Search Results for "doodledood" | AgentCC

research-web

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 waves when gaps are identified, then synthesizes findings. Use when asked to research, investigate, compare options, find best practices, or gather comprehensive information from the web.\n\nThoroughness: quick for factual lookups | medium for focused topics | thorough for comparisons/evaluations (waves continue while critical gaps remain) | very-thorough for comprehensive research (waves continue until satisficed). Auto-selects if not specified.

scrollytelling

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, narrative scroll experiences, or story-driven landing pages.

Consultant

Consults external AI models (100+ via LiteLLM) for complex analysis. Use for architectural reviews, security audits, deep code understanding, or whenever extended reasoning is required. Runs asynchronously with session management.

decide

Personal decision advisor that prioritizes QUALITY over speed. Uses exhaustive discovery, option finding, sequential elimination, and structured analysis. Intended for investments, purchases, career moves, and life decisions. Surfaces hidden factors, tracks eliminations with reasons, and produces confident recommendations. Triggers: "help me decide", "should I...", "which should I choose", "compare options", "what should I do", "weighing options".

ask

Single-model consultation using consultant agent. Defaults to gpt-5.2-pro.

analyze-code

Deep code analysis using a consultant agent. Identifies technical debt, risks, and improvement opportunities.

ask-council

Multi-model ensemble consultation. Runs 3 models in parallel for diverse perspectives.

prompt-engineering

Craft or update LLM prompts from first principles. Use when creating new prompts, updating existing ones, or reviewing prompt structure. Ensures prompts define WHAT and WHY, not HOW.

rewrite-history

Rewrite a branch into clean, narrative-quality commits. Creates a backup, reimplements the changes on a fresh branch, verifies the result is byte-identical to the backup, then replaces the original branch history.

define-seo-strategy

Create a comprehensive SEO_STRATEGY.md covering both traditional SEO and Generative Engine Optimization (GEO) for AI platforms. Requires CUSTOMER.md to exist first. Includes platform-specific tactics for Google AI Overviews, ChatGPT, Perplexity, Claude, and Gemini with effort/impact prioritization.

compress-prompt

Compresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action space. Use when asked to compress, condense, or minimize a prompt.

define-design-guidelines

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 layout patterns. Bakes in frontend-design skill principles to avoid generic AI aesthetics.

example

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.

rebase-on-main

Update main/master from origin, rebase current branch on it, resolve conflicts, and push.

learn-from-session

Analyze Claude Code sessions to learn what went right or wrong and suggest high-confidence improvements to skills. Use this Skill when asked to analyze a session, learn from a session, or review workflow effectiveness. It accepts a session UUID, a .jsonl session file path, or inline commentary; automatically locates and reads session files when given an ID; and creates a persistent analysis log (/tmp/session-analysis-{id-short}-{timestamp}.md). Outputs contain only high-signal recommendations that would have prevented specific rework, each tied to exact message numbers and justified by the “3/3 counterfactual” test: (1) identify the rework message(s), (2) show the skill change would have triggered before the rework, and (3) show the change would have produced correct output initially. Use cases include post-mortems, CI feedback for skill authors, repository hygiene, and training-data corrections. Core advantages are reduced rework, actionable fixes with reproducible evidence, and a clear audit trail; if a session file cannot be found, the Skill prompts the user for the path or corrected ID.

review

Production-level PR review using a consultant agent. 10-category framework focused on correctness.

Investigate Bug

Deep bug investigation using a consultant agent. Identifies root causes and suggests fixes.

explore-codebase

Find all files relevant to a query using orthogonal exploration to achieve comprehensive coverage. Returns a topic-specific overview plus a file list with line ranges. Uses parallel agents for thorough+ levels to ensure nothing is missed.

define-x-strategy

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 audience, or social media presence.

update-claude-md

Create or update CLAUDE.md with best practices - brevity, universal applicability, progressive disclosure

define-customer-profile

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 research agents and multi-choice workflow with feedback cycles.

define-brand-guidelines

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.

Optimize Prompt Token Efficiency

Iteratively optimizes prompts for token efficiency by maximizing information density — reduces verbosity, removes redundancy, and tightens phrasing while preserving semantic content. Use when asked to compress, shorten, reduce tokens, tighten, maximize density, increase information density, or make a prompt more concise.

auto-optimize-prompt

Iteratively auto-optimize a prompt until no issues remain. Uses prompt-reviewer in a loop, asks the user about ambiguities, and applies fixes via a prompt-engineering skill. Runs until converged.