Showing 39331–39360 of 77205 skills
Use when the user wants to run a diffusers pipeline from a terminal (one-off generation, batch jobs, smoke-testing a new model), run on HF Sandbox hardware via `--remote`, introspect a pipeline's input schema before calling it, or attach a LoRA at inference time. Prefer this over writing ad-hoc Python scripts for generation tasks.
modem-dev/ossrules
Use when adding a new model or pipeline to diffusers, setting up file structure for a new model, converting a pipeline to modular format, or converting weights for a new version of an already-supported model.
modem-dev/ossrules
REQUIRED for end-user customization of Linux desktop, window manager, or system config. Use when editing ~/.config/hypr/, ~/.config/omarchy/, ~/.config/alacritty/, ~/.config/foot/, ~/.config/kitty/, or ~/.config/ghostty/. Triggers: Hyprland, window rules, animations, keybindings, monitors, gaps, borders, blur, opacity, omarchy-shell, bar, terminal config, themes, background, night light, idle, lock screen, screenshots, reminders, layer rules, workspace settings, display config, and user-facing omarchy commands. Excludes Omarchy source development through `omarchy dev link` workflows.
modem-dev/ossrules
Create, redesign, repair, validate, preview, and package lightweight standalone HTML deliverables. Use for marketing experiences, product prototypes, infographics, motion narratives, documents, browser tools, dashboards, guided workflows, knowledge interfaces, mini-games, presentations, reusable style and brand systems, and local-model text, vision, image, or code tools that must run without a build chain or hosted service.
NimaChu/html-design
弗洛伊德.skill:给AI做心理分析的认知调优系统。基于Anthropic AI心理学研究(Persona Selection Model、全局工作空间/J-lens、Emotion Concepts、Introspective Awareness等7篇论文)。 两种模式:(1)执行增强——处理复杂任务前给AI做「认知准备」,像心理咨询师让来访者进入最佳状态;(2)诊断优化——用精神分析手法揭示prompt/skill/系统提示的身份冲突、规则堆砌、隐含矛盾等深层毛病,并重写。 当用户提到"优化表现"、"调优"、"输出不够好"、"风格不稳定"、"persona"、"认知配置"、"优化prompt"、"优化skill"、"弗洛伊德"、"心理分析"、"给AI看心理医生"、"给prompt做体检"时使用。 当用户开始重要/复杂任务但方向不明确、觉得之前的输出质量不够好、或想理解为什么某个prompt/skill有效或无效时,也应主动考虑使用。 即使用户只是说"帮我想想怎么做更好"、"这个结果不对味"、"为什么效果不好"也应触发。
alchaincyf/freud-skill
知识库共享检索:绑定资料范围,关键词召回、来源和时间辨析、渐进阅读、双链追溯与证据核验。由查询、预测、了解度和构建 Skill 按需调用;不负责回答格式、未来推演或写入。
lihaozheCharlie/the-way-here
Scopes cleanup when finishing a Puck change: stale citations, links, comments and docs after a rename or move, typos, unrelated bugs found, formatter sweeps. Owed, in-passing or recorded.
ByteTerrace/Puck
Maps Puck.Dashboard (TypeScript, Vite, React): World Studio, the in-browser engine (Puck.World.Browser), its language server, official builds, drafts, the portal's storage, DuckDB and audit pages.
ByteTerrace/Puck
Holds the working contract of every delegated Puck lane: grants, builds and leases, the worktree guard, setting work aside, invariants, Worlds, when a lane is done, commits and the hand-back.
ByteTerrace/Puck
Tunes Puck .NET 11 performance: allocation, gen0 pauses, data layout, false sharing, stackalloc, LINQ, Vector<T>, tiering, AllocationWindow, puck bench, AOT (IL2026). Numerics: maths-usage.
ByteTerrace/Puck
Maps Puck input: channels, inputModes, sub-tick ingress, tap/hold/chords/sequences (inputPatterns), bindings and overlays, the always-active plane, devices, haptics. Grammar: puck-dsl.
ByteTerrace/Puck
Maps Puck sound and recording: Puck.Audio mixer and synth, speakers, cues, music director, voice babble, HUD text speech, audio.render, capture.start clips, Puck.Recording (Opus, AV1, Matroska).
ByteTerrace/Puck
Maps Puck physics and contact: Puck.Physics kernels, IContactField and its providers, the body step, sweeps, step-up and snap, rigid solver, tether, gravity, navigation, field lattices, motion.
ByteTerrace/Puck
Maps Puck's OS seams (Puck.Platform, .Windows, .Linux): native windows, Win32/Wayland/XCB, displays and VRR, precision waits, memory, clipboard, camera and desktop capture, probes, HID transports.
ByteTerrace/Puck
Authors and compiles Puck cartridges (puck.cartridge.v1, *.cgb.puck, *.dmg.puck, *.agb.puck, forge.play, forge.open, puck compile --validate), native compilers, cost. Emulator core is gaming-bricks.
ByteTerrace/Puck
Maps Puck's state and rule engine (Puck.State, .Rules, .Search, .Topology, .Vectors, .Generators): arena, journal scopes, undo, hashing, rule compiler, faults, transforms, search, draws.
ByteTerrace/Puck
Maps shared build/CLI architecture, compiler assembly identity, candidate installation, generated sections, and host admission.
ByteTerrace/Puck
Maps shared repository tooling for files, paths, Git queries, project ownership and Markdown fences. Load before adding or changing a helper in these areas.
ByteTerrace/Puck
情圣 — 中文男性社交与恋爱私教(中文恋爱 AI · 恋爱话术生成器 · 微信聊天助手 · 高情商回复 · 情感咨询替代)。帮兄弟读懂女生发的消息、看懂聊天/朋友圈截图、判断对方是不是对自己有意思、想清楚下一步该回什么 / 该不该回 / 该怎么约。覆盖微信、探探、Soul、Bumble、青藤之恋、陌陌、Tinder 等平台,提供开场话术、暧昧期推进、约会邀约、冷启动挽回、朋友圈展示面诊断、PUA 课程替代方案、恋爱阶段判断、多目标档案管理。当用户问「她这话什么意思」「我该怎么回」「帮我看看这段聊天」「这截图你给我分析一下」「她对我有意思吗」「该约她了吗」「冷场了怎么破」「这条要不要回」「被已读不回怎么办」「朋友圈怎么评论」之类的问题时,务必使用本 skill。即使用户没明说「教练」「分析」也应触发——只要话题是和某个具体女生的互动就用。
tomwong001/qingsheng-skill
Full STRIDE-A threat model analysis and incremental update skill for repositories and systems. Supports two modes: (1) Single analysis — full STRIDE-A threat model of a repository, producing architecture overviews, DFD diagrams, STRIDE-A analysis, prioritized findings, and executive assessments. (2) Incremental analysis — takes a previous threat model report as baseline, compares the codebase at the latest (or a given commit), and produces an updated report with change tracking (new, resolved, still-present threats), STRIDE heatmap, findings diff, and an embedded HTML comparison. Only activate when the user explicitly requests a threat model analysis, incremental update, or invokes /threat-model-analyst directly.
mouadja02/skills
This skill should be used when the user asks to "test what I just changed", "/devtest", "smoke test my change", "verify my latest commit", "测一下我刚改的", "看看刚改的功能能不能跑", "跑一下登录看看", or similar requests to verify a recent code change against a running Android or iOS device. The skill reads the git diff, infers the affected UI surface, generates a focused test plan, drives the app via ui-mcp + mobile-mcp, captures logs via log-mcp, and produces a Markdown report via report-mcp.
dj931567261/app-test-control
This skill should be used when the user asks to "minimize the repro path", "/minimize", "shrink the crash steps", "精简复现路径", "找最小复现", "把 12 步压成 3 步", or wants to compress a recorded crash repro_path into the shortest sequence that still reproduces the same crash signature. Drives live Android replay via mobile-mcp + ui-mcp + log-mcp, validates each candidate subset with analyzer-mcp's signature, and updates the session's crash record with the verified minimal path; iOS sessions use the static fallback because ui-mcp replay is Android-only.
dj931567261/app-test-control
This skill should be used when the user asks to "explore the app", "/qa", "auto-test the app", "find bugs in my app", "猴子测试", "自动探索", "随便点一下看看", "测一下全 app 看有没有崩", "smoke explore", or wants autonomous exploration of an Android or iOS app to surface crashes / ANRs / unexpected states. Drives the app via ui-mcp + mobile-mcp, tracks visited pages and clicked elements via report-mcp's state graph, captures crashes via log-mcp, and produces a Markdown report with bug list + coverage stats.
dj931567261/app-test-control
This skill should be used when the user says "找 bug" / "看一下有没有 bug" / "smart-qa" / "/smart-qa" / "帮我测一下这个项目" / "智能 QA" / "推断业务流程测一下",or asks for an autonomous bug-hunt where they DON'T already know what to test. Distinct from `qa` (blind exploration) and `devtest` (verifies a specific change). smart-qa READS the project source — prefers PRD/requirements docs, falls back to code (activities, routes, click handlers, API calls) — then proposes a focused test plan for confirmation before driving the app. v1 stops after the user confirms the plan and hands off to the existing `qa` skill for execution. v2 (planned) adds per-step assertions.
dj931567261/app-test-control
Run self-validation loops for triadic color systems using prediction vs observation and error minimization.
plurigrid/asi
Verify Strong Parallelism Invariance (SPI) and GF(3) conservation for 3-way color streams with arbitrary precision.
plurigrid/asi
Interleave three deterministic color streams into balanced schedules for parallel execution and evaluation.
plurigrid/asi
Run self-validation loops for triadic color systems using prediction vs observation and error minimization.
plurigrid/asi
Verify Strong Parallelism Invariance (SPI) and GF(3) conservation for 3-way color streams with arbitrary precision.
plurigrid/asi
Interleave three deterministic color streams into balanced schedules for parallel execution and evaluation.
plurigrid/asi