В каталоге 183 730 навыков в 14 категориях.
Re-run the analysis pipeline on all runs matching an RQ, reaggregate metrics, and propose findings updates against the f...
Clone a section, widget, page or animation from any reference (a live website URL, a screen recording, an mp4/mov/webm,...
React Native Reanimated 4.x animation patterns. Use when adding animations, transitions, entering/exiting effects, or ge...
React Native Reanimated animation patterns. Use when implementing animations.
REANN 势能面训练技能，基于递归原子神经网络拟合势能面。适用于：机器学习力场训练、势能面拟合、分子动力学前置模型训练与包含 REANN 标准训练包的数据任务。
Reclaim disk by deleting a PROCESSED source's heavy artifacts — the full podcast source.mp4 (re-downloadable from its sa...
Reapply local modifications after a GSD update
Imported skill rearrange from anthropic
Turn a learning, planning, assessment, or improvement request into an evidence-grounded loop of observable targets, unce...
Advanced reasoning with search strategies (beam search, MCTS). WHEN: Complex problem-solving requiring exploration of mu...
First principles reasoning and optimization methodology. Applies the Idiot Index, requirement questioning, and 5-step op...
Logical Chain-of-Thought (CoT) and cognitive planning workflows.
MANDATORY structured reasoning framework for complex analysis. Provides dependency analysis, risk assessment, hypothesis...
Generate and evaluate explanatory hypotheses from incomplete observations. Use when diagnosing anomalies, explaining une...
"Common reasoning protocol shared across all subagents."
Transfer knowledge from source domains to novel target situations through structural mapping. Use when facing new market...
Tested reasoning approaches for Claude prompts — 18 variants across 6 categories (Analytical, Strategic, Creative, Techn...
Execute evidence-based decision-making through 6-stage causal flow. Use for known processes, operational execution, and...
Stop paying for deep reasoning on easy turns by setting a modest default reasoning effort and escalating per task. Use w...
Reasoning and planning framework. Defines task analysis, risk assessment, hypothesis forming. Applied automatically for...
Structured reasoning via sequential-thinking MCP. Forces explicit step-by-step analysis before coding for complex proble...
Multi-provider reasoning/thinking configuration. Discriminated unions for OpenAI effort, Anthropic budget, Google level/...
Meta-skill that wraps reasoning skills to capture notes in real-time, protecting against context compression. Creates ch...
Overcome token-level randomness limitations in RL by shifting exploration to latent reasoning strategies. Train a VAE en...
Use this skill for rigorous theoretical derivation with supercollider mode (G1-G7 simultaneous), diffusion reasoning, an...
Template for pre-reasoning → action → post-verification model allocation
Apply semi-formal certificate reasoning to code analysis — patch verification, fault localization, patch equivalence. Us...
Persist reasoning and decisions to disk before returning. Use whenever a non-trivial method, parameter, or phase-boundar...
---
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verd...
ReasoningBank integrations that rely on AgentDB for memory and retrieval.
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvemen...
Adaptive learning for moflo agents via ReasoningBank: trajectory storage, verdict judgment, memory distillation, consoli...
Verify each generated claim against provided sources, enforce inline citations, and prune unsupported text. Use when out...
Draft and enforce system-level persona/rules for Ollama SYSTEM blocks. Use to translate role/constraints into Modelfile...
Sweep a configured pool of resolved or end-of-life `<issue-tracker>` issues and re-assess each against the current `<def...
After a slice completes, review whether the milestone roadmap still fits reality. Reads recent summaries, surfaces devia...
Read-only dashboard over a directory of `verdict.json` files produced by `issue-reassess` campaigns. Surfaces a health r...
Restore context and momentum via Pratyabhijñā (recognition)
Turn a target allocation into a concrete order list — dollar and share deltas per name, a tax tag per row, and an option...
Maintain portfolio allocations over time using calendar-based, threshold-based, and tax-efficient rebalancing strategies...
Rebase a branch onto another — resolve merge conflicts carefully by inspecting each conflict individually. Use when reba...
Start a local Git rebase when the user explicitly requests replay of a named source ref, or of the current branch, onto...
Use when the user asks to rebase the current branch onto another branch or update branch history without merging.
Rebase local changes on top of remote branch updates
Rebase the current branch with smart conflict resolution.
Execute /rebase or /rebase <branch> slash command.
Rebase a tree of dependent branches (including siblings) after upstream changes. Auto-detects downstream branches and re...
Rebase the current branch onto an updated main branch. Use when main has been updated and you need to incorporate those...
Rebase after a parent PR has been merged to main. Use when your branch was stacked on another PR that has now been merge...
Update main/master from origin, rebase current branch on it, resolve conflicts, and push.
Rebase the current branch onto main with guardrails. Manual command — run with /rebase-onto-main when the user asks to r...
Use when rebasing onto a shared/team branch someone else pushed overlapping work to, or rebasing a branch you are not on...
Rebase the current branch onto an updated parent PR branch. Use when you have stacked PRs and the parent branch has been...
Keep a feature branch current with main. Use when asked how to update or sync a branch; not for merging it into main.
Rebase a PR on its base branch, fix conflicts, and verify build
スタックした PR (下段の上に上段を積む構成) を、下段の変更に追随させて上段へ rebase 伝播し、各段を検証して push する。下段がマージされた・衝突した・リモートが消えた等の分岐を判定しながら段を上がる。ユーザーが「スタックを...
Use this skill when working with stacked diffs (Branch B based on Branch A, which is based on main).
Standard workflow for all rebase operations ('rebase branch', 'rebase on main', 'rebase onto'): replaces bash-based git...
Reboot a fleet node safely by one protocol: pre-flight (save state, finish syncing, warn peers, verify autostart is arme...
Create and verify durable control checkpoints so a Story-Film project can resume safely after a machine reboot or proces...
Rebrand the app — change the product name, logo, description, theme, and navigation. Use when porting this template into...
Applies brand customization across the entire site — colors, fonts, logos, metadata, and social images. Use when rebrand...
Plan and execute a brand transformation — from diagnosis to new brand definition to rollout. Use when the user says "reb...
品牌重塑 - 账号定位、视觉和内容的全面升级
When the user wants to plan or execute a rebrand—domain change, 301 redirects, migration, or announcement. Also use when...
Apply Nix configuration changes. Use when modifying .nix files, after flake updates, or when user asks to rebuild/apply...
Rebuild the wikilink entities cache. Triggers on "rebuild cache", "rebuild wikilink cache", "update cache", "refresh wik...
Rebuild manifest.json for any artifact storage type. Scans directories and regenerates from scratch.
Render a reverse-spec rebuild package as traced, script-checked visuals — a Mermaid ER diagram of model.md entities, cap...
Rebuild the astroray Python extension cleanly, clearing every stale .pyd shadow copy that can mask a fresh build. Use wh...
Rebuild search index for requirements repository
Rebuild a scientific poster, graphical abstract, dense one-page slide, or reference slide image as a high-fidelity edita...
Rewrite third-party skills as DME Technology originals. Use when onboarding new skills from marketplace or repos. Applie...
This skill covers how to apply configuration changes to the devbox, including full rebuilds with nixos-anywhere. Use thi...
Prepare a paper for peer review. Reads the paper and experiment results, selects the strongest ablations, anticipates re...
실제 심사평을 받은 뒤 지적을 단위로 나눠 분류하고, 원고를 고치고, 심사 대응표와 답신을 쓸 때 사용. "심사평 왔어", "리비전", "답변서", "rebuttal", "대응표", "major revision",...
Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-o...
Use when planning, drafting, revising, compressing, or auditing conference rebuttals and author responses in OpenReview...
Systematic quality check for a completed rebuttal document before submission. Use after Stage 3 document compilation or...
Use when reviewer comments arrive and each one needs a tracked decision, when a revise and resubmit letter must map ever...
Plan and write an academic rebuttal in two stages. Stage 1 triages the reviews, split them into atomic concerns, diagnos...
Imported skill recalc from anthropic
Load context from vault memory. Temporal queries (yesterday, last week, session history) use native JSONL timeline. Topi...
Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, pri...
Reconstruct and narrate the current development context from contextual commits. Run at session start, when resuming wor...
Query memory system for relevant learnings from past sessions
Search Origin's local memory by query. Targeted lookup, not orientation. Invoked as `/recall <query>`. Use when the user...
Recall source-attributed local memory before work.
Queries the vault to find or confirm information, answering with citations (path + date) and a confidence level, and say...
Harmonia recall - surface relevant past learnings for the current repo mid-session. Use ONLY when explicitly invoked as...
Deep search across all past Claude Code sessions for decisions, solutions, and discussions
This skill should be used when the user asks to "recall related knowledge", "search previous solutions", "check what we...
Recall marketing learnings. Use when: querying what we know about a channel, audience, objective, or past campaign.
Use when resuming work or reconstructing project context from workspace-scoped history.
Cross-session search combining claude-mem semantic vector search with conversation history grep for comprehensive memory...
Semantic-search personal knowledge (memory, plans, handoffs, skills, Codex rules) via the local RAG index at ~/.claude/r...
Retrieves and presents relevant memories from the database for the current project context. Queries the memories table a...
Smart graft search that picks the right tool (query → retrieve → explore) based on the question's shape, escalates when...