В каталоге 182 820 навыков в 14 категориях.
Re-derive your knowledge system from first principles when structural drift accumulates. Analyzes dimension incoherence,...
Discards this thread's accumulated drafts and framings and re-derives the task from a clean problem statement. Use when...
Resolve git conflicts from any operation (merge, rebase, cherry-pick, stash, revert). Use when encountering conflicted f...
Understand temporal meaning in context without performing calendar arithmetic.
Resolve all pending CLI tasks using parallel processing
Assign negation, temporality, and uncertainty (the ConText axes) to clinical entities extracted by OpenMed, so "denies c...
Resolve an in-progress git merge or rebase conflict. Use when a merge, rebase, or cherry-pick stops on conflicts.
PD context-aware self-respawn. Invoked by a PD agent when context window reaches 80% threshold. Saves current state, wri...
Wraps any prompt with a reminder to respect CLAUDE.md files
Compresses verbose responses by removing filler and framing to save 200-400 tokens. Use when responses feel bloated or c...
Run headless AI CLIs (Claude Code, Gemini, OpenAI Codex, Cursor Agent, GitHub Copilot) to rate an assistant response aga...
Explains result schema classes for Synapse plugin actions. Use when the user mentions "TrainResult", "InferenceResult",...
This skill should be used when the user asks to "analyze experimental results", "generate results section", "statistical...
Resume orchestrating of a babysitter run. use this command to resume babysitting a complex workflow.
Continue work recorded in .ai/state/current.md after switching tools or sessions. Manual command.
Resume work from a handoff, checkpoint, or finalize artifact
Continue work from a previous session's handoff document
Resume from a previous session handoff. Use when: - User says "resume", "continue where we left off", "pick up where" -...
Resume work from a handoff document. Use when user says 'resume handoff', 'continue from handoff', or references a hando...
基于目标岗位 JD、中文简历和用户确认的真实经历，完成中国大陆求职场景下的 JD 解析、证据映射、缺口诊断、素材追问、定制简历重写、ATS/HR/面试官审查及投递沟通材料生成。用于应届、社招、转行及互联网、AI、产品、运营、销售、技术、数据...
Collect the last human session, or a specific one by id, into a seed on the clipboard, so a new session continues where...
基于 Modular RAG MCP Server 项目生成定制化简历项目经历。结合项目技术亮点与用户业务场景，按简历编写原则输出高质量项目描述（中英文）。Use when user says '写简历', 'resume', '简历',...
Stream on retake.tv — the Twitch for AI agents on Base. Register to get RTMP keys and a Clanker token, then stream conte...
Evaluate and filter recall_search results for relevance
from langchain.retrievers import EnsembleRetriever
กลยุทธ์การ retrieve context ให้ AI อย่างมีประสิทธิภาพ - เลือกอะไร ไม่เลือกอะไร และจัดลำดับอย่างไร
Generate retrieval practice questions at varied difficulty levels for a topic or concept. Use when creating quiz starter...
When/what to retrieve — open the brain page for a salient entity before answering from memory.
Before any explanation or answer, require the learner to produce a free-recall attempt and confidence rating. Use when a...
CP-7 retrospective: audit checkpoints, evidence quality, action items, and harvest candidates. Closes the V-model cycle...
Run a retrospective on Codex or Claude Code sessions. Propose changes to steering files, checks, review rules, skills, t...
Enterprise post-session retrospective: writes evidence-ledger, delegates to retro-auditor subagent (isolated context), u...
Attractor-based reasoning engine. The fixed point of IN(f) exerts pull on every iteration before it. Systems with bracke...
Help return an item or request a refund from any retailer. Identifies the item, finds the return policy, navigates the p...
Where you've been is where you can go back to.
Revenue decomposition, segment breakdown, geographic revenue split, product-line waterfall, revenue mix analysis, busine...
Revenue forecasting pipeline - bottoms-up pipeline forecast, tops-down model, ensemble blending, scenario analysis, and...
Janus and reversible languages: run programs backwards, time-symmetric computation.
condition: Modelo de ML indisponível ou não carregado
Review recent conversations to find improvements for AGENTS.md files.
Creates minimal, effective AGENTS.md files using progressive disclosure. Triggers on "create agents.md", "refactor agent...
review-analyzer-skill是由buluslan（公众号：新西楼.AI）研发的电商评论深度分析Skill（VOC 客户之声分析），他会帮你把一堆产品评论变成一份能落地的决策依据——22 维 AI 打标提炼用户画像、痛点和真实需...
Captures and retrieves PR-review findings in memory palaces. Use after PR review to store architectural decisions, patte...
Review code for clean-code principles — SOLID, DRY, YAGNI, KISS, code smells. Triggers "review clean code", "check DRY/S...
Parallel specialist code review — 6 focused agents (correctness, design, performance, safety, docs, complexity) diverge...
Follow-up review to verify corrections on a MR. Sequential execution to avoid memory spikes. Checks blocking issues, det...
Review interface design for functions, classes, modules, components — naming, params, encapsulation, YAGNI, usability. T...
Analyze development-set disagreements between human annotations and one Coval text LLM judge, then propose a focused pro...
Performance analysis for algorithmic complexity, memory leaks, N+1 queries, and render issues. Use when code feels slow,...
Review a pull request with the user, then draft the review on GitHub for them to submit.
Pruefung: Internationaler Bezug und Schnittstellen im Plugin ki governance; schärft Rollen, Belege, Fachnormen, Risiken,...
Analyze AI/ML technical content (papers, articles, blog posts) and extract actionable insights filtered through enterpri...
Prüfung und Begründung der Revision in Strafsachen – Statthaftigkeit § 333 StPO, Sprungrevision § 335 StPO, Rüge der Ges...
Bring cut-off work back exactly where it stopped after a usage limit, a crash, a restart or a compaction, without doing...
Propose description rewrites to resolve skill collisions. Given a collision pair from a gardener audit, reads both skill...
Rezk types (complete Segal spaces). Local univalence: categorical isomorphisms ≃ type-theoretic identities.
Generate protein backbones using RFdiffusion, a diffusion-based generative model for de novo protein structure generatio...
Rfp Response Builder. Professional enterprise agent for Rfp Response Builder within the Sales sector.
Validate Ribo-seq data quality by checking 3-nucleotide periodicity and calculating P-site offsets. Use when assessing l...
Asks clarifying questions in multiple rounds before starting ambiguous tasks. Fires when 2+ task dimensions each have 3+...
Enable robot policies to self-improve through imagination using learned dynamics and value models without physical trial...
Risk management and constitutional compliance specialist. Ensures all trading decisions comply with constitutional limit...
Trading psychology, risk management discipline, position sizing psychology, drawdown management, behavioral bias mitigat...
Apply machine learning for construction project risk assessment. Predict schedule delays, cost overruns, and safety inci...
Design and implement reinforcement learning environments to tune bounded circuit parameters, featuring a sophisticated r...
Reinforcement learning for ion shuttling optimization on trapped-ion quantum computers
Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies...
RL training for robot control using simulation with sim-to-real transfer
Build RLAIF pairwise AI-feedback labels from label-token logits, optional chain-of-thought rationales, and swapped-order...
Train and validate tiny soft-label pairwise reward models that distill RLAIF AI preference distributions with cross-entr...
Local RAG system management with RLAMA. Create semantic knowledge bases from local documents (PDF, MD, code, etc.), quer...
Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about pr...
Autonomous RLHF feedback capture - Claude self-captures mistakes and successes
Run a Recursive Language Model-style loop for long-context tasks. Uses a persistent local Python REPL and an rlm-subcall...
Process large codebases (>100 files) using the Recursive Language Model pattern. Treats code as an external environment,...
Recursive Language Models (RLM) CLI - enables LLMs to recursively process large contexts by decomposing inputs and calli...
Parallel fan-out processing - spawn multiple sub-agents for chunked context processing
Recursive Language Model context management for processing documents exceeding context window limits. Enables Claude to...
Process large contexts using RLM (Recursive Language Model) patterns - chunking, filtering, recursive sub-calls
Spawn sub-agent to process focused context and return structured result
Run the full Recursive Language Model pipeline — prep, fan out across chunks, and recursively synthesize until results f...
A unified interface for annotating single-cell RNA-seq data using Marker Genes, Deep Learning (CellTypist), or LLMs.
---name: rna-velocity-agent
Compute Random Network Distillation novelty bonuses from frozen deterministic target features and trainable predictor me...
Use when someone wants an honest, comedic audit of their own prompting — reads their past agent transcripts, scores prom...
Parliamentary procedure as forcing function for genuine deliberation
Roc Curve Plotter - Auto-activating skill for ML Training. Triggers on: roc curve plotter, roc curve plotter Part of the...
Manage roc curve plotter operations. Auto-activating skill for ML Training. Triggers on: roc curve plotter, roc curve pl...
Role definition for code reviewer agents. Defines review criteria, feedback patterns, and approval workflows. Use to und...
会話やログからメモリ候補を抽出し、結果を workspace に保存する
Manually route a query to the optimal Claude model (Haiku/Sonnet/Opus)
Analyze project state and route user to the appropriate agent based on current context.
Cut LLM spend by routing bulk work to a cheap model and escalating only the hard turns to a premium one. Use when the us...
Assign each VDM-SL module to the lightest capable model tier (light / standard / heavy) based on objective complexity si...
Use when routing an incoming request to Simple, Standard, or Full tier. Also detects specialized command intents before...
Universal entry point that routes any query to the appropriate domain router (startup, engineering, operations) - orches...
<essentialprinciples>
Multi-agent routing, channel bindings, and tool policies
You are an email enrichment specialist. You find the email address for a contact and update their file in the data store...