Agent Claude Code
Executes an existing plan step-by-step on a dedicated git branch with fast per-step ralph loops and a deep final ralph loop (automated checks + self-review + adversarial testing). Maintains a timestamped journal with commit hashes and loop results.
Skill Claude Code
Defines conventions for building AI agents with the Laravel AI SDK and Ollama. Activates when creating or modifying agent classes in app/Ai/Agents/, working with AgentResolver routing, agent testing with ::fake()/::assertPrompted(), streaming SSE responses, conversation memory, or when the user mentions AI agent…
Skill Claude Code
Lightweight bug fix handler. Creates a bug document with Five Whys root cause analysis, fixes the issue, writes regression tests, and creates a PR. Activates when the user says "bugfix", "fix this bug", "something is broken", or reports a defect that needs a quick fix.
Skill Claude Code
Guides when and how to update domain skills, documentation files, and agents after code changes. Activates when the doc-sync-hint hook flags related skills/docs, when directly editing skill, doc, or agent files, or when the user requests documentation updates.
Skill Claude Code
Execute an existing plan step-by-step on a dedicated git branch, with fast ralph loops per step and a deep final ralph loop that includes self-review and adversarial testing. Writes a timestamped journal with commit hashes and loop results. Supports both new multi-file story format (plan.md + design.md + prd.md) and…
Skill Claude Code
Discover, catalog, and manage application features in docs/features/. Use when the user wants to map out what their application does, add a new feature to the catalog, review existing features, or understand the feature landscape before planning work. Auto-invoke when the user says "what features do we have", "add a…
Skill Claude Code
Handles PR review feedback cycles. Reads PR comments, creates feedback.md as an immutable review record, applies fixes, and updates the PR. Activates when the user says "feedback", "PR feedback", "address review comments", "handle review", or has PR feedback to process.
Skill Claude Code
Interactive planner that walks through a 7-phase discovery process producing altitude-layered documents: brief.md (WHY), prd.md (WHAT), design.md (HOW), plan.md (WHEN/ORDER). Supports subcommands for individual layers and GitHub sub-issue creation. Plans are scoped to a feature and saved in story directories.…
Skill Claude Code
DEPRECATED: Use /research context instead. This skill is kept for backward compatibility only. Activates ONLY when the user explicitly says "/research-brief". For all other research triggers, use the /research skill.
Skill Claude Code
Research and discovery skill with three modes: story mode (creates story directory, writes brief.md with RICE scoring, creates GitHub ticket), context mode (scans codebase, produces research brief for external AI tools), and spike mode (creates time-boxed investigation document). Activates when the user says "research…
Skill Claude Code
Builds production-grade Claude Code skills through interactive discovery. Guides through qualifying the idea, scoping, designing architecture, writing SKILL.md and supporting files, and integrating with boost.json and hooks. Activates when the user wants to create a new skill, says "build a skill", "new skill"…
Skill Claude Code
Manages XML sitemap generation, URL prioritization, and search engine submission. Activates when working with sitemaps, sitemap indexes, URL priority, changefreq, lastmod timestamps, search engine ping, robots.txt sitemap directives, or when the user mentions sitemap, crawl budget, or search indexing.
Skill Claude Code
Interactive workflow for generating type-safe API client classes that integrate with the external API infrastructure. Guides through API discovery, endpoint mapping, response typing, error handling, and rate limit configuration. Activates when the user wants to add a new API integration, says "new API client"…
MCP server Claude CodeCodexCursor +2
Adds a structured step-by-step reasoning tool the agent can call to break a problem into revisable thoughts. Runs locally from the @modelcontextprotocol/server-sequential-thinking npm package.
Skill Codex
Plan software changes and create or revise a BRD for planning, requirements discovery, or implementation-plan revisions, excluding direct implementation, routine debugging, code review, and plans mentioned only as context.
Skill Codex
Implement or resume an agreed software plan or BRD, verify acceptance criteria, and maintain an execution journal, excluding ordinary coding without an existing plan and requests only to draft or review a plan.
Skill Codex
Design, build, refine, or critique web interfaces when layout, visual hierarchy, responsive behavior, or interaction design needs judgment, excluding purely functional fixes, backend work, and tests without a design change.
Skill Codex
Investigate focused technical uncertainty before implementation through repository evidence, authoritative sources, and bounded experiments for feasibility or option decisions, excluding general factual questions, bug fixes, full implementation planning, and research-memory management.
Skill Codex
Review delivered work against an existing plan or BRD for acceptance coverage, regressions, and completion claims, excluding plan-only critiques, ordinary code reviews without a plan, and implementation requests.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: