spec-creator
claudeCreating or amending specifications for software projects or features
3 skills
Claude Code and Codex plugins their authors filed under "development". All categories.
Creating or amending specifications for software projects or features
3 skills
Multi-language project setup plugin. Sets up code conventions, dependencies, CLAUDE.md, and installs a language-specific convention skill into the target project.
1 skill · 2 commands
Luna-first orchestration with a local Rust control plane, durable runs, and an MCP Apps workbench.
2 skills · 1 MCP server
Automatic discovery of skills, plugins, and MCP servers across 19 sources
1 skill · 1 command · 1 MCP server
Plan reasoning — surface decisions, tradeoffs, and assumptions as scannable abstracts
1 skill · 1 MCP server · hooks
WiFi ADB deployment, OSS license inventory, and OpenAPI specification update skills
3 skills
Three-phase GitHub PR pipeline: script-first review with structured findings, automated preparation with CI gates, and deterministic squash merge with co-author trailers
3 skills
Curated MINION engineering discipline, precise technical writing, and advisory-only deterministic prose auditing
3 skills
Ensure modern pythonic development with source-authoring standards, single-file script discipline, and modern uv, ruff and ty project tooling.
3 skills
Tracks the pull requests a session opens and tells it when their checks or reviews change, through the pr-tracker CLI
2 skills · hooks
Development kit for working with the Claude Agent SDK
1 command · 2 agents
Manage a Keeper MSP tenant using Keeper Commander CLI (keeper): managed companies, licenses and add-ons, MSP billing reports, switch-to-mc context switching, and distributor operations.
1 skill · 1 command · 1 MCP server
Manage stacked branches and pull requests with git config metadata, Deno helper scripts, and the gh CLI.
3 skills
Sprint-drain — auto-alternate agile-10-implement and agile-11-merge-train to a fixed point, with an actionable-work guard. Requires agile-execution + agile-merge-review. Needs gh + Atlassian MCP.
1 skill · 2 agents
Generate modular dungeon rooms, assemble levels, apply lighting, and bake NavMesh from natural language
3 skills
Generate production-quality C# MonoBehaviours, ScriptableObjects, and systems from natural language
3 skills
v1.2.0 | 사용자 prompt 원문 전체(자동 마스킹 후) + 도구 호출 통계를 동의한 프로젝트에서만 jsonl로 누적(멀티세션 격리·병렬 락·flush dead-letter). /project-init 통합 동의, /del_prompt_log 로 로그 이동·동의 재확인.
1 skill · 1 command · hooks
A reviewer that assumes your code is wrong, in a context window that never saw you write it. Split-context review modelled on Bun's Zig-to-Rust rewrite.
1 skill · 1 agent · hooks
Dioxus 0.7 expert: local docs, example and source search, Serena MCP for Rust symbols, and a dioxus-expert subagent that cites its sources.
1 skill · 1 agent · 1 MCP server
Implement a spec-planner plan — build each task in an isolated jj/git workspace, gate it through a semi-formal correctness review and a definition-of-done validation, then merge. Self-contained (workspace isolation vendored); parallel by default (max 4 agents) or sequential. Consumes a spec-planner plan folder; produces merged, reviewed, validated code.
3 skills
LLM/AIエージェントを含むシステムの設計。エージェント構成、ツール・コンテキスト設計、RAG、ガードレール、人間の介在点設計(承認ゲート・監査)
3 skills
受託開発の法規制コンプライアンス。個人情報保護法の実務、OSSライセンス監査(SBOM)、生成AI利用の権利処理。法的助言ではなく実務の型
3 skills
Graft code context graph for OpenClaude — 6 MCP tools (graft_find_code, graft_find_all, graft_trace_calls, graft_file_api, graft_repo_map, graft_check_freshness) + auto hooks that inject graph context into prompts, rebuild after edits, track token savings. Requires npm install -g @nanonets/graft.
1 skill · 1 MCP server · hooks
Multi-source journal research MCP (Scopus, arXiv, OpenAlex, Semantic Scholar, Crossref, DBLP, Unpaywall) with unified dedup.
2 skills · 1 MCP server
AI-powered video editing assistant using Gemini + DaVinci Resolve. Analyzes footage, plans edits, and builds timelines automatically.
2 skills · 1 MCP server
Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask review/看看代码/合并前/看看issue/PR/release/push or to implement an approved plan, with safety gates for dirty and untracked worktrees. Not for exploring ideas, debugging root causes, or prose review.
1 skill · 2 agents
Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask review/看看代码/合并前/看看issue/PR/release/push or to implement an approved plan, with safety gates for dirty and untracked worktrees. Not for exploring ideas, debugging root causes, or prose review.
1 skill · 2 agents
Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask review/看看代码/合并前/看看issue/PR/release/push or to implement an approved plan, with safety gates for dirty and untracked worktrees. Not for exploring ideas, debugging root causes, or prose review.
1 skill · 2 agents
Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask review/看看代码/合并前/看看issue/PR/release/push or to implement an approved plan, with safety gates for dirty and untracked worktrees. Not for exploring ideas, debugging root causes, or prose review.
1 skill · 2 agents
Six-step frontend behavior work: a 7-axis spec, a Bend proof, generated fast-check conformance tests, RED, GREEN and one review.
2 skills · hooks