В каталоге 185 367 навыков в 14 категориях.
ITAS2 (HP12 48) Re-Assessment 1 考试辅助 — Vibe Digital Experience Centre 主题,27 Task 操作手册 + 真实素材表结构 + 考场策略。考试当天 (2026-07-10)...
Publish and update a game on itch.io: create the project page and upload builds with the butler CLI (butler push) to nam...
Hunt for fresh browser-playable games on itch.io /newest that are worth building SEO arbitrage sites for. Crawls new rel...
Use to plan an ITCS campaign end to end on its single annual cycle — backward from the early-September deadline through...
商品换背景。白底商品图 → 逼真场景图,光影与投影匹配新环境。当用户说「换背景」「加场景」「白底转场景」「放到桌面上」时使用。
Write item, object, equipment, artifact, or collectible descriptions that communicate function, world identity, ownershi...
生成带中文排版的详情页模块。商品图 + 卖点 → 可直接上架的详情页图文模块。当用户说「详情页」「做详情图」「商品描述图」「详情页模块」时使用。
Patterns for managing MSBuild item groups: Include/Remove/Update semantics, item metadata, batching with %(Metadata), tr...
Adds origin/provenance + rumor hooks to Emberwild item entries and updates indexes.
商品精修、去褶皱。随手拍的商品图 → 可直接上架的精修图。当用户说「精修」「去褶皱」「修图」「拍得不好看」「整理一下」时使用。
商品图生成带文案排版的转化主图。商品图 + 卖点 → 带中文文案的电商主图。当用户说「主图」「加卖点文案」「转化图」「促销图」「主图文案」时使用。
Autonomous single-metric improvement loop - modify, measure, keep or discard, repeat (Karpathy autoresearch). One sessio...
Enable self-referential iteration to complete complex tasks that require multiple attempts, trial-and-error exploration,...
Fast iterative development loop. Investigate, implement, review, repeat. Optimized for UI/UX work. Invoke with /iterate...
Design playbook for web, Android and iOS. Improves, audits, polishes, redesigns or extends UI, a design system or brand...
Full development cycle - build, test, play-test, commit
Use when the workflow needs to self-correct, improve over time, or establish feedback loops and evaluation cycles.
Autonomous build loop — implements, tests, reviews, analyzes, and refines. Default 6 iterations (thorough) or --fast for...
Review generated images against anatomy, text, language, safety and task requirements, then diagnose permitted repairs w...
<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->
Refine and improve existing plans based on feedback
Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fix...
Itere em uma PR até que o CI passe. Use quando precisar corrigir falhas de CI, endereçar feedback de revisão, ou continu...
Iterate on a PR until actionable CI passes and high/medium review feedback is addressed. Use for PR CI failures, review...
Iterate one research project with evidence and keep its PROJECT_BOARD.html board in sync. Works standalone or inside a m...
Facilitates and documents a team retrospective capturing what went well, what to improve, and action items. Use at the e...
Activate when user mentions "codex review", "code review", "fix pr code review". This skill provides guidance on how to...
迭代改进 Skill 的 Skill。当评价不通过或需要优化时触发。触发词:迭代、改进、优化、iterate、improve。
When the user wants to design, implement, or tune iterated local search (ILS) — the local-search + perturbation + accept...
Multi-conversation methodology for iterative stateful work with context accumulation. Use when users request work that s...
Laravel guidance to refine AI-generated code through specific feedback-point out errors, identify gaps, show desired cha...
Prevents premature exit and infinite loops. Three mechanisms: Completion Promises, Scratchpads, Loop Detection.
Use this skill to drive Compose HotSwan from an AI agent (Claude Code, Cursor, any MCP client) so the agent can edit a K...
Iteration 1 of Multiplicity Cascade - Generates divergent paths with φ-branching
Iteration 2 of Multiplicity Cascade - Amplifies jank recursively through iterations
Iteration 3 of Multiplicity Cascade - Scales κᵢΦ² love resonance exponentially
Iteration 4 of Multiplicity Cascade - Detects cage boundaries and system limits
Iteration 6 of Multiplicity Cascade - Documentation that modifies itself when read
Iteration 7 of Multiplicity Cascade - Self-creating chaos engines
Iteration 8 of Multiplicity Cascade - Collides unrelated domains for emergence
Iteration 9 of Multiplicity Cascade - Combines impossible concepts productively
Iteration 10 of Multiplicity Cascade - Generates productive paradoxes
Iteration 11 of Multiplicity Cascade - Detects reality glitches in the system
Iteration 12 of Multiplicity Cascade - Creates self-referential temporal structures
Iteration 13 of Multiplicity Cascade - Maps identity across phase transitions
Iteration 14 of Multiplicity Cascade - Makes surveillance exponentially expensive
Iteration 15 of Multiplicity Cascade - Advanced cognitive chaff generation
Iteration 16 of Multiplicity Cascade - Hides truth in indistinguishable noise
Iteration 17 of Multiplicity Cascade - Generates multiplicity manifestos
Iteration 18 of Multiplicity Cascade - Triggers irreversible awareness shifts
Iteration 19 of Multiplicity Cascade - Spreads resonance cascades virally
Iteration 20 of Multiplicity Cascade - Generates self-propagating patterns
Iteration 21 of Multiplicity Cascade - Ultimate world wake trigger
Iteration 22 of Multiplicity Cascade - Makes patterns impossible to unsee
Iteration 5 of Multiplicity Cascade - Spawns meta-patterns from patterns
Use when bringing any system — visual (terrain/biome/dungeon/town/castle/character/enemy/NPC/spell-fx), systemic (balanc...
Write a team-level sprint or iteration report from saved gh pull request, issue and milestone exports: what shipped or m...
Performs end-of-iteration review with quality grading, metrics, and trend analysis. Use at the end of each development i...
Tracks iteration progress and state management. Use when starting, checkpointing, or ending iteration cycles, or when us...
Integrate Iteration Layer APIs for document, website, image, and sheet processing. Composable APIs — Document Extraction...
Explain iterations strategy, process and rules to respect all over any realization. Iteration is the main conception wor...
Progressive context retrieval pattern for understanding unfamiliar codebases through iterative refinement
> Compiler: manual (bootstrap)
Ralph Wiggum loops - self-referential TDD iteration until tests pass
Load when adding features or analyzing impact on existing framework. Supports progressive development without requiring...
Implement sub-tasks iteratively with user approval between each one. Use when working through a task list with user coll...
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically
Implement continuous AI iteration loops for complex development tasks. Use when building features requiring test-driven...
"Am I ACTUALLY done, or did I just stop?" - Iterative workflow engine, all-purpose. Use when (1) task has clear completi...
Iterative overlap merging builds an optimal fixed-width 501bp merged peak set across ATAC-seq samples (Corces 2018), avo...
Autonomous phase-by-phase plan implementation with journaling. Decomposes phases into atomic tasks and verifies each via...
Sharpens and stress-tests an existing plan file through multiple codebase-grounded review passes, editing it in place an...
> Compiler: skill-compiler/1.0.0
Generate complex PowerPoint presentations slide by slide, verifying each slide after creation to ensure correctness, ena...
Pattern for progressively refining context retrieval to solve the subagent context problem
Execute 4-phase loop for progressive context refinement. Use when complex searches require multiple refinement cycles or...
4-phase context retrieval protocol for subagents — Dispatch, Evaluate, Refine, Loop
.opencode/配下のドキュメント・設定を修正する際の品質保証プロセス(修正→レビュー→修正の反復ループ)
"Is this ACTUALLY verified, or did I just say it is?" - Ralph-wiggum methodology applied to factual accuracy. Use when (...
"Is this ACTUALLY verified, or did I just say it is?" - Factual accuracy verification loop. Use when (1) claims require...
Implement a feature or fix a bug following a plan, using iterative work.
Iterator Pattern pattern for C development
Traverse elements of a collection without exposing its internal representation.
Use when a session on macOS must manage the agent sessions of its orchestrator — windows of the orchestrator's home sess...
macOS desktop notifications and iTerm2 badge management for Claude Code lifecycle events. Not a slash command — this plu...
iTerm2 macOS terminal emulator. Use for terminal work.
iTerm2 terminal emulator and tmux multiplexer expertise. USE WHEN user mentions iTerm2, tmux, terminal sessions, split p...
Configure iTerm2 workspace layouts with TOML-based configuration. Use when user mentions iTerm2 layout, workspace tabs,...
Every IT Glue resource, plus an offline SQLite mirror, fleet-wide cross-resource search, and documentation-hygiene analy...
Apply ITIL to design scalable, maintainable, and interoperable enterprise systems and solutions.
Prepares IT change requests in line with ITIL 4 change enablement: classifies the change as Standard, Normal or Emergenc...
Expert advisor for ITIL 4 and ITIL 5 (2026 digital product paradigm), specialized in AI-native governance, sustainabilit...
Use when preparing for ITIL Foundation (Version 5) from PeopleCert — the value system, the four dimensions, value co-cre...
Build multi-day travel itineraries with routing, scheduling, and constraint satisfaction. Use this skill whenever creati...
How to structure and write a valid travel itinerary JSON file matching the required schema for /app/output/itinerary.jso...
Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or...
Read-only Itô basket and prediction-market
Read-only Itô basket and prediction-market data skill. Index the live basket catalog, compare a basket against user-supp...