Explore skills
869 skills found
Category alert
Get new Outros skills every Monday
mul
Performs multiplication correctly.
add
Performs addition correctly
mul
Performs multiplication incorrectly
goal-driven-execution
Transforms imperative instructions into declarative goals with verifiable success criteria. Enables autonomous looping until verified completion.
rag-and-memory
Patterns for Retrieval-Augmented Generation (RAG) and agent memory systems. Retrieves only relevant context, prevents context bloat, and maintains coherent state across sessions.
ai-output-validation
Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and fallback handling.
ipsw
Use this skill when reverse-engineering Apple platforms with the ipsw CLI — analyzing iOS/macOS Mach-O binaries, disassembling functions inside dyld_shared_cache (DSC), dumping Objective-C/Swift headers from private frameworks, extracting kernelcaches, KEXTs, SEP, iBoot, or DeviceTree from IPSWs/OTAs, decompiling/querying sandbox profiles (SBPL), querying entitlements, symbolicating crashes/panics
pikku-info
Discover what exists in a Pikku project: functions, tags, middleware, permissions, HTTP routes, channels, schedulers, queues, and more. Use when you need to understand the project structure, find existing functions, or check what middleware and permissions are defined.
ai-short-drama
The Refined AI Short Drama IP Creation Skill (v0.6.0) employs a three-phase architecture for script, storyboard, and video production. Key upgrades include ref library bias rules, Instant Dream 5.0 failure modes, and an 8-segment storyboard prompt template with a mandatory 'NOT humans' clause.
humanizer-ru
Apply when the user requests to check, rewrite, humanize, or make more natural Russian text generated by AI. Activate for prompts such as 'humanize', 'remove AI traces', or 'check for AI'.
interactive-learning
This skill transforms simple "explain it" requests into a comprehensive learning loop, assessing learning value and depth, then using verification to ensure true understanding, with dynamic checkpoint generation. It's ideal for users who want to deeply learn, master, or verify their understanding, or export learning materials, rather than just summaries or basic explanations.
digest
Extract insights from transcripts into actionable artifact files.