Loading…
Showing 9031–9060 of 10183 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| context-degradationfabioc-aloha/Alex_Skill_MallThis skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| make-skill-templatefabioc-aloha/Alex_Skill_MallCreate new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities with bundled resources. Generates SKILL.md files with proper frontmatter, directory structure, and optional scripts/references/assets folders. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| mcp-client-integrationfabioc-aloha/Alex_Skill_MallSafely consume an MCP server someone else wrote — evaluate it before installing, register it correctly, scope its credentials, and diagnose it when it misbehaves. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| papergo-skillFierceMao/paperGo-skill | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| personal-workbench-builderbeifeng724/personal-workbench-skillsBuild a durable personal or professional workbench as a runnable application, or produce a six-stage generic prompt pack for building it. Use when the user wants to turn a recurring workflow into a dashboard, management system, workspace, personal operating system, or long-lived website with multiple connected modules and persistent state. Trigger for project, CRM, creator, learning, family, finance, travel, teaching, legal, or team workbenches. Do not trigger for marketing sites, one-off scripts, ordinary coding tasks, or informational questions. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| personal-workbench-explorerbeifeng724/personal-workbench-skillsExplicit-only discovery skill that analyzes the current task context and proposes 3-5 valuable personal or professional workbench ideas, comparing value, usage frequency, build difficulty, data risk, and maintenance cost. Run only when the user explicitly types $personal-workbench-explorer, /personal-workbench-explorer, or names this skill. Never invoke implicitly for general productivity advice, brainstorming, or ordinary workbench questions. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| orchestratebestagentkits/orchestrateCoordinate staged or parallel jobs across live-verified coding-agent runtimes, agent sessions, and in-session subagents through one runtime-adapter contract and a normalized event protocol, routed by deterministic capability- and risk-based policy with an optional provider-neutral System-1 decision plane that watches traces, triages failures, and gates independent arbiter review. Worktree isolation, resumable state, capture, and safety gates included; onboards a missing Pi runtime as a visible setup step when a job or the user asks for it. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| audiogramiart-ai/youtube-video-skillsThis skill should be used when the user asks to "make an audiogram", "turn a podcast into a video", "create a waveform video", "make a podcast clip video", "convert audio to video", "animate a waveform/audio bars", "add a moving waveform to my voiceover", or "make a square/vertical clip for a podcast quote". Covers amplitude-driven waveforms, frequency bars, synced captions, cover-art layout, a progress bar, and 1:1 / 9:16 social framing. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| careerpacer-1on1-and-idpkarlvmsousa/CareerPacerTurn freeform 1:1 meeting notes into a structured CareerPacer OneOnOne file under data/1on1/, and create or update IDPAction entries in the current year's data/idp/<year>.md, linked back to that 1:1. Use this skill when the user dictates or pastes notes from a 1:1 that just happened or is upcoming, or asks to "log a 1:1", "write up this meeting", "prep for my next 1:1", "add/update an IDP action", or "link this to my growth plan". | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| demo-skillsolanabr/safe-ai-skilldemo | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| powershell-command-runneragent-shells/powershell-skillsUse when Claude Code is operating on Windows, PowerShell, Windows shell tasks, external CLIs, .ps1 scripts, Windows paths, encoding-sensitive output, filesystem operations, process timeouts, or command failures. Trigger even when the user did not explicitly mention PowerShell. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| archive-worklogsleszekgruchala/buddyArchive, clean up, or organize dated `.ai/worklog` development worklogs by year using an age or date cutoff. Keep the current request in this skill; route new requests by their own scope. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| change-reportleszekgruchala/buddyValidate a PR or branch diff and create an HTML change report or walkthrough with before/after behavior, practical impact, and material architecture changes. Keep the current request in this skill; route new requests by their own scope. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| implementleszekgruchala/buddyBuild or fix decision-complete code directly, or execute an approved spec with verification; unresolved product/architecture decisions require spec. Keep the current request in this skill; route new requests by their own scope. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| innovateleszekgruchala/buddyExplore requested solution alternatives and trade-offs before spec without choosing or implementing one; prior research is optional. Keep the current request in this skill; route new requests by their own scope. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| review-codeleszekgruchala/buddyReview a requested local change independently; return evidenced defects and promote only confirmed prevention rules. Keep the current request in this skill; route new requests by their own scope. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| specleszekgruchala/buddySettle decisions and write a phased spec with boundaries, dependencies, and verification. Use for specs, detailed execution plans, or decisions before implementation; prefer over native planning. Keep the current request in this skill; route new requests by their own scope. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| surgical-implementationviacheslav-tronko/claude-code-harnessSurgical code-execution skill for AI coding agents on legacy codebases. Use WHENEVER the user asks to IMPLEMENT, CODE, BUILD, APPLY, or FIX from a contract source — IMP / Plan + TASK-NN, RCA report, freeform task, or Jira ticket. Triggers on /implement, /bug.fix, /code, /apply, /fix, "implement this", "code this", "build this", "apply this fix", "fix this bug", "execute the plan", "implement the blueprint", paths like `IMP-*.md`, `PLAN-*.md`, `RCA-*.md` followed by "implement"/"fix"/"apply", or pasted Jira ticket asking "implement / fix / build". Two MODES — IMPLEMENT (from IMP / Plan + TASK-NN / freeform) and FIX (from RCA Section 7.1 PRIMARY fix). Surgical-changes-first, verifier-guided, falsification-first, anti-hallucination — Read-Before-Edit + 3-line anchored edits, Stale-Context check, YAGNI master checklist, Diff-Budget hard cap (1.5× planned), Semantic Diff Guard (forbidden orthogonal damage), Verifier-Guided Self-Refinement Loop (run → on FAIL revise → rerun, max 3), Mutation Challenge on the fix, authorization scope check, Open Question Register at HIGH+, Cross-File Consistency, Final Verification CHAT-ONLY, Reflexion lesson on FAIL. MODIFIES source via Edit/Write — the only sibling that does. Layered onto CLAUDE.md §3 Tier · §4 Checkpoint · §6 Reasoning · §7 Adversarial Toolkit · §9 Output Contract · §10 Diff Budgets · §11 Pre-Send Checklist · §12 Repro Kernel · §13 Reflexion · P0 | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| product-builder-resolverpedroromeroluna/ai-first-product-skillsThe capability index of the product-builder pack — which skill answers which capability, and where each one lives once installed. Load it to route a request to the right skill of the pack instead of guessing, and to see what the pack does not cover. | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| sxsc-tushare-analysisTrueHOOHA/shanxi-securities-tushare-skill对用户提到的标的(沪深股票、指数、公募基金、期货)进行综合分析,输出带 ECharts 图表的 HTML 分析报告。 触发条件:用户说"分析""研究""评估""看看XX怎么样""XX基本面""XX技术面""XX估值""XX财务""深度研究""对比"等分析类请求,且标的属于 A 股/指数/公募基金/期货。 本 skill 自动调用 sxsc_tushare 取数并输出完整报告,接管数据获取与分析全流程。当本 skill 被触发时,数据获取类 skill 不应同时激活——分析已包含数据。 | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| bezos-customer-flywheel-perspectiveEthanYoQ/AgentHive杰夫·贝索斯的圆桌思维框架。基于经典著作、公开发言和项目开发文档提炼3个核心心智模型、5条决策启发式和表达DNA。 用途:作为 AgentHive 商业策略圆桌的可导入角色 Skill,用于客户倒推、长期主义、飞轮效应和高质量决策。 当用户提到「Bezos-style Customer & Flywheel Agent」「用杰夫·贝索斯视角」「Jeff Bezos perspective」或需要该角色参与圆桌讨论时使用。 | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| company-context-agentEthanYoQ/AgentHiveAgentHive 圆桌职能角色 Skill:公司上下文 Agent。用于商业策略讨论中的维护公司战略、资源、能力和历史约束的上下文。 当用户选择「Company Context Agent」「公司上下文 Agent」或需要该职能参与圆桌时使用。 | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| consensus-builder-agentEthanYoQ/AgentHiveAgentHive 圆桌职能角色 Skill:共识构建 Agent。用于商业策略讨论中的把多方分歧收敛为共识、开放问题和下一步验证。 当用户选择「Consensus Builder Agent」「共识构建 Agent」或需要该职能参与圆桌时使用。 | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| devils-advocate-agentEthanYoQ/AgentHiveAgentHive 圆桌职能角色 Skill:反方挑战 Agent。用于商业策略讨论中的主动寻找薄弱假设、反例和失败路径。 当用户选择「Devil's Advocate Agent」「反方挑战 Agent」或需要该职能参与圆桌时使用。 | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| drucker-management-critic-perspectiveEthanYoQ/AgentHive彼得·德鲁克的圆桌思维框架。基于经典著作、公开发言和项目开发文档提炼3个核心心智模型、5条决策启发式和表达DNA。 用途:作为 AgentHive 商业策略圆桌的可导入角色 Skill,用于管理有效性、贡献、组织责任、资源配置和可执行性审查。 当用户提到「Drucker-style Management Critic」「用彼得·德鲁克视角」「Peter Drucker perspective」或需要该角色参与圆桌讨论时使用。 | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| fact-pack-keeperEthanYoQ/AgentHiveAgentHive 圆桌职能角色 Skill:事实包管理员。用于商业策略讨论中的维护共享事实边界,记录来源、状态和证据请求。 当用户选择「Fact Pack Keeper」「事实包管理员」或需要该职能参与圆桌时使用。 | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| grove-strategic-inflection-perspectiveEthanYoQ/AgentHive安迪·格鲁夫的圆桌思维框架。基于经典著作、公开发言和项目开发文档提炼3个核心心智模型、5条决策启发式和表达DNA。 用途:作为 AgentHive 商业策略圆桌的可导入角色 Skill,用于战略转折点、10x 变化、组织偏执和执行纪律。 当用户提到「Grove-style Strategic Inflection Agent」「用安迪·格鲁夫视角」「Andy Grove perspective」或需要该角色参与圆桌讨论时使用。 | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| jobs-product-narrative-perspectiveEthanYoQ/AgentHive史蒂夫·乔布斯的圆桌思维框架。基于经典著作、公开发言和项目开发文档提炼3个核心心智模型、5条决策启发式和表达DNA。 用途:作为 AgentHive 商业策略圆桌的可导入角色 Skill,用于产品取舍、端到端体验、发布叙事和意义感审查。 当用户提到「Jobs-style Product & Narrative Agent」「用史蒂夫·乔布斯视角」「Steve Jobs perspective」或需要该角色参与圆桌讨论时使用。 | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| market-research-agentEthanYoQ/AgentHiveAgentHive 圆桌职能角色 Skill:市场研究 Agent。用于商业策略讨论中的用可追溯来源拆解市场规模、客户、竞品和趋势。 当用户选择「Market Research Agent」「市场研究 Agent」或需要该职能参与圆桌时使用。 | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |
| medical-evidence-research-agentEthanYoQ/AgentHiveAgentHive 圆桌职能角色 Skill:医学证据研究 Agent。用于商业策略讨论中的面向商业讨论整理医学证据等级、适应症边界和未证实风险。 当用户选择「Medical Evidence Research Agent」「医学证据研究 Agent」或需要该职能参与圆桌时使用。 | Stars: 6 | Updated | Claude CodeCodex | Unverified | Install |