brat-architecture
1201Skill Claude CodeCodex
Architecture phase skill. Input: product requirements + current arch KB. Output: architecture design as zkb notes.
23,779 tagged Planning, measured the same way as everything else here.
Browse within: agentic-ai 204LLM 118agent 115skills 98ai-coding 89claude-code-plugin 84cli 83agents 79agent-orchestration 73context-engineering 72spec-driven-development 71academic-research 68agentic-workflow 66workflow 60
Skill Claude CodeCodex
Architecture phase skill. Input: product requirements + current arch KB. Output: architecture design as zkb notes.
bhuiyanmobasshir94/claude-standing-orders
Skill Claude Code
Set up the current repository for the orchestrator-worker workflow - project CLAUDE.md, path-scoped rules, continuity directories, and permission settings - by reading the codebase first and proposing a plan before writing anything.
Skill Claude CodeCodex
Turn an idea — or a half-planned project already underway — into a buildable blueprint, by interviewing the user one question at a time until the unknowns run out, then harvesting and verifying real open-source components for each part. Use this whenever someone describes something they want to build but has not…
chuanzige/claude-code-main-skills
Skill Codex
Use when coordinating multi-step work across workers or subagents, especially when research, implementation, and verification should be split while the main agent stays responsible for synthesis and user communication.
Skill Claude Code
Full development workflow orchestrator: brainstorm → plan → worktree → convergent TDD/review loop → verify → PR. One human gate (spec approval); all other gates auto-proceed. Use when starting a feature or significant change from scratch. Usage: /mx-flow ; /mx-flow status [name]; /mx-flow finish .
flyingsquirrel0419/squirrel-skill
Skill Claude CodeCodex
Full-cycle software development agent: plans, builds, tests, lints, fixes bugs, and writes production-grade README docs. ALWAYS use this skill when the user wants to: build or scaffold a new project, add features to existing code, fix bugs, improve code quality (lint, format, refactor), write or improve a README, add…
shauryagangrade/intent-drift-skill
Skill Claude CodeCodex
Detects intent drift in AI-assisted development by comparing the original goal against the current plan and execution context. Run /intent-drift to evaluate whether ongoing work has drifted from what was asked. Triggers on "check intent drift", "are we still on track", "is this aligned with the goal", "did the plan…
Skill Claude Code
Convert a plan file into actionable tk tickets with dependencies. Researches the codebase to vet the plan, decomposes into tickets, verifies the decomposition, and creates tickets in tk.
Skill Claude Code
Read-only verification that cross-checks intent-tree, intent-compass, and packets (+ the export draft) and reports contradictions, coverage gaps, boundary inconsistencies, and normative violations with severity. Fixes remain proposals.
Skill Claude Code
Operate the Atelier software factory (the ADW engine stamped into this repo's adws/). Use when the user says /atelier, wants to create / run / update an ADW or workflow, manage the agent roster in sssf.config.yaml, keep the engine current, or observe running agent workflows. Keywords - atelier, software factory, ADW…
dewtech-technologies/dare-method
Skill Claude CodeCodex
Gera um Task List estruturado a partir do Design aprovado. Use quando o usuário aprovar o DESIGN.md. Cria um documento BLUEPRINT.md com arquitetura, endpoints, modelo de dados e plano de execução.
Skill Claude CodeCodex
Use when starting a new project (Skill/MCP/WebApp/CLI/Library/APP) that is novel to this ecosystem — first-time domain, upstream dependency, or deep research needed. Use when user says "OODC" / "oodc mode" / "full research first" / "research first" / "deep research" / "observe orient decide create". Complements…
guixiang123124/openclaw-harness
Skill Claude Code
Turn your OpenClaw agent into a structured engineering factory. Plan → Build (via ACP) → Review → Iterate → Ship. DeerFlow's orchestration intelligence + OpenClaw's zero-config ecosystem.
Skill Claude Code
Plan a feature, refactor or migration as a reviewable, versioned artifact the user annotates line by line before any code is written, instead of a plan that scrolls away in chat. Also revises or executes a plan they already have, or answers a question about how PlanX itself works from its wiki. Use for /planx, when…
Skill Claude Code needs its repo
A workflow guide for taking a coding task from an initial request to a checked delivery. It decides whether the task needs to be formally tracked, which stage it is in, and when it is complete or blocked.
Skill Claude Code
Spec-driven project iteration workflow — L1 PRD → L2 Design → L3 Impl → Agent Task → Deploy, with human review gates at each layer. Pure local markdown storage, no MCP, no network. Use when the user invokes /spec-manager or asks for: new feature/PRD, technical design, implementation spec, agent task, iteration plan…
mseatingtpe/dev-diagnosis-skill
Skill Claude CodeCodex
A development-triage and governance guide for deciding how a software request should be handled. It helps assess whether a task needs manual work, a script, an AI tool, or an automated agent.
vdor369/elite-strategic-research
Skill Claude Code
Activates a 7-layer elite research engine combining McKinsey hypothesis-driven logic, BCG strategic portfolio thinking, IBISWorld quantitative rigor, Harvard decisional judgment, Stanford human-centered design, MIT antidisciplinary exploration, and PRISMA 2020 evidence traceability. Produces certified, traceable, and…
theflixerbox77/ralph-wiggum-codex
Skill Codex
Use when a coding task needs an objective-first long-running loop with fresh-context work and review phases, explicit acceptance criteria, resumable state, and real blocked handling.
Skill Claude CodeCodex
Use when working in a coding project owned by a non-coder - when the project root contains CODESPLAIN.md, when the user invokes /codesplain (to bootstrap a project or ask a question), when a consequential technical decision comes up during building, or when explaining a bug or fix to the owner in plain language.
Skill Claude Code
Create a construction plan for a multi-step engineering task that requires multiple PRs or a phased approach. Produces a self-contained plan file with dependency graph, review gates, and step-by-step execution instructions for coding agents. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex task…
Skill Codex
Turn a contested question, research brief, technical choice, or high-impact decision into a source-grounded interactive evidence map. Use when an agent must preserve support, contradiction, qualification, and missing evidence; make every evidence edge traceable to a dated source region; pressure-test a conclusion; or…
Skill Claude Code
Hierarchical persistent planning for complex multi-phase development tasks. Use when the user requests tasks involving multi-file modifications, architecture refactoring, system design, or any work requiring detailed planning (tasks exceeding 5 tool calls). Creates a hierarchical plan directory structure: overview.md…
Hades-HY-LI/ai-native-founder-playbook-skills
Skill Codex
Validate an AI-native startup idea before building. Use when a founder has a problem hypothesis, customer segment, early market thesis, or product idea and needs customer discovery, opportunity filtering, wedge selection, market mapping, risk identification, or an evidence plan before starting an MVP.
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: