Workflow plugins

LensTemper runs structured spec-driven development reviews with fresh reviewer subagents and lens-specific synthesis.

6 skills

팀 지식베이스 개발 워크플로: kb-brief(착수 브리핑) · kb-log(즉시 기록+원장 폴백) · kb-wrap(원장 flush) + 기록 유실 방지 훅 + kb MCP 연결(로컬/원격)

3 skills · 1 command · 1 MCP server · hooks

Turn a Slack bug-reports channel into Jira tickets — ledger-backed, idempotent, capped, with a threaded reply on every message it touches.

1 skill · 5 agents

A reusable, AI-first SDLC: setup, plan, design, build, test, deploy and maintain.

6 skills

Operate Paseo agents and daemon: orchestrate staged workflows, configure agent profiles, and report results.

5 skills

Works a GitHub issue backlog to zero, unattended: plan proposes it, health audits for it, the design-plan skill designs ahead of it, work drives it to a merged PR.

5 skills

Save session context and resume in fresh Claude sessions without losing continuity

1 skill · 3 commands · hooks

Workflow skills for review, delivery, repo-local stack skills, setup audits, and cleanup.

5 skills

Just-in-time coding conventions for Claude Code: path/content-matched rules that block or nudge at the moment of an edit, with pluggable detectors, per-session escape hatches, and tool-call guardrails. Ships a Rails preset, including an optional commented Sorbet inline-RBS advisory that hands off to a bundled skill.

1 skill · 3 commands · hooks

Create a project in an empty folder; initialise or audit a repository's agent harness: AGENTS.md, project profile, skills, hooks, docs, and the layer model behind them. Stack-agnostic.

1 skill · 4 commands

Frontend conventions for React / Next.js: UI rules for every screen, component discipline, and hooks for locale parity, translation keys and localised metadata titles. Enable in a web front.

3 skills · 1 command · hooks

Explore and spec ideas first, align intent, share a language, map the system, run tight feedback loops, checkpoint progress, validate before done, hand off cleanly, track every implementation decision as a reproducible recipe, and grow evolvebooks: guides for one kind of job that improve every run.

3 commands · hooks

Full dev lifecycle orchestrator: spike planning in Linear, duplicate detection, implementation tracking, Greptile-gated PRs, and round-robin reviewer assignment. One command — /juan-is-working — handles the ceremony so you focus on the creative work.

2 commands · 2 agents

Keep a repository ready for AI-agent work by enforcing what can be enforced and documenting only what cannot. audit writes a score-free gap report: which guidance docs exist (root and module AGENTS.md and the CLAUDE.md that imports it, docs/design decision records, a verification doc), which lint/typecheck/test/architecture checks exist and whether CI actually runs them, and every documented rule sorted into already enforced, cheap to enforce, not enforceable, or out of date. apply creates only what you approve: a short root AGENTS.md with a one-line CLAUDE.md that imports it (@AGENTS.md), module docs, decision-record pairs with union merge, an anti-pattern ledger, scripts/verify.sh with a git pre-push hook, a docs consistency check, and lint or architecture-test drafts for rules that only lived in prose. lessons turns corrections from the session and PR review into the same kinds of drafts. Release history lives in CHANGELOG.md.

3 skills · 1 agent

Dev toolkit: isolated worktrees for PRs/issues, ASD-STE100 PR/issue explanations, narrated video explainers, and draft-first pending PR reviews

4 commands

Skills for AWS role assumption (granted), 1Password CLI, and driving herdr agent loops

4 skills

Browser canvas for Claude Code — visual plan review, structured questions, inline annotations

1 skill · 1 command · hooks

開發規範：Conventional Commits 繁中版、docs/ 文件分類法、GitHub Flow 分支流程

3 skills

Persistent cross-session agent memory via markdown wiki

3 skills

Pick up, put down, fork, rename and hand off long-running Claude Code topics — a topic being a stable name that outlives the session beneath it, so work survives being resumed, set aside, split in two, moved between profiles, or handed to a fresh session. Teaches Claude the procedures; the `topic` CLI does the work.

3 skills

The exhale half of the inhale/exhale rhythm. A PostToolUse hook nudges for a simplicity and duplication review after every non-refactor commit, /exhale-init installs a diff-scoped rubycritic runner so that review has evidence behind it, and /simplify-with-analysis runs the deeper regression pass on demand.

2 commands · hooks

Make coding agents work like senior engineers: understand before acting, right-size rigor, keep changes simple and surgical, verify with evidence, and report honestly. Includes design and Next.js architecture protocols.

3 skills

Ensures edits to chosen files are reviewed before they are written.

1 skill · hooks

Write, edit and debug zopf workflows and connectors — the YAML that zopf runs as a graph of agent, shell, gate, input and branch steps.

2 skills

Semantic lock coordination for AI agents: acquire/release TTL leases on shared resources (deploys, migrations, shared files), plus lock monitoring and stale-lock cleanup.

2 skills

Coordinator + researcher/implementer/evaluator, a session budget, an accident catcher that closes the excludedCommands chaining hole, and an audit trace.

1 skill · hooks

Supervised autonomous loop: one Claude supervises, a separate headless claude -p daemon does the work in verify-then-resume cycles, with hard cost and cycle ceilings, mechanical gates, and a real kill switch.

2 skills

Restructure oversized SKILL.md or scattered project rules into a well-organized Skill directory, with cross-tool thin shells, SessionStart hooks, Task Closure Protocol, and self-evolving workflows.

2 skills

Push Claude Code completions to your phone via ntfy. The Stop hook sends what Claude actually said at turn-end (PR link / decision / error) instead of a static message; Notification events push permission/attention prompts. Auto-generates a private topic on first run with subscribe instructions. Cross-platform Node, no dependencies.

1 command · hooks

Ships a UserPromptSubmit hook that prepends 'Remember the code commenting rule.' to every prompt, plus a skill containing the rule itself (when to comment, when not to). Keeps Claude's commenting discipline consistent across long sessions and after context compactions, without per-seat settings.json edits.

1 skill · hooks