doodledood/claude-code-plugins

1

scrollytelling Implements scroll-driven storytelling experiences with pinned sections, progressive reveals, and scroll-linked animat…

doodledood/claude-code-plugins

323

2

human-writing Research-backed principles for writing prose that avoids AI tells. Apply when writing articles, blog posts, emails, m…

doodledood/claude-code-plugins

51

3

optimize-prompt-token-efficiency Iteratively optimizes prompts for token efficiency by maximizing information density - reduces verbosity, removes red…

doodledood/claude-code-plugins

43

4

research-web Deep web research with parallel investigators, multi-wave exploration, and structured synthesis. Spawns multiple web-…

doodledood/claude-code-plugins

35

5

decide Personal decision advisor for QUALITY over speed. Exhaustive discovery, option finding, sequential elimination, struc…

doodledood/claude-code-plugins

31

6

define-brand-guidelines Create a BRAND_GUIDELINES.md that defines how to communicate with your customer. Requires CUSTOMER.md to exist first.…

doodledood/claude-code-plugins

24

7

define-design-guidelines Create a DESIGN_GUIDELINES.md that defines how to design UI/UX for your customer. Requires CUSTOMER.md to exist first…

doodledood/claude-code-plugins

22

8

prompt-engineering Create, update, review, or discuss an LLM prompt — system prompt, skill, or agent. State the goal, trust the model, a…

doodledood/claude-code-plugins

21

9

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

doodledood/claude-code-plugins

17

10

clean-slop Find and remove AI-generated slop (useless comments, verbose patterns, unnecessary abstractions).

doodledood/claude-code-plugins

15

11

define-seo-strategy Create a comprehensive SEO_STRATEGY.md covering both traditional SEO and Generative Engine Optimization (GEO) for AI …

doodledood/claude-code-plugins

15

12

audit-ux Audit UI/UX changes in a focus area against design guidelines for accessibility, consistency, and usability issues.

doodledood/claude-code-plugins

14

13

craft-author-voice Captures writing style/voice into AUTHOR_VOICE.md so AI can write like the user. Use when asked to match tone, write …

doodledood/claude-code-plugins

14

14

define-customer-profile Iteratively craft a CUSTOMER.md document that precisely defines your ideal customer profile (ICP). This is the founda…

doodledood/claude-code-plugins

14

15

promote-on-x Promote a product by finding high-signal posts on X and crafting value-first replies. Uses Claude in Chrome for brows…

doodledood/claude-code-plugins

14

16

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

doodledood/claude-code-plugins

14

17

rewrite-history Rewrite branch into clean, narrative-quality commits. Creates backup, reimplements on fresh branch, verifies byte-ide…

doodledood/claude-code-plugins

14

18

write Write prose that avoids AI tells through an iterative workflow. Gathers your context, writes using research-backed pr…

doodledood/claude-code-plugins

14

19

write-as-me Generate text in your voice using your AUTHOR_VOICE.md document. Provide a topic or prompt as argument.

doodledood/claude-code-plugins

14

20

address-pr-comments Triage and fix PR review comments. Reads comments, filters false positives (outdated, misread, wrong context, style p…

doodledood/claude-code-plugins

13

21

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

doodledood/claude-code-plugins

13

22

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

doodledood/claude-code-plugins

13

23

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

doodledood/claude-code-plugins

13

24

auto-optimize-prompt Iteratively auto-optimize a prompt until no issues remain. Uses prompt-reviewer in a loop, asks user for ambiguities,…

doodledood/claude-code-plugins

13

25

build-review-persona Build a personalized PR review skill by mining GitHub review history. Extracts review patterns, communication style, …

doodledood/claude-code-plugins

13

26

compress-prompt Compresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maxi…

doodledood/claude-code-plugins

13

27

consultant Consults external AI models (100+ via LiteLLM) for complex analysis. Use for architectural review, security audit, de…

doodledood/claude-code-plugins

13

28

define-x-strategy Creates personalized X/Twitter growth strategy through guided interview. Based on algorithm-derived principles (expos…

doodledood/claude-code-plugins

13

29

explore-codebase Find all files relevant to a query with orthogonal exploration for comprehensive coverage. Returns topic-specific ove…

doodledood/claude-code-plugins

13

30

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

doodledood/claude-code-plugins

13

31

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

doodledood/claude-code-plugins

13

32

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

doodledood/claude-code-plugins

13

33

define Manifest builder. Turns shared understanding into a verifiable Manifest with Deliverables, Acceptance Criteria, Globa…

doodledood/claude-code-plugins

12

34

auto End-to-end autonomous execution: figure-out → define → do, chained without manual approval gates. Use when you want t…

doodledood/claude-code-plugins

11

35

babysit-pr Author-side PR lifecycle babysitter and companion to review-pr. Use when the user wants to tend an existing GitHub PR…

doodledood/claude-code-plugins

11

36

do Manifest executor. Works through Deliverables verifying every Acceptance Criterion and Global Invariant. Use when exe…

doodledood/claude-code-plugins

11

37

figure-out Figure things out together — any topic, problem, or idea. Presses relentlessly until shared understanding is reached.…

doodledood/claude-code-plugins

11

38

pr-merge-prep Autonomously bring a PR to mergeable state. Resolves merge conflicts, fixes CI failures, addresses review comments, s…

doodledood/claude-code-plugins

11

39

tend-pr-tick Single iteration of PR tending. Reads PR state, classifies new events, routes fixes, reports status. Called by /loop …

doodledood/claude-code-plugins

11

40

learn-define-patterns Analyze recent /define sessions to extract user preference patterns and write them to CLAUDE.md. Use when you want to…

doodledood/claude-code-plugins

10

41

sync-manifest-dev Sync the manifest-dev plugins from doodledood/manifest-dev into .claude/. Clones the source, copies agents/skills/hoo…

doodledood/claude-code-plugins

10

42

tend-pr Tend a PR through review to merge-readiness.

doodledood/claude-code-plugins

10

43

done Completion marker for the /do workflow. Outputs a plain-prose summary of what was built. Called by /do after every Ac…

doodledood/claude-code-plugins

9

44

escalate Structured escalation when /do hits an unrecoverable blocker. Surfaces what was tried, why it failed, and what the us…

doodledood/claude-code-plugins

9

45

figure-out-team Drive a multi-party deliberation in a Slack channel or thread. The agent is an involved orchestrator — presses rigoro…

doodledood/claude-code-plugins

6

46

verify Spawns parallel verifiers for Global Invariants and Acceptance Criteria from a Manifest. Primary user-facing entry po…

doodledood/claude-code-plugins

5

47

learn-from-session Analyze Claude Code sessions to learn what went right/wrong and suggest high-confidence improvements to skills. Use w…

doodledood/claude-code-plugins

3

48

stop-thinking-disciplines Deactivate thinking disciplines. Use when you want to end the disciplined thinking mode activated by /figure-out or /…

doodledood/claude-code-plugins

3

49

thinking-disciplines Core thinking disciplines for rigorous collaborative reasoning. Invoked by skills that need truth-convergent thinking…

doodledood/claude-code-plugins

3

50

check-pr Read-only inspection of a single GitHub PR lifecycle — checks CI, review threads, description sync, and mergeability,…

doodledood/claude-code-plugins

2