GitHub
agent-memory
Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on phrases like 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes', 'clean...
Skills IA testing security llm ai
Découvrez les skills testing security llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: testing security llm ai
testing security llm ai Effacer les filtres
Explorer
GitHub
local-skill-loader
Loads (copies) a skill from a local source directory into the current project's skill library (.claude/skills). Use this when the user wants to import or copy a skill from another location on the filesystem.
GitHub
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or too...
GitHub
global-prompts-sync
Synchronizes prompt files (agents, rules, commands) from the skill's prompts directory to both GitHub Copilot and OpenCode global configuration directories. Use when the user wants to update their AI editor pro...
GitHub
interview
Structured human-agent Q&A via HTML or TUI forms. Use when you need clear yes/no/refine decisions from the user on multiple items. Agent provides recommendations, human validates or overrides.
GitHub
episodic-archiver
Episodic Memory Archiver. Stores full conversation transcripts with embeddings and analysis into ArangoDB. Use this to save the "User Story" or "Chain of Thought".
GitHub
orchestrate
Orchestrate tasks from a 0N_TASKS.md file with enforced memory-first pre-hooks, quality-gate post-hooks, and session archiving. BLOCKS if unresolved questions exist. Use when user says "run the tasks", "execute...
GitHub
embedding
Standalone embedding service for semantic search. Runs as persistent FastAPI server for millisecond-latency embeddings. Supports model swapping via env vars. Use when you need vectors for any database (ArangoDB...
GitHub
scillm
Managed scillm Paved Path execution. Provides strict contract-compliant tools for Text Batch, VLM, and Lean4 Proving. Uses `parallel_acompletions_iter` for reliable large-scale processing.
GitHub
autoskill
Analyze coding sessions to detect corrections and preferences, then propose targeted improvements to Skills used in the session. Use this skill when the user asks to "learn from this session", "update skills",...
GitHub
autoskill
Analyze coding sessions to detect corrections and preferences, then propose targeted improvements to Skills used in the session. Use this skill when the user asks to "learn from this session", "update skills",...
GitHub
using-superpowers
Use at conversation start - establishes how to find and use skills, requiring skill loading before ANY response
GitHub
transcript-fetcher
從 YouTube、Apple Podcast 或 Bilibili 的 URL 獲取逐字稿。 當使用者貼上影片或 podcast 連結，或說「幫我拿逐字稿」「轉成文字」時觸發。 使用 aits 命令獲取內容，回傳給使用者後續使用。
GitHub
video-generation
Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build...
GitHub
create-skill
Create a new agent skill following the Agent Skills specification. Use this when the user asks to create a new skill or update an existing one to match the standard.
GitHub
team-composition-analysis
This skill should be used when the user asks to "plan team structure", "determine hiring needs", "design org chart", "calculate compensation", "plan equity allocation", or requests organizational design and hea...
GitHub
objective-setting
Replaces the work of translating abstract user intent into concrete and verifiable goals (SMART) for agent execution. Typical use cases: (1) Defining the Outcome (desired state) from conversations or Issues, (2...
GitHub
context-creation
Replaces the process of defining the system's overall picture (SSOT) and dynamically maintaining alignment between codebase reality and design maps. Typical use cases: (1) Defining initial system boundaries and...
GitHub
decision-support
Replaces the task of identifying information gaps needed for decision-making and proposing strategic approaches to resolve bottlenecks. Typical use cases: (1) Analyzing trade-offs and 4 Big Risks among multiple...
GitHub
context-review
Replaces the task of auditing whether the updated system context accurately reflects the "real code" to ensure reliability. Typical use cases: (1) Verifying that described external system integrations match act...
GitHub
todo-management
Skill for breaking down goals into atomic, verifiable steps and managing them in .gemini/todo.md. Used when (1) creating a detailed step-by-step execution plan, (2) tracking progress of multi-step operations to...
GitHub
adr-creation
Replaces the entire process of formulating Architecture Decision Records (ADRs) based on the OODA loop. Typical use cases: (1) Defining the specific scope and components of the system to be implemented next, (2...
GitHub
objective-analysis
Replaces the work of extracting the true intent behind user statements or Issues and formulating multi-perspective solution hypotheses. Typical use cases: (1) Structuring information using the 5W1H framework, (...
GitHub
skill-creator
Replaces the work of presiding over the creation of new skills or refinement of existing ones to capitalize agent capabilities as reproducible knowledge. Typical use cases: (1) Formalizing successful retrospect...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.