Claude Code and Codex plugins their authors filed under "productivity". All categories.
Database-backed coordinator workflows with automatic legacy-state migration, exclusive work lanes, evidence-based verification, safe recovery, and goal-oriented reporting.
15 skills · hooks
SDLC support: grooming (product & tech-debt) → planning → development (TDD) → testing, with optional Jira slicing/uploading. Draft + human-approve, reuse-first (the ladder), AC as the contract.
11 skills · 3 agents · 1 MCP server · hooks
Multi-agent simulation of EU institutional processes: all 21 Commissioner personas, College deliberation, inter-service consultation, trilogue, full OLP, and compound analysis commands (mandate-conflict, red-team-college, subsidiarity-stress, timeline).
16 skills
Sets up the clinic, onboards students, runs structured intake, tracks deadlines with malpractice-aware caution, and hands off cases at semester end — built within ABA Formal Op. 512.
16 skills
One `office` CLI over a single transactional runs.db authority. Adaptive harness/model/effort routing, one-submit verification with independent code and visual review, rolling plan review, durable amendments, version-pinned runs, and human merge-to-main.
16 skills
Portable development workflows from requirements to verified delivery
16 skills
Ace in my space -- a suite of agent skills for scoping, delivering, and reviewing work in a workstream, with pull requests, cross-repository consultation, report publication, and harness detection.
15 skills
Switchboard plugin for Claude Code. Manage and switch between multiple accounts without logout.
14 skills · hooks
9 skills covering the full SA lifecycle: requirements, architecture, data modeling, security review, integration planning, estimation, project planning, proposal assembly, and deliverable review
9 skills · 2 agents · 4 MCP servers
Scaffold AI-development-ready FastAPI projects with canonical agent guidance, Agent Targets, MCP config, and design docs
15 skills
Horizon Europe grant management, infringement procedures (Arts. 258-260 TFEU), and public procurement. For grant managers, infringement officers, and procurement experts.
15 skills
Complete YouTube content production workflow: research competitors, generate video ideas, build briefs, craft titles and thumbnails, and create detailed video outlines with demo prep checklists.
5 skills · 7 commands · 3 agents
Emil Kowalski's motion-and-feel rules for UI and games, routed through one skill and wired to impeccable's detector.
14 skills · hooks
Workflow skills for Claude Code and Cursor - an adaptive flow conductor plus grilling, deslop, knowledge memory, PR babysitting, handoff, a git-ops owner, skill authoring, env preflight/bootstrap, and post-merge verification; ships auto-recall, runbook-hint, and handoff-nudge hooks.
14 skills · hooks
Professional git commits with Conventional Commits, GitHub Flow branch enforcement, auto PR creation, security validation, and auto-detection
5 skills · 10 commands
Auto-Apply That Ends on an Interview. Search matched jobs, tailor your resume and cover letter per role, and apply on 30+ hiring systems from Claude Code.
14 skills · 1 MCP server
Professional git commits with Conventional Commits, GitHub Flow branch enforcement, auto PR creation, security validation, and auto-detection
5 skills · 10 commands
Dynamic, evidence-based development governance for Claude Code and Codex CLI.
13 skills · 1 MCP server
Belt — the cloud platform for AI agents. Run hundreds of AI apps, manage knowledge, search and publish skills, connect MCP servers.
10 skills · 3 agents · 1 MCP server
Dev workflow essentials: project setup, code review, cleanup analysis, pro/con
14 skills
Hook-enforced development discipline for Claude Code. Skills teach methodology (TDD, debugging, verification, SDD); hooks enforce compliance (git gates, branch protection, test evidence); store survives compaction.
14 skills
Project folders, automatic daily logs, travelling memory, and the personal OS commands.
12 commands · 1 agent · hooks
Stigg skills for AI-assisted dev — pricing, plans, features, entitlements, subscriptions, credits, governance, widgets, webhooks. Load the `stigg` umbrella first; it routes to the right pillar.
14 skills
Multi-agent software delivery orchestration with independent quality and security gates.
14 skills
Thirteen reasoning-and-review skills: goal confirmation before work (skopos), Socratic elenchus and inquiry (quaestio), reductio ad absurdum, negative dialectics, argument warrants, Lakatosian counterexamples, dialectical-inquiry counterplans, a single review pass (emend), review rounds gated by outside evidence (ratchet), rulings on others' reports about a text, rules for text a model follows (regula), and deepening a request by a field's best practice before running it, plus dia-router, a short entry point. A skill starts when the message begins with dia or the skill's name.
14 skills
The ACF cycle, out of the box: /whip is the front door (where you are, and the one command to run next). Small work goes straight to /task and /go; risky work gets a plan in docs/cycles/ that you approve once, bound to its content hash, after which /task --plan decomposes it, /go builds it, /whip shows per-deliverable coverage, and /retro closes the cycle with one-rule lessons and an action plan that feed the next plan. /whip --auto runs the whole loop hands-off until a fresh judge agent finds the goal met; plans still wait for your yes unless you opt in with --approve. Spec reviewers and workbenches (GapTrap ships as the example) plug in with one committed file. Workflow-native backlog automation. /task decomposes a scope into atomic, dependency-aware tasks, each with a role; /go runs each unit as its OWN nested workflow — the shipped harness (implement, quality gates, an adversarial review) run by the generic whippet worker, which loads the role's skill on demand (an installed specialist agent is still honoured) — in isolated git worktrees (one per slug), reviews each accepted diff (once, when a configured gate passed and the harness's own reviewer accepted that commit) and integrates via LP-CAS, looping until every task is accepted or blocked. A bare /go runs your FOCUS: the tasks /task just created, or the ones you selected with /whip-focus — so the ordinary path needs no arguments and still runs only your own work, while /go --all drains the whole backlog and /go <ids|MUL-1234|a natural-language filter> runs exactly what you name. On a shared board a bare /go with no focus refuses rather than draining everyone's queue. The snapshot is narrowed in the STORE (--only emits just the closure of the named tasks) and carries a relay header the orchestrator verifies, so a large board can no longer be silently truncated on its way through a scan agent and reported back as missing task ids. An integrity FATAL now holds out the ONE task it names instead of stopping the ru
13 skills · hooks
Analista desenvolvedor Sankhya: banco só leitura, dicionário e grafo, Central de Ajuda e conhecimento da empresa.
11 skills · 2 MCP servers · hooks
Delegate Host-assisted discovery, review, and verified isolated implementation to Pi.
10 skills · 2 agents · hooks
Standardizes .aiwork/ artifact organization by task (aiwork-protocol skill), with skills for the full loop: intent → spec → tickets → implement → review (triage, to-spec, to-tickets, implement, implement-spec, next-steps, code-review-diff, grill-with-docs, tdd, prototype, wait-what)
12 skills · hooks
Know your unknowns — skills for the gap between your plan and the actual situation, in any domain: what you don't know, what the AI doesn't, and what neither knows yet. Eleven skills: blind-spot passes, field primers, interviews, divergent prototypes, brainstorming, reference read-backs, tweakable plans, a deviation log, buy-in docs and quizzes — plus two Claude Code agents.
11 skills · 2 agents