of one root cause across a codebase. Use immediately after a vulnerability, logic bug, or bad pattern turns up in a specific file and the question becomes where else it occurs, including the bare conversational form ("are there others like this?", "is this the same bug?"). Also for generalizing one known instance into a CodeQL or Semgrep query for its whole pattern family, and for triaging a set of look-alike candidates against a known root cause. Not for initial discovery with no bug in hand.

Runs a Trailmark summary analysis on a codebase. Returns auto-detected languages, entry point count, and dependency list. Use when vivisect or galvanize needs a quick structural overview. Triggers: trailmark summary, code summary, structural overview.

Searches 18 scholarly APIs for papers, preprints, citations, open-access full text, repository records, and journal OA status, and returns results with reproducible provenance. Covers PubMed, PMC, Europe PMC, bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall, OpenCitations, PubTator3, Zenodo, Figshare, ROR, BioStudies, and DOAJ. Use when searching for papers, citations, DOI/PMID/arXiv lookups, abstracts, full text, open-access PDFs, preprints, citation graphs, author publications, biomedical entity annotations, deposited records (Zenodo, Figshare, BioStudies), institution ROR IDs, or any scholarly literature query. Triggers on mentions of any supported database or requests like "find papers on X", "look up this DOI", "who cites this paper", or "get me the PDF".

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.

Packmind seamlessly captures your engineering playbook and turns it into AI context, guardrails, and governance.

Use this skill when an agency operator wants the partner roster for a brand split by relationship status, plus the active partners who have gone quiet so they can be chased or reactivated. The output is a read-only worklist; the outreach itself happens outside this skill. How a partner's relationship status is read depends on the network. Some advertiser networks report it through the API. Awin does not: its advertiser API returns only already-joined publishers with no relationship-status field, so every Awin row maps to unknown and neither the roster split nor the dormant worklist can be derived from the API. Awin's roster and per-partner relationship status are read from the operator's own authenticated Awin session (new UI, app.awin.com) through Claude-in-Chrome, read-only. Awin Classic (ui.awin.com) accounts have no equivalent and are detected and stopped. Trigger on: "Who's gone quiet on Acme?", "Acme's partner roster health", "Which partners have gone dormant on [brand]?", "Build a reactivation list for Acme", "Show me Acme's roster by status".

Use this skill when an agency operator wants the list of partner applications waiting on a decision for a brand: who has applied to the programme and is sitting in the pending queue. The output is a read-only queue; the approve or decline happens in the network dashboard. How the queue is read depends on the network. Some advertiser networks expose application status through the API. Awin does not: its advertiser API returns only joined publishers with no application status, so Awin's pending queue is read from the operator's own authenticated Awin session (new UI, app.awin.com) through Claude-in-Chrome, read-only. Awin Classic (ui.awin.com) accounts have no equivalent and are detected and stopped. Trigger on: "Which partner applications are pending on Acme?", "Acme's application queue", "Who's waiting for approval on [brand]?", "Show me pending partners for Acme".

Your AI agents, finally with a memory that compounds. AI Memex turns chats, documents, research, and project decisions into a living Markdown knowledge base, maintained by agents and versioned in Git.

The Intelligence Layer: A Mind for Your Machine. An open-source agentic system that turns your machine from an inanimate silo into something conversational, proactive, autonomous. Model-independent by design— it dynamically loads every model tied to your API keys, runs entirely offline via your preferred model library, or takes a hybrid approach.

Keel turns coding agents into work owners: a project-neutral issue-to-done workflow backbone.