一个技能，一个新的可能。找到适合你的 AI 工作流。
human-in-the-loop
【设计与创意】Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from …
lead-enrichment
【数据与研究】Turns a raw or partial prospect list into a send-safe dataset by filling missing fields (work email, direct or mobile phone, title, firmographics, technographics) through a per-field provider waterfall, verifying every email, and stamping freshness. Use when someone says "enrich this list", "find the email for these people", "verify these emails befo…
evopdf-next-pdf-edit
【文档与办公】Open and modify an existing PDF in .NET with EvoPdf Next PdfEditor: add text, images, shapes and HTML templates to loaded pages, append blank pages, flatten, and save. Use for stamping, watermarking and post-processing tasks.
evopdf-next-pdf-merge
【文档与办公】Combine PDF documents in .NET with EvoPdf Next: the PdfMerge class which preserves bookmarks, annotations and internal links, AddStartPdf and AddEndPdf to wrap a generated PDF with existing documents, and AddPdfTemplate to draw one PDF onto another for stamping.
contract-renewal-tracker
【效率与协作】Never get auto-renewed into another year again — the contract inventory with the dates that matter (notice deadlines, not renewal dates), the calendar system with decision-time buffers, and the renewal-decision ritual that renegotiates instead of rubber-stamping. Use when asked track our contracts and renewals, we got auto-renewed again, when do we h…
implementing-log-integrity-with-blockchain
【效率与协作】Builds an append-only log integrity chain using SHA-256 hash chaining, where each entry incorporates the previous entry's hash so tampering invalidates all subsequent hashes; covers log ingestion (syslog/JSON/plain text), chain verification, pinpoint tamper detection, and checkpoint anchoring to external timestamping services. Use for tamper-evident …
verifying-skill-accuracy
【文档与办公】Fact-check LLM-drafted technical content against primary sources — source hierarchy, programmatic existence probes for tool and plugin names, class-before-instance error triage, the truncated-negative trap, adversarial re-checking, and the verified-stamp discipline. Use when auditing a SKILL.md for factual errors, before stamping a skill verified, wh…