claude-code-plugins

End-to-end autonomous execution: figure-out → define → do, chained without manual approval gates. Use when you want to define and execute without intervention during planning. Triggers: auto, autonomous, end-to-end, just build it, tend pr, babysit pr.

Manifest builder. Turns shared understanding into a verifiable Manifest with Deliverables, Acceptance Criteria, Global Invariants, and Approach. Use when planning features, scoping refactors, debugging complex issues, or whenever a task needs structured thinking before coding. Triggers: define, manifest, scope, plan, spec out, break down.

Manifest executor. Works through Deliverables verifying every Acceptance Criterion and Global Invariant. Use when executing a manifest, running a plan, implementing a defined task. Triggers: do, execute, run the manifest, implement plan, run plan, execute manifest, ship the manifest.

Completion marker for the /do workflow. Outputs a plain-prose summary of what was built. Called by /do after every Acceptance Criterion and Global Invariant verifies PASS, not directly. Triggers: completion summary, manifest complete, all criteria pass, finish manifest, summarize completion, wrap up, mark done.

Structured escalation when /do hits an unrecoverable blocker. Surfaces what was tried, why it failed, and what the user can decide. Called by /do, not directly. Triggers: blocked, can't proceed, unrecoverable failure, need user decision, blocker, hit a wall, escalate, stuck.

Figure things out together — any topic, problem, or idea. Presses relentlessly until shared understanding is reached. Use when you need to understand something before acting, or when figuring it out IS the goal. Triggers: figure out, help me think through, dig deeper, press this, what is really going on, investigate, work through, why does.

Drive a multi-party deliberation in a Slack channel or thread. The agent is an involved orchestrator — presses rigorously, brings evidence, names trade-offs, surfaces disagreements, advances when answers cohere; owner-by-Slack-handle overrules. Use when the people involved can't all sit in a Claude Code chat and the deliberation has to happen where they already talk. Triggers: figure out with team, slack figure-out, team press, async deliberation, group thinking, get the team aligned.

Sync the manifest-dev plugin from doodledood/manifest-dev into .claude/ for local development. Clones or pulls the repo, copies agents/skills/hooks, and removes only previously-synced items that disappeared upstream. Other plugins in .claude/ are left alone. Use when asked to sync manifest-dev, update manifest-dev, or pull latest manifest-dev.

Craft, update, or review LLM prompts from first principles. Use when creating new prompts, updating existing ones, reviewing prompt structure, or diagnosing a failing prompt. Ensures prompts define WHAT and WHY, not HOW. Triggers: write a prompt, edit a prompt, review a prompt, improve a prompt, diagnose prompt failure, fix failing prompt, system prompt, skill, agent.

Research-backed principles for writing prose that avoids AI tells. Apply when writing articles, blog posts, emails, marketing copy, social media, or any prose content. Covers vocabulary, structure, tone, rhythm, and craft techniques that make writing feel authentically human. Not for code, commit messages, or technical documentation.

Tend a PR through review to merge-readiness. Classifies comments (bot/human, actionable/FP/uncertain), fixes issues via manifest amendment + scoped /do (or directly in babysit mode), tends CI, syncs PR description, and asks before merging. Use when a PR needs tending through review, or to babysit a PR. Triggers: tend pr, babysit pr, review loop, get this merged, tend this PR.

Single iteration of PR tending. Reads PR state, classifies new events, routes fixes, reports status. Called by /loop via /tend-pr setup. Can be invoked manually to run a single tick.

Review and analyze LLM prompts against prompt-engineering principles. Provides detailed assessment without modifying files.

Babysit a PR until merge-ready, then ask before merging. Runs pr-merge-prep on a 10-minute loop, monitors readiness (CI, reviews, conflicts), auto-stops when ready, and requires explicit user confirmation to merge. Never merges autonomously. Use when: "babysit this pr", "watch pr until ready", "keep fixing pr until mergeable".

Autonomously bring a PR to mergeable state. Resolves merge conflicts, fixes CI failures, addresses review comments, syncs PR description, and requests re-review. Designed for unattended cron execution via loop skill. Use when: "prep pr for merge", "make pr mergeable", "fix pr blockers", "autonomous pr maintenance".

Promote a product by finding high-signal posts on X and crafting value-first replies. Uses Claude in Chrome for browser interaction and writing plugin for human-quality prose. Triggers: promote on twitter, promote on x, post replies on x, social media promotion.

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

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.

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.

Write prose that avoids AI tells through an iterative workflow. Gathers your context, writes using research-backed principles, reviews via writing-reviewer agent, auto-fixes HIGH+ issues, loops until clean. Use for articles, blog posts, emails, marketing copy, social media. Triggers: write content, draft article, write blog post, write email, write copy.

Build a personalized PR review skill by mining GitHub review history. Extracts review patterns, communication style, priorities, and blind spots — generates a calibrated review-as-me skill that posts inline comments on PRs. Use for onboarding, cloning review style, or creating a reviewer persona.

Triage and fix PR review comments. Reads comments, filters false positives (outdated, misread, wrong context, style preference), validates relevance against current diff, and fixes valid ones with confirmation. Use when: "fix pr comments", "address review feedback", "handle pr feedback".

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

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, shorten, reduce tokens, tighten, maximize density, increase information density, or make a prompt more concise.

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

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 management.

Deep bug investigation using consultant agent. Identifies root causes and fix suggestions.

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

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.

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.

Rewrite branch into clean, narrative-quality commits. Creates backup, reimplements on fresh branch, verifies byte-identical, then replaces original branch history.

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.

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.

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.

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

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

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

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.

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.

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.