the-magician
claudeSpec-Driven Development harness: skills, agents, commands, and safe hooks
4 skills · 10 commands · 5 agents · 1 MCP server · hooks
Claude Code and Codex plugins their authors filed under "Developer Tools". All categories.
Spec-Driven Development harness: skills, agents, commands, and safe hooks
4 skills · 10 commands · 5 agents · 1 MCP server · hooks
用于在 Render 上部署、调试、监控和迁移应用的技能。
21 skills
Standalone supporting plugin for build-loop's debugger bridges — extended capability (cross-project incident memory, additional assessor coverage, coordination across build-loop instances). Build-loop bundles its own debug-loop / debugging-memory / logging-tracer skills + MCP server; install this only when bundled capability isn't enough.
3 skills · 9 commands · 7 agents · 1 MCP server · hooks
Superpowers Chinese development workflows
21 skills
Connect your agent to your Plumlayer project record and the precon skills that work it: upload and index drawing sets, build one cited scope list for the job and split it into trade packages, level sub bids, and place takeoffs. Everything recorded carries its author, the time, and the sheet it came from.
9 skills · 10 agents · 1 MCP server
A guided software-delivery workflow built from Matt Pocock's skills and Superpowers worktree discipline.
19 skills · 1 agent
Developer plugin for building production integrations with Clous through the SDKs, CLI, API, remote MCP, OAuth, A2A, and webhooks.
7 skills · 6 commands · 3 agents · 3 MCP servers · hooks
Experiment-tracking skills (probe-research:probe, probe-research:track-work, probe-research:visualize-progress, probe-research:instrument-code, probe-research:plan-research-review) wired to a read-only Probe MCP server; writes via the `probe` CLI.
17 skills · 1 command · 1 MCP server · hooks
A collection of skills that I use on a day-to-day basis
20 skills
The Graph Works plugin: a path-native work-item pipeline plus a wiki scan/ingest/query/lint surface, driven through the gw CLI, alongside brainstorming, planning, TDD, debugging and delivery workflows for coding agents.
19 skills · hooks
Twenty portable agent skills for software research, planning, task handoffs, retrospectives, code and test review, verification harnesses, instruction review, bug diagnosis, dependency and privacy audits, documentation, writing, product UI design, and MAUI Blazor browser development, with four optional MCP integrations in the complete GitHub edition.
20 skills
OpenSpec workflow skills, dependency tooling, orchestration helpers, and Codex guard hooks.
19 skills · hooks
Build, govern and operate apps on Microsoft Copilot Managed Runtime (ms CLI + @microsoft/managed-apps SDK) with end-to-end best practices and anti-patterns.
17 skills · 2 agents · hooks
released
20 skills
released
20 skills
Spec-driven workflow cho Claude Code: intake → spec → plan → build (implement/QC/report). Duyệt bằng chat tự nhiên, hook nhắc bằng mã [TDQ:*] và kiểm bằng hiệu ứng thật, chế độ nhanh (express) / chuyên sâu (deep), working log bắt buộc. Một nguồn skills/ chạy trên Claude Code, Codex, OpenCode và Antigravity.
12 skills · 6 agents · hooks
Session-lifecycle skills for the test-automation-portfolio: resume, derive/loop worklists, code reviews, in-depth project reports, implementation logs, handovers, project close-out, portfolio-wide fan-outs, and a zero-config repository analyser. Each skill delegates to the canonical prompt in this repo; the project is an argument.
19 skills
Evidence-backed codebase reconstruction: architecture, features, flows, settings effects, and source-bound change maps.
1 skill · 18 agents
Spec-driven agentic development: grill the user until nothing is guessed, write the spec, plan, then execute with TDD.
18 skills · hooks
Mod almost any game you own with an AI agent: engine recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos, and a shared knowledge base of how games were modded.
14 skills · 3 agents · 1 MCP server · hooks
Deploy the app you built in one step, share it like a document, and see who used it.
18 skills · 1 MCP server
DeepStack raises a task in altitude, depth, and range, then proves the result. Principles follow Felix Rieseberg, How to be more ambitious: A tutorial for humans with models, in this plugin's own words.
17 skills · 1 agent · hooks
Skills from https://github.com/mattpocock/skills, pinned in sources.toml.
19 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
18 skills · hooks
Optimized skills library for Claude Code: proportional process, TDD, debugging, collaboration patterns
17 skills · hooks
Delegate review, diagnosis, and bounded fixes to non-Claude models (DeepSeek, GLM, Kimi, MiniMax, ...) via the OpenCode CLI.
9 skills · 7 commands · 2 agents
Plan software work in a Schematic Planner project: design canvases in specs, executable task canvases in plans, shared by you and the agent.
16 skills · 1 command · hooks
Architecture, GitHub triage, UI, database-migration and dev-tooling skills
18 skills
Internal workflows used by Cursor developers for CI, code review, shipping, control-cli, control-ui, verify-this, test reliability, code cleanup, and work summaries. Designed to work without requiring third-party service integrations. (from Cursor)
17 skills · 1 agent
Codex-native orchestration system for safe, evidence-led engineering work.
16 skills · 1 MCP server · app connector