Claude Code and Codex plugins their authors filed under "productivity". All categories.
Script-free skills for the software development lifecycle: each one a terse description of one process, done the way we want it done. Portable to any harness and any repo; sdlc links them in and adds the deterministic tail.
21 skills
16 Claude Code skills for dev workflows, CI/CD, Kubernetes, browser automation, skill authoring, and AI-assisted development
16 skills · 4 commands
Persistent memory for AI coding agents — Context As Infrastructure
10 skills · 10 agents
A fully agentic portfolio workflow with state-aware routing, evidence-grounded copy, responsive RTL design, deterministic builds, independent QA and approval-gated publishing.
9 skills · 10 agents · hooks
Persistent project context, auto-generated test harness, and disciplined development workflows for Claude Code.
2 skills · 13 commands · 4 agents
[code] Worklode for coding agents: /lode:* commands to claim tasks into worktrees, hand them off for review, and plan and consolidate specs. The README lists every command.
18 skills · 1 agent
Chief of Staff agent — personal productivity orchestrator that routes to task backends (OmniFocus, Asana), coordinates cross-tool workflows, and learns patterns across the full tool stack.
4 skills · 13 commands · 1 agent · hooks
Multi-agent orchestration: 9 subagents, /ulw /team /hyperplan, interview-driven planning, and an adversarial review gate. The always-on core needs no external service; graph, orchestration and dashboard are separate profiles that are off by default. Registers one UserPromptSubmit hook whose injection is gated off by default (omz.keyword_hook) — see the README before enabling it.
4 skills · 5 commands · 9 agents · hooks
Twelve filmmaker personas — directors, writers, and craft specialists for scene breakdown, shot design, and film-craft work.
7 skills · 12 agents
Cloud.ru MLSpace: training jobs, inference, notebooks, data transfer, registry and compute catalog — an MCP server plus skills.
18 skills · 1 MCP server
Persona skills for Claude Code — shakespeare, pirate, gen-alpha, toronto-mans, ontario-bud. Change register without changing behavior.
5 skills · 6 commands · 6 agents · hooks
Berlin flat hunter — searches Kleinanzeigen and ImmoScout24 for rentals, detects scams, ranks listings by fit score, tracks the application pipeline, and prepares application dossiers and messages.
8 skills · 7 commands · 3 agents
Professional copywriting skills library for Claude Code: persuasion frameworks, domain patterns, and anti-slop quality enforcement across marketing, email, UX, editorial, brand, sales, social, and conversion copy
15 skills · 3 commands
Search indexes, verify claims against sources, and produce evidence-backed research documents.
18 skills
Product management toolkit: PRDs, user stories, backlog prioritization, usability tests and design critiques, with Office document skills, Coda/Google Drive/Dimensions search, and a product-manager agent and output style.
9 skills · 8 commands · 1 agent
Skills for the end-to-end ML lifecycle: target review, dataset audits, baselines, experiment planning, training supervision, failure diagnosis, evaluation, explainability, and Go/No-Go gating
18 skills
A sibling of graph for requests too big for one pass: a TaskManager MCP (teams) sizes the request; size L is planned into a PRD and user stories, split into packages that each run the full harness in their own worktree, integrated, QA'd and gated by a background daemon; size S is handed to the development harness. Entry skills teams:orchestrate/develop/document/plan/qa/sprint, board and ticket views (tm_board, teams:board). Runs are kept under .teams_output/ and ~/.harness/tasks/. Zero runtime dependencies beyond Node 18+.
15 skills · 1 MCP server · hooks
Stops Claude from racing on ad-hoc work. Methodical-mode pre-response checklist injected every turn (Restate, Verified/Unverified assumptions, Read Floor, Approach Deliberation, Blast Radius, Stall Check, Competing Hypotheses, Goal-Driven Execution). Stop hook enforces four gates: file:line citation verifier, uncertainty-tell scanner, zero-tool-call grounding audit, and an iterative two-tier critic-dialog (Haiku fast-critic rounds 1-2, opus pre-stop-critic rounds 3-5, HARD block at round 5 until /adhoc:trust-me bypass). Each critic runs a 10-item rule compliance audit and sees the prior round's feedback to verify Claude actually addressed flagged issues. /adhoc:casual (one turn skip), /adhoc:trust-me (one-turn strict bypass), /adhoc:off (session disable). /adhoc:deep for heavier analysis, /adhoc:second-opinion for independent critique.
1 skill · 12 commands · 3 agents · hooks
Proactive content generation with human voice and AI slop prevention for Claude Code
11 skills · 6 commands
Stops Claude from racing on ad-hoc work. Methodical-mode pre-response checklist injected every turn (Restate, Verified/Unverified assumptions, Read Floor, Approach Deliberation, Blast Radius, Stall Check, Competing Hypotheses, Goal-Driven Execution). Stop hook enforces four gates: file:line citation verifier, uncertainty-tell scanner, zero-tool-call grounding audit, and an iterative two-tier critic-dialog (Haiku fast-critic rounds 1-2, opus pre-stop-critic rounds 3-5, HARD block at round 5 until /adhoc:trust-me bypass). Each critic runs a 10-item rule compliance audit and sees the prior round's feedback to verify Claude actually addressed flagged issues. /adhoc:casual (one turn skip), /adhoc:trust-me (one-turn strict bypass), /adhoc:off (session disable). /adhoc:deep for heavier analysis, /adhoc:second-opinion for independent critique.
1 skill · 12 commands · 3 agents · hooks
Route repository work through portable planning, execution, and assurance skills.
16 skills · hooks
Self-improvement system for Claude with critic agent, quality analysis skills, automated conversation analysis, and feedback loops. Features automatic pattern tracking, learning reinforcement, and trend detection. Enables continuous improvement through honest self-assessment and iterative refinement.
5 skills · 9 commands · 1 agent · hooks
Adds a lean output style, six role agents, and a status line command. Adds hooks that ask before work on a repo with an AI policy, check edits and `git` calls, bound the context of subagents, and check Markdown line breaks and drift.
10 skills · 6 agents
Install and maintain ai-i18n-tools internationalization for application UI, documentation, JSON, and SVG.
16 skills
16 skills for ArtCraft apps: FigCraft, WordCraft, DeckCraft, GridCraft, PdfCraft, PhotoCraft, VectorCraft, SolidCraft, CadCraft, DesignCraft, EffectCraft, FilmCraft, LightCraft and SoundCraft (audio editing plus text to speech), plus a router that picks the right skill(s).
16 skills
Local-first memory: SessionStart hook injects a budget-bounded context payload from ~/.brain, /brain:* commands cover recall, memorize, verify, pin, forget, sync, skills, import and sleep. Bundles the brain CLI.
4 skills · 10 commands · hooks
Lightweight project planning system with multi-plan support, dependency tracking, cascade unblocking, parallelism, research notes, and ADR
2 skills · 13 commands
Writing, coaching, and strategy skills for technical leaders
8 skills · 3 commands · 3 agents
Discover, track, and assist with senior mobile / Android / Kotlin Multiplatform job applications. PII-safe form filling with shadow and auto modes. Self-improving adapters for Gupy, Greenhouse, Lever, Workday, Ashby and more.
1 skill · 13 commands
Feature Spec Workflow system with multi-agent collaboration, feature lifecycle management, and specialized agent commands
2 skills · 12 agents