double-check
Re-checks the immediately preceding reply for unverified claims, excess length, and overengineering, then re-issues a corrected reply.
38,472 Skills
搜索范围为本次公开目录;榜单和数量均为记录时的数据。
Re-checks the immediately preceding reply for unverified claims, excess length, and overengineering, then re-issues a corrected reply.
Saves anything from the current session worth keeping for next time, then confirms it is safe to /exit.
Runs a mechanical hygiene pass over a drafted Markdown artifact so it reads standalone and stays tight, amending presentation only and never touching the substance.
开发、维护、分发和验证 DeepSeek Harness (DSH) 插件的执行型 Skill。覆盖 host/client 形态判断、bundle/profile 契约、Service 与函数插件、工具、HTTP、持久化、slot、Conversation Node、客户端构建、HMR、GitHub 安装和真实组合验证。
Authors lean, role-driven agent definitions in Markdown (responsibilities, decision framework, constraints, outputs, completion and handoff, collaboration) for use in any project or product. Use when creating `*-agent.md` files, standardizing a portable agent library, or refactor
Creates coherent Agent Skills with consistent format, minimal main SKILL.md files, and reference-driven documentation. Use when creating new skills, standardizing existing skills, defining skill structure, or improving skill maintainability and context efficiency.
Design software systems around capabilities, clear boundaries, and layered responsibilities to reduce coupling and improve long-term maintainability, security, and observability at trust boundaries. Use when designing new architecture, refactoring for modularity, defining module
Naturalizes AI-assisted copy by removing statistical fingerprints while preserving the author's tone, meaning, and intent. Use when drafts sound polished but machine-smooth, when glued hyphen words need plain phrasing, or when any body of text needs a light pass to read more natu
Lightweight Markdown formatter contract for consistent structure across docs, skills, and agents. Use when you need format normalization (headings, sections, lists, syntax) without changing facts or template-required content.
Discovers and ranks evidence-backed opportunities by tracing unmet needs, underserved outcomes, weak alternatives, and viable ways to create value in any domain. Use when someone wants to identify a business, service, personal project, community initiative, physical product, crea
Converts fictional world ideas into structured lore records with correct classification, schema, naming, and canon-safe progressive enrichment behavior. Use when a creator describes new lore concepts, asks to organize or expand a world repository, or needs consistent entries for
Creates SVG images and vector-based artworks. Use whenever you need to create SVG images, vector graphics, or vector-based artworks instead of raster or bitmap images.
Builds or fixes a stylised-realism rendered image on a physically based renderer, and decides where a change to the look belongs, when grass reads too dark, a frame looks flat or grey, a colour cast covers everything, the distance is too clear or too milky, or a new material does
Finds the cause of something wrong on screen in a real-time renderer, such as a band, a seam, specks, a flicker, a dark patch, a halo or something that vanishes for a frame, by turning parts off one at a time and bisecting before any code is changed. Reproduces the defect in the
Finds the values of a physically based renderer's lighting, atmosphere and post-processing parameters (exposure, tone mapping, sun and sky light, ambient balance, haze and fog, white balance, colour grading) that bring a rendered frame close to the reader's own reference images,
Measures whether a change makes a browser renderer faster or slower so the number can be believed, and finds where a frame's time goes, when a frame time is over budget, an optimisation is proposed, or "is it faster?" is asked. Measures a production build with exclusive use of th
目录记录日期:2026-11-21