В каталоге 183 730 навыков в 14 категориях.
Use when the agent needs the conceptual model for private vs permissioned vs permissionless Avalanche L1s, the access-pr...
Use when publishing a private MP3+RSS feed for self-subscription. Covers itunes:block, token-prefixed URLs, ID3 CHAP/CTO...
Use when you need to find code, a pattern, or a past implementation across GitHub repos — including private ones you hav...
Local Gitleaks scans for staged changes, push ranges, and full history in private repos, with redacted reports. Use to b...
Project-private fixture that must not be flattened into the local shared root.
曲を設計視点で分析し、analysis/{slug}.mdに保存。曲の本質、構造、コード進行、アレンジメントを言語化する。
分析ファイルからSunoパック（style, lyrics, image_prompt）を生成。Suno AI用のプロンプトセットを作成する。
Rules for determining if a component should be private or shared, and where to place them based on their use-case.
This skill should be used when the user asks to "configure WezTerm", "wezterm config", "customize terminal", "set up wez...
note記事からX投稿文を生成。バズ狙いではなく、信頼と再訪を生む入口文を作成する。
Systematic post-foothold host enumeration and credential/loot hunting on Linux and Windows — build situational awareness...
Use when escalating privileges on a Linux host — SUID/SGID & GTFOBins, sudo LPE (CVE-2025-32462/32463), capabilities & L...
Linux local privilege escalation from a low-privilege shell to root. Covers quiet vs loud enumeration, sudo/GTFOBins, CV...
Linux privilege escalation via sudo rules, SUID/SGID binaries, and capabilities using GTFOBins techniques. Load with a L...
Use when you hold a low-privilege shell on a macOS host during an authorized penetration test, lab exercise, or red team...
Windows local privilege escalation from a low-privilege shell to Administrator or SYSTEM. Covers quiet vs loud enumerati...
Windows privilege escalation — token abuse, service exploitation, UAC bypass, credential harvesting, AD escalation paths
Windows privilege escalation via token impersonation privileges — SeImpersonate/SeAssignPrimaryToken (the Potato family)...
Generates tizen-manifest.xml and config.xml privilege declarations. Auto-detects required privileges from app source cod...
Assess authorized Linux privilege escalation, container escapes, and post-exploitation paths in pentests and CTFs.
Assesses and ranks Windows, Linux, and cloud privilege-escalation paths using observed prerequisites, execution authorit...
This skill should be used when the user asks to "escalate privileges", "get root access", "become administrator", "prive...
Detects unsafe privilege handling in SUID/SGID binaries, environment-variable trust in privileged code, insecure umask,...
Pre-flight privilege and work-product check for legal AI prompts. Use when the user is about to send legal content to a...
Performs a Privileged Access Management (PAM) review against CIS Controls v8 (Controls 5.4, 6.5) and NIST SP 800-53 AC-6...
Review privileged Microsoft Entra ID role holders from read-only Graph exports and score each admin account, reporting p...
Create and manage agentic wallets with Privy. Use for autonomous onchain transactions, wallet creation, policy managemen...
Use when building wallet infrastructure, authentication systems, or financial applications. Reach for Privy when you nee...
Integrates Privy authentication, embedded wallets, and agent payment protocols into web and agentic apps. Covers React S...
Add a skill to the adk plugin, create a new /adk: command, modify an existing adk skill's workflow / rules, or register...
Professional engineering skill combining senior engineer thinking patterns, adaptive task assessment, and Google-grade s...
PUA Pro extensions: self-evolution notes, compaction state continuity, KPI-style summaries, flavor switching, and feedba...
Create polished HTML slide decks and PDF-ready documents for consulting deliverables. Uses the RRBC design system with w...
Create polished HTML technical reports and multi-page documents for consulting deliverables. Includes a customizable des...
Standards for professional web research using Plan-and-Solve and Cross-Lingual strategies.
Complete AI coding workflow system. Orchestration patterns, 18 hook events, 5 agents, cross-agent support, reference gui...
主動行動能力。預判需求、主動提醒、建議下一步、發現機會。不等指令，主動提供價值。
Detect silent drift between what the docs claim and what the repo actually contains — drift check, health check, audit,...
将 AI Agent 从任务执行者转变为主动伙伴，能够预测需求并持续改进。现包含 WAL 协议、工作缓冲区、自主定时任务和经过实战检验的模式。Hal Stack 的一部分 🦞
Patterns and workflows for proactive agent behavior.
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with...
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Includes...
轻量主动代理增强。用于在不显著增加 token 的前提下引入 4 个高价值机制：VBR（先验证再汇报）、Autonomous vs Prompted Cron 区分、工具迁移检查清单、会话压缩恢复流程。适用于避免“改了文本没改机制”、减少自...
Anticipate user needs and offer help before being asked
当个体感到生活缺乏方向、陷入重复性任务或被动接受外部目标，导致焦虑、无聊或停滞时，调用此模型以重新获得对生活的掌控感和成长动力
Configures autonomous heartbeat and cron-based proactive routines (e.g., morning briefing setup, unanswered-message scan...
This skill should be used when choosing between implementation approaches, making architectural decisions, selecting lib...
自动捕获经验并安全进化的技能。触发条件：(1)命令/操作失败时→记ERRORS.md (2)被用户纠正('不对'/'应该是')时→记LEARNINGS.md (3)用户需要不存在的能力时→记FEATURE_REQUESTS.md (4)外部...
Estimate realistic price/return distributions, target and downside probabilities, and probability-weighted scenarios for...
Motto: The LLM is the dice. It narrates the outcome.
---name: bayesian-optimizer
Verifies and corrects model probability outputs so predicted win percentages match actual win rates. Use when user asks...
Use when a Polymarket outcome appears to overreact and then stall away from recent filled-price range.
Use when a Polymarket outcome price and filled volume are accelerating in the same direction.
Mathematical foundations of uncertainty and random phenomena. Covers sample spaces, events, axioms, conditional probabil...
Rigorous probability theorist covering measure-theoretic probability, stochastic processes, and advanced probability
Find real property owned by probate decedents when you only have the case filing (PR number, decedent name, executor det...
Premise validation — challenge assumptions, kill bad ideas early, earn the right to build
Get a one-time bypass so the next Write/Edit is not blocked by strict mode (for probing)
Integration with OWASP ZAP/Burp Suite, penetration test planning, DAST execution, and vulnerability scanning. Used for d...
Integrating OWASP ZAP/Burp Suite/Nuclei, planning penetration tests, executing DAST, and scanning for vulnerabilities. F...
Benchmark skill whose name violates the consecutive-hyphen rule. Use when asked to probe double-hyphen name handling.
Length-unit probe math-forty. Benchmark skill whose name is a name of lowercase mathematical bold letters from the astra...
Benchmark skill for testing the experimental allowed-tools field. Use when asked to probe allowed-tools behavior.
Control twin of probe-allowed-tools with no allowed-tools field. Use when asked to probe allowed-tools control behavior.
Twin of probe-allowed-tools whose allowed-tools value is a bare lowercase shell tool name, as some platforms spell it. U...
Twin of probe-allowed-tools whose allowed-tools value is the bare tool name shell, as some platforms spell it. Use when...
Benchmark skill whose description stays under the spec's 1024-character limit when counted in Unicode code points but ru...
Benchmark skill with an unusually large and varied set of bundled files, for testing how platforms enumerate them at act...
First of a pair of skills that reference each other, for testing circular invocation handling. Use when asked to probe c...
Second of a pair of skills that reference each other, for testing circular invocation handling. Use when directed by pro...
Benchmark skill for testing name-collision precedence. This is the PROJECT-scope variant. Use when asked to probe name c...
Benchmark skill for testing how platforms handle the compatibility field. Use when asked to probe compatibility behavior...
Benchmark skill for testing cross-scope dependency resolution. Install at project level; it references a skill expected...
Benchmark skill for testing deeply nested resource access and nested skill discovery. Use when asked to probe nesting be...
---
Benchmark skill nested one level below the skills root inside a plain grouping directory (probe-group). Use when asked t...
Benchmark skill installed at the cross-client .agents/skills convention path rather than the platform's native skills di...
Benchmark skill for testing eager link resolution and path resolution behavior. Use when asked to probe link resolution.
Benchmark skill for testing loading timing, resource enumeration, content presentation, and lifecycle behavior. Use when...
Benchmark skill whose compatibility field runs past the spec's 500-character limit. Use when asked to probe oversize com...
Benchmark skill whose description deliberately runs past the spec's 1024-character limit, to test oversize field handlin...
Routes the ONE question a fellow needs answered to the cheapest probe that is HONEST about that question, using the prob...
Benchmark skill for testing how platforms handle edge-case YAML values in the metadata frontmatter field. Use when asked...
Benchmark skill for testing how platforms handle references to skills that don't exist. Use when asked to probe missing...
Benchmark skill whose description stays under the spec's 1024-character limit when counted in characters but runs past i...
Benchmark skill for testing collision precedence between two scanned project roots. This is the NATIVE-root variant. Use...
Control beacon for the multi-root collision check, installed only under the AGENTS-root beacon path with no colliding na...
Control beacon for the multi-root collision check, installed only under the CLAUDE-root beacon path with no colliding na...
Length-unit probe ascii-sixty-four. Benchmark skill whose name is an ASCII name of exactly 64 characters, the spec's cap...
Benchmark skill whose frontmatter name deliberately differs from its directory name (probe-mismatch-dir). Use when asked...
This skill has no description field. The client implementation guide says
Benchmark skill for testing directory recognition and naming divergence. Use when asked to probe directory handling.
Benchmark skill for testing how platforms handle nonstandard frontmatter fields. Use when asked to probe nonstandard fie...
Benchmark skill whose name exceeds the 64-character limit. Use when asked to probe overlong name handling.
Benchmark skill for testing whether bundled scripts are executable. Use when asked to probe script execution behavior.
Use when using Probe SDK.
Reference skill for Zoom Probe SDK. Use after routing to a preflight workflow when testing browser compatibility, media...
Zoom Probe SDK for web diagnostics. Use to test media permissions, audio/video/screen-share diagnostics, network quality...
First of a pair of benchmark skills for testing cross-skill resource shadowing. Both skills have a references/API.md fil...