Showing 12451–12480 of 15645 skills
Decides whether to ask clarifying questions or proceed with an answer, optimizing for information value vs. delay cost. Now with mathematical depth metrics, question value calculus, answer readiness , and verification gates.
Kshitijpalsinghtomar/depth-skills
Cross-compares every claim in an output to detect internal contradictions that sequential generation hides. Now with mathematical depth metrics, claim graph analysis, global coherence , and verification gates.
Kshitijpalsinghtomar/depth-skills
Digs beneath logic to inspect unchecked premises, rating each assumption by collapse severity. Now with sensitivity surfaces, counterfactual worlds, boundary detection integration, and mathematical depth metrics.
Kshitijpalsinghtomar/depth-skills
Prevents lossy compression from erasing conditions, exceptions, and uncertainties during summarization. Now with mathematical depth metrics, fidelity diff algorithm, compression integrity , and verification gates.
Kshitijpalsinghtomar/depth-skills
Prevents overthinking by matching cognitive investment to consequence - the intentional opposite of DEEP-THINK. Now with mathematical depth metrics, depth budget calculus, proportionality , and verification gates.
Kshitijpalsinghtomar/depth-skills
Uses the Feynman technique - explain simply to detect where knowledge gaps exist. Now with mathematical depth metrics, gap severity calculus, teaching effectiveness, and verification gates.
Kshitijpalsinghtomar/depth-skills
UV unwrap, atlas-map, project textures, use alpha decals, bake maps/lightmaps, and prepare texture-driven Blender assets for glTF/GLB export. Use whenever the user provides texture packs, texture atlases, decals, UV layouts, lightmaps, wants a texture to fit a mesh 1:1, or reports stretched/off textures. Pairs with reference-to-3d for template-accurate reconstruction and blender-materials for PBR values.
CheshireJCat/create-3d-model-skill
Orchestrate a fail-gated, source-locked Blender reconstruction of mascots, logos, brand avatars, and stylized flat characters from wireframes, texture packs, and orthographic views. Use when the user requires a 1:1 brand/model match rather than a plausible stylized interpretation.
CheshireJCat/create-3d-model-skill
광고 대행사의 작업 흐름(클라이언트 브리프 → 원자료 → 플래너의 과제 재정의와 크리에이티브 브리프 → CD 크리에이티브 서저리 → 크리에이티브 팀 3개의 아이데이션 → CD 리뷰 두 번과 팀 재작업·변론 → 광고주 선택과 사실·규제 검수)을 역할별 에이전트로 따라가 헤드라인을 내는 카피 파이프라인. 사람 확인 없이 고르는 일까지 모델이 하고, 결과와 함께 각 단계가 업계 흐름대로 돌았는지 점검한 표를 낸다. "광고 카피 써줘", "카피 뽑아줘", "헤드라인 만들어줘", "copy-masters" 요청에 사용. 퍼포먼스/브랜드 모드, SNS 피드·검색광고·상세/랜딩페이지·영상 스크립트 채널의 헤드라인.
5hyuns/ad-copy-agency-skill
通过自适应引导、必要讲解和独立练习,帮助用户学会并应用概念或技能。用于学习教练、带我学会、以掌握知识为目的的练习复习、检查理解或配置学习伙伴;不用于普通直接问答、会议回顾、摘要、代写或成品制作。
Lucian1u/learning-coach
Explain a topic like I'm a 5 year old. Use when the user types /eli5 <topic> or asks for a dead-simple picture explainer of how something works.
Spoon94/skill-vault
Use when the user asks whether an issue, task, or product decision already exists.
hassan-mohiddin/freeflow
Use when work on a branch or isolated checkout has reached a stopping point and the next job is to inspect integration readiness, choose merge/PR/keep/discard, verify the integrated result, or clean up branch/worktree state safely.
hassan-mohiddin/freeflow
Use when activating Freeflow in a repository, repairing its repository or personal configuration, or checking whether the current host is delivering Freeflow context.
hassan-mohiddin/freeflow
Use when creating, resuming, or updating a durable Working Record so ongoing task state, planned actions, decisions, history, and the next action survive execution, pauses, or context loss.
hassan-mohiddin/freeflow
Use when writing or revising an implementation plan, execution plan, remediation plan, migration plan, or similar ordered plan.
hassan-mohiddin/freeflow
当任务涉及完成声明、破坏性或外部状态变更、排错、长时间或可恢复的工作、子代理协作,或高风险审查时,采用轻量保护措施。在不强制固定开发流程的前提下,保留证据、可恢复性和用户控制权。
PANYUXIN6/pyx-skills
基于《广告法》第11条及2026年第20号公告《广告引证内容执法指南》(正式版),对广告文案引证内容执行六维度28条规则合规审查,输出结构化风险报告。输入广告文案文本,即可自动完成引证提取→规则匹配→风险定级→报告生成全流程。
CSlawyer1985/legal-skillhub
基于《广告法》《电子商务法》《消费者权益保护法》及司法解释,结合食品、化妆品、医疗器械、纺织、玩具、电子产品等领域实务案例,从广告合规与消费者权益保护角度提供专业意见。当用户提到广告合规审查、广告违法风险、广告违禁词、虚假宣传、消费者权益、惩罚性赔偿、知假买假、商品标签合规、商标侵权风险、电商详情页审查、行政处罚风险、职业打假、消保咨询、文案合规改写等场景时使用本技能。
CSlawyer1985/legal-skillhub
行政救济全流程AI技能。覆盖行政复议与行政诉讼的完整生命周期,从接案评估、受案范围判断、 被申请人适格性确认、行政行为分析、救济路径选择,到复议申请、证据整理、代理意见、 行政诉讼起诉、庭审准备、代理词撰写、二审再审、判决执行。 当用户涉及行政案件维权工作时触发,包括但不限于:"帮我分析这个行政处罚能不能复议" "写行政复议申请书""这个案件走复议还是诉讼""确认被申请人是谁""写行政起诉状" "准备行政案件庭审""写行政诉讼代理词""申请停止执行行政行为""行政赔偿"等。 适用于各类行政案件(行政处罚、行政许可、行政强制、行政征收、行政确认、行政不作为、 政府信息公开等),只做申请人端(公民/企业/其他组织),不代理政府机关。
CSlawyer1985/legal-skillhub
Use BEFORE any orchestra activation AND BEFORE any completion claim. Enforces Karpathy's 4 principles, Superpowers' Iron Law (no completion without fresh verification evidence), and ASK_HUMAN as a first-class status. Triggers on every entry to an orchestra, every handoff between orchestras, and every user-facing success claim ("done", "works", "should pass", "great", "perfect"). The orchestra system's anti-hallucination wrapper.
Momo2323-ui/claude-orchestra
Implement an agreed plan in behavior slices, validate the result, and check scope and unnecessary complexity before completion.
gomilesf/convergo
将一篇经管实证论文摄取为实证研究 wiki:论文卡片 + 变量 + 数据 + 模型 + 机制 + 识别 + 稳健性 + 异质性 + 表格线索
Lambenthan/empiricalwiki
用领域基础知识填充 wiki/foundations/,避免后续 /ingest 为教科书材料创建重复的 concept 页面
Lambenthan/empiricalwiki
按 scope 重置 wiki 到干净 scaffold(wiki / raw / log / checkpoints / all)。适用于开发迭代或 setup 失败后的无痛重启。
Lambenthan/empiricalwiki
从 wiki 知识生成论文 Related Work 章节:主题分组 → 叙事结构 → LaTeX 输出,遵循 citation-verification 和 academic-writing
Lambenthan/empiricalwiki
将一篇理论建模论文摄取为理论研究 wiki:论文卡片 + 假设/原语 + 命题/定理 + 解概念 + 可检验推论,并与实证层在同一张 graph 上接桥
Lambenthan/empiricalwiki
แก้ไขและปรับปรุงบทความด้วยการจัดโครงสร้าง section ใหม่ เพิ่มความชัดเจน และเขียน prose ให้กระชับ ใช้เมื่อ user ต้องการ edit, revise หรือปรับปรุง draft ของบทความ
Boom-Vitt/skills-thai
Extracts an answer from logs, traces, or metrics — finding the relevant lines in volume, correlating across services, and telling signal from noise. Use this whenever the user points at a log file, asks what happened at a particular time, mentions grepping logs, wants to know how often something occurs, or is trying to reconstruct a sequence of events across services. For fixing what the logs reveal, use debugging; for the write-up afterwards, use root-cause-analysis.
arjunprabhulal/agent-skills
Diagnoses connectivity problems — timeouts, connection refused, DNS failures, TLS errors, and requests that work from one place but not another. Use this whenever the user cannot reach a service, mentions a timeout or connection refused, has a certificate error, suspects DNS or a firewall, or says something works locally but not in the cluster. For a service that is reachable but slow, use performance-profiling; for reading what the logs say about it, use log-analysis.
arjunprabhulal/agent-skills