Ai skills

This skill audits each claim's evidence by inspecting the manuscript and reporting gaps with actionable fixes in MISSING_EVIDENCE.md.

This skill crafts a survey-quality paragraph from evidence packs, balancing tension, contrast, evaluation anchor, and limitation for subsection prose.

This skill writes per-section survey prose into sections/*.md files by enforcing citation scope and argument moves for QA-ready drafts.

This skill builds a large, verifiable candidate pool of literature with stable IDs and provenance for evidence-first surveys.

This skill binds section-specific evidence IDs from the evidence bank to each subsection, enabling precise writer-auditor references.

This skill downloads arXiv agent-survey PDFs, extracts text, and generates a STYLE_REPORT to help you study real survey structures for better writing.

This skill runs end-to-end research pipelines with workspaces and checkpoints, delivering auditable Units.csv and artifacts.

This skill fills outline/tables_index.md from evidence packs with citation-backed rows to support later writing and traceability.

This skill writes paper-like front matter sections (Abstract, Introduction, Related Work, Discussion, Conclusion) with high citation density for a cohesive

This skill ensures numeric claims are reviewer-safe by enforcing minimal protocol context (task, metric, constraint) and avoiding underspecified model naming.

This skill defines a tutorial spec with audience, prerequisites, measurable objectives, non-goals, and a running example for deterministic planning.

This skill reads a WeChat official account article from a given link and returns a structured summary with key insights.

This skill analyzes local Claude Code logs to summarize token usage by date and model, returning readable Markdown tables.

This skill helps you create Claude Code skills quickly by generating a ready-to-use SKILL.md and structure.

This skill helps you craft memorable product messaging using the SUCCESs framework to boost clarity, credibility, and emotional impact.

This skill generates professional text-heavy images using Qwen-Image-2-Pro via inference.sh, delivering realistic renders and strong semantic adherence for

This skill generates Gemini native image outputs from text prompts, enabling high-quality, customizable images with editing and multi-image input.

This skill helps you create and optimize clear data visualizations with best practices for chart types, color, and storytelling.

This skill filters audio by keywords using FunASR transcription and FFmpeg editing to remove specified content.

This skill converts text to speech with script parsing, emotion tagging, and optional voice-changer post-processing using Edge TTS.

This skill converts voice in audio using RVC AI model for authentic timbre transformation with automatic chunking and flexible presets.