Workflow plugins

Portable agent skills — scan for hardcoded values, extract to config, and embed resolver scripts

2 skills

Process skills that shape how a feature gets built, starting with software-factory's four approval gates.

1 skill

Behavioral guidelines to reduce common LLM coding mistakes: Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution

1 skill

Behavioral guidelines to reduce common LLM coding mistakes: Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution

1 skill

Робочі процеси лабораторії ai-lab: експерименти, контент-пайплайн, двомовність UA/EN, публікація, GMI-аудит, тижнева ретроспектива. (7 скілів)

Review, annotate, and approve Claude Code plans in a local web UI.

反舞弊调查全流程技能包 — 调查哲学方法论、舞弊类型与调查方案、证据链与底稿管理、访谈笔录分析、写作技巧、审计技术、流程分析、结果可视化

23 skills · 13 commands · 7 agents · hooks

Code quality for Claude Code — multi-agent code review, coverage-gap analysis, and refactoring

11 skills · 25 agents · hooks

The DevStride agentic delivery loop — thirty skills covering guided repo setup, roadmap planning, dependency-ordered execution, a delivery profile that scales rigor across the prototype, standard and extended delivery profiles, adversarial review before CI, and owner-cut releases. Configured per repo via .claude/ds-config.json.

31 skills · 1 MCP server · hooks

Short-spelling alias of the devstride plugin — the same plugin, the same skills, the same version, installed under a shorter name. Canonical entry: devstride. Install one or the other, not both.

31 skills · 1 MCP server · hooks

Question → Evidence → Draft → Verify → Cite discipline for scholarly writing. Tiered session boot, deterministic hooks (citation-gate, block-fabrication, protect-sources, stop-gate, prompt-router), user-invocable skills (claim-check, citation-audit, peer-review, outline, journal-fit, response-to-reviewers), review agents (peer-reviewer, integrity-reviewer, fact-checker, outline-planner), a CLAUDE.md ruleset, reviewer-feedback memory, and field overlays.

23 skills · 5 agents · hooks

Classifies each task, routes it to the cheapest capable executor (opencode, codex, cursor-agent, agy, claude), briefs, verifies and commits.

14 skills · 13 commands · hooks

Apptension SDLC processes as skills plus bundled docs: paired human guidance and portable agent contracts for how we work.

23 skills · 1 command

Subagents, slash commands, and workflow skills for Claude Code: a planner/engineer/debugger/reviewer team plus commands for commits, branches, worktrees, and PR shepherding.

2 skills · 8 commands · 12 agents

EPCC (Explore-Plan-Code-Commit) systematic development workflow with 12 specialized agents for exploration, planning, coding, and commit phases

7 commands · 12 agents

Subagents, slash commands, and workflow skills for Claude Code: an engineer/reviewer/debugger team plus commands for commits, branches, worktrees, and PR shepherding.

3 skills · 8 commands · 6 agents

Turn PRDs into lockable, evidence-backed work packets for humans and coding agents.

8 skills · 6 agents · 1 MCP server · hooks

Builds a navigable map of a project — zones, nodes and verified edges — as a `map.json`, through an eight-agent pipeline (scan -> extract -> verify -> emit -> validate) where every stage runs in a fresh isolated context and a deterministic guardian script, not an LLM, is the sole authority on whether the result can be trusted. Use when you need a structural view of a large or unfamiliar repository that a file tree cannot give, or when a project's forgeplan artifact graph should be shown alongside its code. Not a documentation generator: an edge is either sourced from the artifact graph or proven by a grep, and an unproven one is dropped rather than shipped as noise. Full history in CHANGELOG.md.

3 skills · 4 commands · 8 agents · hooks

Complete software-development methodology for AI coding agents: TDD, systematic debugging, brainstorming, plan-driven execution, and ~50 composable skills.

15 skills · hooks

Fabius — one set of rules above every model: plan, act, verify and remember. Fifteen coordinated skills guide the work through your chosen model and a compatible agent app, using its tools and permissions. Scout wide, strike narrow.

15 skills

Installs the harness-kit pipeline (product-manager + staff-software-engineer agents, slash commands, skills, hooks, status bar) into your project via the bundled installer.

14 skills

Decide what and how to build with Claude Code — research, specs, phased plans, design exploration, and architecture review

13 skills · 1 agent

CodingOnRails workflow: setup, think, research, plan, code, test, work router, plus design, review, refactor and docs phases

13 skills

Structured multi-agent development pipeline with phased investigation, planning, implementation, and two-stage review (spec compliance + pluggable evaluators)

1 skill · 10 agents · hooks

Brownfield extraction pack — turns legacy code and documents into a structured forgeplan graph through a discover agent and twelve extraction skills (ubiquitous language, use cases, invariants, causal links, scenarios, knowledge-graph curation, reproducibility). Use when taking over an undocumented codebase and the first problem is not what to build but what is already there and why it is that way. Full history in CHANGELOG.md.

12 skills

Multi-agent harness framework for long-running application development with Claude Code

3 skills · 3 commands · 3 agents · hooks

Spec-Driven Development workflow (spec -> plan -> implement -> test -> verify -> retro) with slash commands. Depends on research-tools, code-agents and frontend-skills.

1 skill · 5 commands · 3 agents

Sets up and keeps lean the Claude Code harness of a project — root CLAUDE.md, settings.json, per-component CLAUDE.md and the project knowledge layer — for new and existing projects, including large multi-component, long-lived codebases. One setup skill with three templates, and the flow's user-invoked commands; no agents or hooks.

8 skills

Orchestrate brainstorm, planning, and execution workflows through coordinated agents and critic gates.

6 skills · 1 command · hooks

Runs one tracked task end to end on whatever issue tracker a project uses — Orchestra, Jira, Linear, GitHub Issues — through seven gated stages, and carries the Orchestra MCP reference (field model, failure modes, query recipes) as a separate skill free of this ecosystem. Use when the board should tell the truth about work in flight: picking a task that can actually be started, keeping its checklist honest while the work happens, proving each acceptance line, and reporting what was NOT done alongside what was. Full history in CHANGELOG.md.

3 skills · 2 commands · 2 agents · hooks