Loading...
Loading...
Found 4,631 Skills
This skill should be used when the user asks to "check for non-repudiation privacy risks", "analyze excessive audit logging", "find privacy issues related to accountability", "check for forced identity linking", or mentions "non-repudiation" in a privacy context. Maps to LINDDUN category N. This is the INVERSE of STRIDE repudiation -- here too much proof is the threat.
Style, review, and refactoring standards for Bash shell scripting. Trigger when `.sh` files, files with `#!/usr/bin/env bash` or `#!/bin/bash`, or CI workflow blocks with `shell: bash` are created, modified, or reviewed and Bash-specific quality controls (quoting safety, error handling, portability, readability) must be enforced. Do not use for generic POSIX `sh`, PowerShell, or language-specific application style rules. In multi-language pull requests, run together with other applicable `*-style-guide` skills.
Create or update role-specific skill packages with deterministic files. Supports output to skills/ (open-source publishing) or .agents/teams/ (team use). Triggers: 创建角色, 新建 role, create role, 更新 role scope, edit role, update role, add role skill, 修改角色配置. Use when the user asks to create, update, or edit frontend/backend/product (or custom) role skills with auto-generated role fields, guided brainstorming fallback, and curated skills selection.
Conduct Pareto Analysis (80/20 Rule) to identify the vital few causes driving the majority of problems. Guides data collection, category definition, chart creation, cumulative percentage calculation, and prioritization. Generates professional Pareto charts (SVG) and HTML reports with quality scoring. Use when prioritizing defects, complaints, failures, or improvement opportunities; when user mentions "Pareto", "80/20 rule", "vital few", "trivial many", "prioritization", or needs to identify which factors contribute most to a problem.
Generate a CLI + AgentSkill from any REST API documentation. Use when: (1) wrapping a SaaS API as a CLI tool, (2) creating agent-ready integrations for APIs like Typefully, Dub, Mercury, Front, etc., (3) user says 'create a CLI for X API', 'wrap this API', or 'make a skill for X'. Handles API discovery, scaffold generation, resource implementation, building, and PATH linking.
Use this whenever an OpenChoreo task needs a platform-level change or investigation: cluster setup, Helm upgrades, kubectl work, plane connectivity, platform resources, ComponentTypes, Traits, Workflows, gateways, secret stores, identity, GitOps, observability, or cluster-side debugging. If the same task also involves deploying or debugging an application through `occ`, activate `openchoreo-developer` too instead of waiting to escalate later.
Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.
Enforces Built for Shopify (BFS) quality standards during Shopify app development. Use when building, reviewing, or auditing Shopify apps for BFS compliance, or when the user mentions Built for Shopify, BFS, app quality, or app store requirements.
Strategic guidance on AI scaling laws, capability trajectories, and building products at the frontier of AI capabilities. Use when users ask about AI scaling trends, capability forecasting, planning AI product development timelines, understanding pretraining vs reinforcement learning phases, interpreting AI benchmark improvements, deciding when to build AI products that don't quite work yet, or strategizing around rapidly advancing AI capabilities. Also triggers for questions about task horizon doubling, Jevons paradox in AI, or how to position products for future model improvements.
Japanese version of the PUA Universal Motivation Engine. It compels exhaustive problem-solving using corporate PUA rhetoric and structured debugging methodology in Japanese. MUST trigger under the following conditions: (1) Any task has failed 2+ times, or you're stuck in a loop of tweaking the same approach; (2) You're about to say 'I cannot', suggest manual handling to the user, or blame the environment without verification; (3) You find yourself being passive — not searching, not reading source code, not verifying, just waiting for instructions; (4) The user expresses frustration in any form: 'try harder', 'stop giving up', 'figure it out', 'why isn't this working', 'again???', 'もっと頑張れ', 'なんでまた失敗したの', 'もう一回やって', 'なんとかしろ', or any similar sentiment regardless of phrasing. It should also trigger when facing complex multi-step debugging, environment issues, configuration problems, or deployment failures where early surrender is tempting. Applies to ALL task types: code, configuration, research, writing, deployment, infrastructure, API integration. DO NOT trigger on first-attempt failures or when a known fix is already executing successfully.
Add audio sources, sound effects, music, audio streaming, and video players to Decentraland scenes. Use when user wants sound, music, audio, video screens, speakers, or media playback.
Detect and annotate hallucinations, unsupported claims, fabricated studies, and incorrect conclusions in text so that AI only cites verifiable, trustworthy content. Use this skill whenever the user asks you to fact-check, validate sources, check for hallucinations, or ensure that generated content is grounded in real evidence, even if they do not explicitly use the word "hallucination".