浏览 doodledood 维护的已发布 AI 技能，比较用途与说明，并通过来源仓库了解安装方式。
已收录技能
69收录技能的仓库 Stars 合计
446仓库 Forks
0平均每个技能的仓库 Stars
6同一仓库中的多个技能可能共享 Stars，合计包含重复仓库数据。
Creates personalized X/Twitter growth strategy through guided interview. Based on algorithm-derived principles (exposure equation, phase model). Use when asked about X growth, Twitter strategy, building audienc...
Orchestrate fixing issues found by /review. Handles issue discovery, user confirmation, plan creation, and execution via /implement.
Deep web research with parallel investigators, multi-wave exploration, and structured synthesis. Spawns multiple web-researcher agents to explore different facets of a topic simultaneously, launches additional...
Analyzes the current project structure and tech stack. Use when asked to explore, understand, or summarize a project. Trigger terms: project overview, analyze codebase, what is this project.
Manifest executor. Iterates through Deliverables satisfying Acceptance Criteria, then verifies all ACs and Global Invariants pass. Use when you have a manifest from /define.
Applies user feedback to prompts with precision - incorporates feedback intent without over-fitting, maintains information density, prevents regressions. Use when asked to apply feedback, incorporate suggestion...
Iteratively optimizes prompts for precision - eliminates ambiguities, resolves conflicts, adds missing definitions. Use when asked to optimize precision, clarify, disambiguate, or make a prompt unambiguous.
Single-agent implementation: executes plans in-place without subagents. Use /implement (default) for complex features; use this for simpler tasks or when subagent overhead is unwanted.
Verify test coverage for code changes. Analyzes diff against main and reports coverage gaps.
Optimizes prompts for goal effectiveness - ensures instructions serve the stated goal, prevents missteps, improves efficiency. Use when asked to optimize a prompt for its goal, improve goal alignment, or make a...
Audit code for over-engineering, premature optimization, and cognitive complexity.
Create or update CLAUDE.md with best practices - brevity, universal applicability, progressive disclosure
Consults external AI models (100+ via LiteLLM) for complex analysis. Use for architectural review, security audit, deep code understanding, or when extended reasoning is needed. Runs async with session manageme...
Iteratively craft a CUSTOMER.md document that precisely defines your ideal customer profile (ICP). This is the foundational document from which everything else (product, features, brand) derives. Uses parallel...
Production-level PR review using consultant agent. 10-category framework focused on correctness.
Iteratively optimizes prompts for token efficiency by maximizing information density - reduces verbosity, removes redundancy, tightens phrasing while preserving semantic content. Use when asked to compress, sho...
Implements scroll-driven storytelling experiences with pinned sections, progressive reveals, and scroll-linked animations. Use when asked to build scrollytelling, scroll-driven animations, parallax effects, nar...
Create a DESIGN_GUIDELINES.md that defines how to design UI/UX for your customer. Requires CUSTOMER.md to exist first. Covers aesthetic direction, design tokens, typography, color, motion, components, and layou...
Run all code review agents in parallel (bugs, coverage, maintainability, simplicity, type-safety if typed, CLAUDE.md adherence, docs). Respects CLAUDE.md reviewer configuration.
Manifest verification runner. Spawns parallel verifiers for Global Invariants and Acceptance Criteria. Called by /do, not directly by users.
Create a BRAND_GUIDELINES.md that defines how to communicate with your customer. Requires CUSTOMER.md to exist first. Covers voice, tone, language rules, messaging framework, and copy patterns.
Rewrite branch into clean, narrative-quality commits. Creates backup, reimplements on fresh branch, verifies byte-identical, then replaces original branch history.
Personal decision advisor for QUALITY over speed. Exhaustive discovery, option finding, sequential elimination, structured analysis. Use for investments, purchases, career, life decisions. Surfaces hidden facto...
Captures writing style/voice into AUTHOR_VOICE.md so AI can write like the user. Use when asked to match tone, write like me, replicate voice, or capture writing style for content generation.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。