Diverter
codexDistill Ultra-style native delegation into non-Ultra Codex sessions.
2 skills · hooks
Claude Code and Codex plugins their authors filed under "productivity". All categories.
Distill Ultra-style native delegation into non-Ultra Codex sessions.
2 skills · hooks
A git-tracked memory for this repo: Claude recalls the rule before it edits a file or runs a command, and captures one after a failure. Reviewable in a pull request, shared with the team, and portable to every other AI coding tool.
1 skill · 1 MCP server
Teach AI agents to download through oxdm: downloads visible in the user's window, resumable after errors, NDJSON output, typed exit codes.
1 skill
A focused StateM profile for durable single-agent task phases.
1 skill
The skeleton to copy when you start a new pack.
1 skill
The skeleton to copy when you start a new pack.
1 skill
Create and refresh evidence-based GitHub profile or project READMEs from repository activity, with free structural templates (icons, badges, table, and more) — no agent or API key. Pairs with Cadence to humanize the prose.
1 skill
Git-backed messaging for AI agent coordination across sessions, worktrees, and machines.
22 skills · 15 commands · 1 agent · hooks
Rank, prepare, submit, tailor, analyze, and interview with jobfishing and visible Chrome.
9 skills · 1 MCP server
Biomimetic long-term memory plugin for Claude Code with MCP server integration.
2 skills · 2 commands · 3 agents · 1 MCP server · hooks
The BootLoops protocol layer: seven disciplines for trustworthy quantitative work with agents — acceptance gates, integer-relation discipline, synthetic-truth controls, provenance bookkeeping, timing discipline, sources-only reading, tool stewardship.
7 skills
Calibre ebook library for Claude: the calibre-mcp server (search, semantic search, content extraction, metadata curation — 19 tools) plus companion skills (guided setup, usage guide, calibre-distill, calibre-distill-topic).
5 skills · 1 MCP server
The BootLoops research skills: heavier machinery for specific tasks — proving with agents (adversary-first pipelines), pre-circulation referee audit, the literature review behind a novelty claim, bibliography verification, and the scientific-prose linter.
5 skills
Use 共序 / GatherThread collaboration projects safely from Codex.
2 skills · 1 MCP server · hooks
Turn long-form videos into short clips and post them to social platforms via the OpusClip API. Ships a skill that drives the API via a bundled bash CLI.
3 skills
Agentic Context Engineering: evolve context through bullets, deltas, and TF-IDF retrieval. Complete with schemas, validation, and production scripts.
3 skills
Live token usage and cost dashboard for Claude Code, Codex and Copilot CLI.
1 skill
Skills for using Riksarkivet MCP tools — HTR transcription, archive search, document browsing
8 skills
Describe AI systems as DTPR datachains and brainstorm the DTPR schema itself. Ships seven agent skills that wrap the remote DTPR MCP at api.dtpr.io/mcp.
7 skills · 1 MCP server
wiki.yowu.dev WikiJS 지식 관리 플러그인 (WikiJS MCP 통합)
2 skills · 2 commands · 1 agent · 1 MCP server
글쓰기 스킬 모음. AI가 쓰는 장황한 문장을 사람이 읽기 쉬운 글로 바꾼다. 기술 문서(yowu-write-tech), 위키(yowu-write-wiki), 에세이/블로그(yowu-write-essay), 회의록(yowu-write-meeting), 코드 주석(yowu-write-comment) 5종 스킬. 전문 용어는 유지한 채 읽는 부하만 낮춘다. 한국어 상시 규칙 카드를 SessionStart 훅으로 모든 세션에 넣는다.
5 skills · hooks
Turns your top-tier model into a tech lead: it keeps decomposition, architecture and final synthesis, routing work to a role roster — an implementer for feature-sized coding, a worker for mechanical edits, a read-only investigator for long digs, and an independent reviewer for finished work. Every role's model is overridable from CLAUDE.md.
1 skill · 4 agents
Five hooks, one batched API call each. Classifies every prompt into a one-line routing hint; sets the model tier a subagent spawns on; judges each edit against the rules already in your CLAUDE.md, AGENTS.md and .claude/rules, citing the one it breaks; and on compaction judges 150 transcript blocks keep, truncate or drop so the survivors carry over verbatim instead of through a generated summary. Fails open everywhere. Shaped by evals over 2,464 real prompts and 250 real edits; see eval/.
4 skills · hooks
Bitrix CMS and Bitrix24 best practices for PHP, core APIs, SQL and ORM.
3 skills
HTML deck(페이지 넘김) 엔진 기반 인터랙티브 발표자료 생성 플러그인. 해상도 독립 16:9, 키보드/터치/진행바 네비게이션, 노트를 별창으로 띄워 동기화하는 발표자 보기(타이머·페이싱), 본문 컴포넌트와 근거 스탬프, 등장 애니메이션, 라이트박스, 다크/라이트 테마 지원.
2 skills
Choose the best Singapore miles card for a merchant.
1 skill · 1 MCP server
A local Codex companion pet asset pack generated from the user's pixel character.
1 skill
48 open reasoning methods for Claude, Codex and Antigravity. Check assumptions, compare options and revisit decisions. Instructions in 10 languages.
166 ready-to-use Claude Code skills organised by job role, so a PM, QA engineer, designer, marketer or analyst can install the workflows for their own job in one command.
168 skills
Universal multi-agent infrastructure: 26 specialist agents, 20 enforced workflow skills, and a lead orchestrator
20 skills · 26 agents · hooks