37,161 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Skill Codex
Clarify ambiguous ideas or implementation requests through an evidence-grounded Socratic interview and produce an execution-ready requirements specification before planning or coding. Use when the user invokes $spec-interview, asks to be interviewed, says not to assume, or provides a broad request without clear scope…
Skill Claude CodeCodex
Plan an OpenSpec change and sync it to the MCP Task Hub as tiered, chunked tasks. Use when the user wants to plan/queue work for the agent drain loop ("hub-plan", "sync tasks to the hub", "queue up this change"). Spec artifacts always come from the official OpenSpec (opsx) tooling — this skill layers reconciliation…
Skill Claude CodeCodex
Start implementing part or all of a designed software project.
Skill Codex
Turn a selected feature idea into a bounded implementation-ready feature plan grounded in existing product surfaces, contracts, and ownership boundaries. Use when the user has chosen a feature candidate and wants the MVP, user flow, reused contracts, new surface area, implementation slices, risks, and validation plan…
Skill Claude CodeCodex
Design software systems using the state machine (statechart) pattern. Use this skill whenever a user wants to model application logic, UI flows, async operations, protocols, workflows, or business processes as a state machine. Triggers include: "design a state machine", "model this as states", "create a statechart"…
Skill Claude CodeCodex
A general workflow for research, planning, implementation, and iteration; RPI is short for those four stages. It can be used by AI agents for engineering tasks on any supported platform.
Skill Claude CodeCodex
A guide for planning software work that has several steps, dependencies, or parallel tasks. It helps organise approved designs or clear requirements into connected tasks and testing or verification steps.
Skill Codex
Initialize, plan, run, inspect, and review resumable Ralph-style autonomous implementation loops with sequential chunks, persistent scratchpad memory, manifests, and idempotent post-sprint hooks. Use for .ralph orchestration or similar long-running coding-agent sprint systems.
Skill Claude CodeCodex
Automate GitHub Projects v2 planning from codebase analysis. Use when: (1) Need to create comprehensive project board with epics and user stories, (2) Converting codebase analysis into GitHub issues, (3) Bulk issue creation with labels and status synchronization, (4) Setting up kanban board with proper organization.…
Skill Codex
Explicit-invocation-only five-stage workflow for coding tasks. Use this skill only when the user explicitly invokes forge or $forge and wants a request turned into prompt.md, research.md, plan.md, implementation, review.md, and stage commits; do not trigger it from task shape alone.
Skill Claude CodeCodex
Walk through pull request review comments one at a time with the user before making or resolving changes. Uses one orchestrator agent that spawns a fresh subagent per comment with isolated context. Presents click-to-choose polls (AskQuestion) at every decision point so the user picks an approach instead of typing. Two…
Agent Claude Code
Automated Developer agent for implementing features based on PRD, architecture, and sprint plan.
Skill Claude CodeCodex
Create a narrow, auditable implementation plan with frozen acceptance slices. Use only when the user explicitly asks for this skill, an implementation plan, or a plan-first workflow before coding.
Agent Claude Code
Read-only context-gathering planner. Discovers the codebase, asks clarifying questions, proposes an implementation plan, and iterates until the user approves.
Skill Codex
Run a Gauntlet Loop on a goal: split work into independent pieces, fan out builder + fresh-context critic pairs, score each piece out of 10 against a concrete bar (reference and/or acceptance criteria), and keep looping until every critical piece is 10/10 or the user stops. Use when the user runs /gauntlet, or says…
joao-aires/agent-skills-public
Skill Claude CodeCodex
Develop, evaluate, compare, and continuously update business and product strategy from first principles. Use for startup ideas, business plans, market entry, wedge/beachhead selection, positioning, competitive analysis, economic power and value capture, market structure, customer behavior and culture, future-market…
Skill Claude CodeCodex
Orchestrate the full atelier workflow in one task window using pi teams runtime teams plus predefined agents, spawning right-side worker panes only when a phase is active and routing review loops until acceptance while preserving planner/implementer live context. Use when running…
Plugin Claude Code
Bundles 8 skills · 586 tokens together
Agent definitions and skill prompts for Claude Code covering requirement-doc planning, technical-spec planning, architecture drafting, execution planning, and end-to-end initiative planning orchestration.
fikrilal/engineering-agent-skills
Skill Claude CodeCodex
Create or revise an engineering proposal from a technical discussion and repository evidence. Use when the user asks to formalize a feature, refactor, architecture direction, platform integration, migration, or other non-trivial change before implementation. Produces a repository-specific proposal rather than filling…
Skill Claude CodeCodex
Detect when the user is asking about their attempted solution (Y) instead of their actual problem (X). Use when the user presents a specific approach, asks how to implement a particular technique, or seems stuck on a path that feels forced or indirect.
Skill Claude CodeCodex
Start from a high-level idea, and systematically turn that into a detailed product description.
scroogy-dev/scroogy-agent-skills
Skill Claude CodeCodex
A workflow for managing software issues through written specifications, task plans and completion summaries. It keeps active issues in a defined workspace structure and can resume interrupted work.
bachkukkik/opencode-plan-build-orchestrator
Skill Claude CodeCodex
End-to-end 6-phase pipeline (problem -> fix+verify -> docs sync -> knowledge graph -> commit+PR -> issue triage) alternating plan and build modes. Works harness-natively (Claude Code, Hermes, opencode TUI) or delegates to opencode CLI / Claude Code CLI / Hermes delegatetask waves. Applies karpathy-guidelines…
Skill Claude Code
Build something straight from a prompt - a short requirements interview, then implement it and run an adversarial build-and-review loop until an independent reviewer is satisfied. Use when the user wants to build a feature without writing a specification first, or mentions "/freehand".
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: