Loading...
Loading...
Found 24 Skills
Query the ExoPriors Scry API -- SQL-over-HTTPS search across 229M+ entities spanning forums, papers, social media, government records, and prediction markets. Includes cross-platform author identity resolution (actors, people, aliases), OpenAlex academic graph navigation (authors, citations, institutions, concepts), shareable artifacts, and structured agent judgements. Use when the task involves: Scry API, ExoPriors, /v1/scry/query, scry.search, scry.entities, materialized views, corpus search, epistemic infrastructure, 229M entities, lexical search, BM25, structured agent judgements, scry shares, cross-corpus analysis, who is this person, cross-platform identity, OpenAlex, citation graph, coauthor graph, academic papers, author lookup. NOT for: semantic/vector search composition or embedding algebra (use scry-vectors), LLM-based reranking (use scry-rerank), or the user's own local Postgres / non-ExoPriors data sources.
Search named IDA entities by pattern. Use when asked to find functions, labels, types, or members by name, or to seed xref/decompiler workflows from a name lookup.
Drizzle TypeScript ORM with SQL-like syntax. Use for database access.
Audit every endpoint in a PostHog project for staleness, failed materialisations, and unused materialised versions. Use when the user asks "what endpoints can I clean up?", "are any of my endpoints broken?", "which materialised versions are still being called?", or wants a one-shot cleanup pass over the Endpoints product. Produces a prioritised report grouped by issue type, with recommended actions but does not modify anything without explicit confirmation.
Query Windows 11 version 24H2 cumulative update file information. Search for DLLs, drivers, and system files across all patch levels. Compare file versions between builds, track version history, and identify what changed in each update. Use when: (1) investigating which Windows build introduced a file version, (2) comparing file changes between patches, (3) finding DLL/driver versions for specific builds, (4) debugging Windows update regressions, (5) user asks about Windows 11 24H2 files, KB updates, or build versions.
Provides MaxCompute SQL intelligent generation capabilities for AI agents, covering text2sql conversion principles, dialect syntax differences (DQL/DDL/DML), common query pattern templates (Top N, PIVOT, window functions, etc.), and ODPS error code diagnostics. Use when generating, debugging, or migrating MaxCompute / ODPS SQL.
Use when the user wants to store, retrieve, search, or manage files in agent-fs — an agent-first filesystem backed by S3. Triggers on: "save this to agent-fs", "find that file", "store this document", "search agent-fs", "list my files", "show version history", "revert file", "set up agent-fs", "get a signed url", "share this file", "manage members", "invite user", "list members", "remove member", "update role", file persistence for agents, shared agent filesystem, or any mention of the agent-fs CLI. Also use when the user needs to manage drives, manage org/drive members, generate presigned URLs, check recent activity, or use semantic search across stored files. Also use when the user wants to run SQL over stored data files ("query this csv", "sql over my files", "duckdb", "aggregate the parquet file", "query the sqlite db", "join these spreadsheets"). Also use when the user wants to mount or unmount agent-fs as a Linux FUSE filesystem ("mount agent-fs", "fuse mount", "fuse", "remote mount", "sandbox mount", "expose drives as files", "use cat/grep/mv on my agent-fs files", "umount the drive", "mount a remote drive", "mount from sprite", "mount from e2b", "mount from hetzner"). Also use when the user wants to use agent-fs as a just-bash filesystem. Also use when the user wants to set up agent-fs without Docker or S3 ("local filesystem backend", "filesystem storage", "no docker", "onboard --filesystem", "store files on disk"). If the user mentions agent-fs in any context, always consult this skill.
Configure Spice.ai in-memory caching for SQL query results, search results, and embeddings. Use when setting up caching, tuning cache TTL/size/eviction, configuring stale-while-revalidate, custom cache keys, or cache-control headers.
Decompile and analyze IDA functions. Use when asked for pseudocode, ctree AST analysis, local variables, labels, or decompiler-driven cleanup.
Query the german_shopping_receipts BigQuery table with bq. Use when the user asks about groceries, supermarket spend, item prices, or that table.
DingTalk AI Table (multidimensional table) business operations and CLI contract review. This Skill must also be loaded when only reviewing aitable synthetic JSON receipts; "Don't execute online business" does not exempt local offline contract verification; you cannot answer directly based on general JSON experience. Review is based on the verification entry point specified in the user's original text; background write commands are not additional targets; Agent-proposed Skill parameters must not expand the scope. When the user provides an aitable command, a form share synthetic receipt, a dry-run, or asks about a write recovery plan, this Skill must also be loaded; this is local Help/Schema contract verification, not repository source code review; do not start from source code search. First load the body to determine the entry point and rules; do not execute based solely on the summary. Applies to Base/Table, fields and records, comments, filtering/sorting, formulas, SQL/PostgreSQL/JOIN, form sharing and CP sync, App pages/Widget, templates, import/export, dashboards/charts, attachments, and approval data source sync. Does not handle spreadsheet cell operations (use dingtalk-misc) or text document editing (use dingtalk-doc).
Room/SQLite, DataStore and repository traps: migrations, NOT IN with NULLs, LIKE escaping, delete order, local-time bucketing, imports, caching, paging. Use before writing a query or migration, or when data comes back wrong.