Productivity plugins

Personal Knowledge Management expert for Obsidian vaults with autonomous orchestration

2 skills · 9 commands · 2 agents · hooks

Plugin voor de Nederlandse Richtlijn Digitale Systemen (NeRDS). Bevat skills voor 13 richtlijnen die richting geven aan het ontwerpen, ontwikkelen en inkopen van digitale systemen binnen de Nederlandse overheid: gebruikersbehoeften, toegankelijkheid, open source, open standaarden, cloud, veiligheid, privacy, samenwerking, integratie, data, algoritmen, inkoop en duurzaamheid.

14 skills

Search and save your work in an Obsidian vault — Flavored Markdown, Bases, Canvas, versioning, a task system, cross-agent coordination, and an auto-maintained index. Config-driven and universal.

3 skills · 8 commands · 2 agents · hooks

Autonomous PR pipeline: plan, implement, internal review, and independent external gates.

13 skills · hooks

Difficulty-based routing to tiered Haiku, Sonnet, and Opus subagents, with escalation, a read-only guard, and user overrides.

4 skills · 9 agents · hooks

Entry point /miniplan <request>: brainstorming, plans, and working skills with routed agent roles and budget hooks.

5 skills · 8 agents · hooks

Iterative product and engineering work with explicit outcomes, evidence, authorization, TDD, and bounded batch coordination.

14 skills

context-keeper — a plugin for context management and .md-based agent memory

7 skills · 5 commands · hooks

Portfolio and career skills: manage (the portfolio deck as one workflow — material, skeleton, feedback, deck, versions), material (collect handed material), fit (JD or company type), portfolio feedback, rewriting and JD tailoring, pattern analysis, mock interview, interview plan, job-application-workflow (through a 자기소개서 step via write:writer-verification), deck-builder (reference template.pptx + deck.mdx → pptx; recolors a pptx to a brand palette), resume-builder (resume-deck.mdx → the user's own .docx, PDF, page fit, final AI-trace check), and render-review (page-by-page review of a rendered deck or resume).

12 skills · hooks

ADHD-friendly AI responses: answer first, zero fluff. 🐿️

12 skills · hooks

Personal skill collection, invoked as superb:<skill>. setup installs and verifies the dependencies the others need; craft turns a vague product idea into a decision-rich CRAFT.md brief without planning or coding; pipeline drives a settled idea to a finished branch by composing the superpowers skills, with a zero-assumption question law, on-disk run state, two approval gates, a per-phase review gate no phase advances past until it closes, planned fix rounds, and dependency waves for parallel implementers; pipeline-auto is its autonomous variant, with one human gate and a three-agent confidence quorum for later decisions that escalates instead of overruling a recorded human answer; fast-pipeline is the quick variant, with one spec approval, no project tests and a final review/bug-fix loop; turbo-pipeline is the autonomous quick variant, with one batch of at most six questions and then no human gate at all, later decisions going to two independent brains whose higher confidence wins; bug-investigate finds why something is broken and stops there; bug-fix carries that same investigation from proven file:line root cause to a regression-tested fix, refusing to plan on a hypothesis.

8 skills · 5 agents

Nested Agent Doctor for multi-agent fleets. 0–100 rubric, Composio connection checks, 1Password/Bitwarden vault health, Slack/Telegram contracts, OTel/Langfuse adapters. Diagnose-and-propose only.

13 skills

Quality control for ACL/ARR papers: proofreading, citation checks, literature from ACL Anthology and arXiv, bib sync, ARR guidelines, reviews, rebuttal, camera-ready.

12 skills · hooks

MCP server for local Claude Code / Codex CLI sub-agents, plus orchestration-mode directive and tool-gate hooks.

9 skills · 1 agent · 1 MCP server · hooks

Orchestrated PM workflows with smart routing (SPEC/RESEARCH/ROADMAP/COMMUNICATE), persistent memory, evidence-based verification, and bundled PM domain expertise.

8 skills · 4 agents

A lightweight toolset for keeping a project's intent, status, and history legible across agent sessions.

9 skills · 3 agents

Productivity tools for project management, refactoring, and research

4 skills · 7 commands · 1 agent

Throw an AI dev at a problem and have it own the outcome. Five Opus agents (router, scout, worker, critic, fresh-eyes) collaborate to investigate, plan, execute, and verify — SSH into systems, spin up infra, edit code, ship features, debug deploys, get airgap bundles working. Worker self-switches between investigating, planning, executing, and verifying modes — one persistent persona, not five different ones. Bounded scout budget (25 tool calls / 5 min, doubled in --paranoid), multi-agent reflexion on stuck (N=2-3 parallel variants + judge — fixes Reflexion's degeneration-of-thought failure mode), critic and fresh-eyes both produce mandatory evidence ledgers of commands they actually ran. One checkpoint (plan approval) for side-effecting tasks, zero for pure investigation. Plan and debrief render in chat; state files exist in .crew/runs/ for resume. Production beats --yolo always. /crew:goal sets a completion condition and runs the worker→critic→fresh-eyes loop unattended — cycle after cycle until critic and fresh-eyes both return pass, or a cycle/time cap stops it — enforced by a Stop hook (goal-gate.py) that blocks the run from ending while the goal is unmet.

6 commands · 5 agents · hooks

Careful low-risk codebase cleanup across 7 focused tracks: deduplication, type consolidation, dead code removal, circular dependency untangling, type strengthening, error-handling cleanup, and deprecated/AI-slop removal. Each track inspects in parallel (read-only), writes a critical assessment, ranks proposed changes by confidence (HIGH / MEDIUM / LOW / UNCERTAIN), and auto-applies ONLY HIGH-confidence LOW-risk changes per batch — running language-appropriate type checks, tests, and lints after each. MEDIUM and LOW changes get surfaced for explicit human decision. Atomic git commits per batch so any failing check is one revert away. Anti-pattern guardrails: never merges code that just LOOKS similar; never removes dynamically-imported / config-referenced / framework-convention / generated code; never strips legitimate boundary types (JSON parses, external APIs, FFI); never silences real error boundaries; never introduces new abstractions just to break a cycle; never uses comments as the source of truth. Refuses to run on a dirty working tree. Default mode is --dry-run (assess only); --apply is opt-in with a checkpoint before changes; --auto skips the checkpoint but never the HIGH-only confidence gate.

4 commands · 8 agents

深度研究插件 - 学术研究、竞争情报、数据分析、事实核查、报告生成等研究能力。12 个代理。

12 agents

PandaDoc document-automation skills + the PandaDoc MCP connector — quotes, NDAs, approvals, invoices and contract insights, with one-click connect.

10 skills · 1 MCP server · hooks

Throw an AI dev at a problem and have it own the outcome. Five Opus agents (router, scout, worker, critic, fresh-eyes) collaborate to investigate, plan, execute, and verify — SSH into systems, spin up infra, edit code, ship features, debug deploys, get airgap bundles working. Worker self-switches between investigating, planning, executing, and verifying modes — one persistent persona, not five different ones. Bounded scout budget (25 tool calls / 5 min, doubled in --paranoid), multi-agent reflexion on stuck (N=2-3 parallel variants + judge — fixes Reflexion's degeneration-of-thought failure mode), critic and fresh-eyes both produce mandatory evidence ledgers of commands they actually ran. One checkpoint (plan approval) for side-effecting tasks, zero for pure investigation. Plan and debrief render in chat; state files exist in .crew/runs/ for resume. Production beats --yolo always. /crew:goal sets a completion condition and runs the worker→critic→fresh-eyes loop unattended — cycle after cycle until critic and fresh-eyes both return pass, or a cycle/time cap stops it — enforced by a Stop hook (goal-gate.py) that blocks the run from ending while the goal is unmet.

6 commands · 5 agents · hooks

Keeps the expensive main model on judgment work: role-tiered subagents, delegation rules, and a PreToolUse hook that denies the main agent's code edits past a per-turn file budget (subagents exempt, hook errors fail open, Bash writes caught heuristically).

4 skills · 4 commands · 3 agents · hooks

Task Lock, progress visibility, Hyperfocus research, boundary review, and audited completion for Claude Code.

8 skills · 3 agents · hooks

SWEny AI workflows — triage alerts, implement fixes, run e2e tests, create custom workflows

9 skills · 1 agent · 1 MCP server · hooks

Shoal orchestration roles, skill and policy bootstrap.

1 skill · 10 agents · hooks

Records numerical results faithfully, and distils source code and knowledge as the work proceeds — for agent-assisted computational research.

11 skills · hooks

Twelve Claude skills for the Indian stock market: a chart scanner for the Nifty 500 and F&O, a news and NSE-filings monitor, an entry timer, an exit planner, a time machine that replays 10,000 sessions, a budget manager in rupees with STT and charges, a risk gate on NSE circuit and ASM/GSM data, an order executor (paper by default; Angel One, Upstox, Groww; never without your yes), price and exit alerts, a results analyst, an insider and bulk-deal tracker, and a nightly shortlist of five swing and five intraday names with the exit list.

12 skills

Search a connected Obsidian vault and project, tag project documents, send selected content to the vault, and manage vault notes with content-preserving workflows.

12 skills

Git-native project plans and agent workflows for any repository

11 skills