fable-mode
claudeMake Opus 4.8 behave like Fable 5: doctrine output style, drift-catching hooks, orchestration skills, and an eval loop against golden Fable transcripts.
3 skills · 2 commands · 1 agent · hooks
Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.
Make Opus 4.8 behave like Fable 5: doctrine output style, drift-catching hooks, orchestration skills, and an eval loop against golden Fable transcripts.
3 skills · 2 commands · 1 agent · hooks
Five skills to remember decisions, re-test assumptions, and grow project-owned investment knowledge.
6 skills · hooks
Personal health management skills — preventive care gap tracking (HEDIS), medication refill monitoring, healthy habits dashboard, diet & exercise analytics, pediatric immunization schedules, and biomedical research / clinical trial monitoring.
6 skills · 1 MCP server
4 multi-agent collaboration skills: fan-out planner, context budget with proposal-only memory, debate, and an acceptance gate that reconciles lane output; 3 redirect stubs remain until 0.7.0.
7 skills
Prevent, catch, and verify architectural violations while Claude Code works.
1 skill · 4 commands · hooks
5 skills for the content-creation workflow: research-collector, publisher-wechatsync, article-optimizer, score-optimizer, yt-dlp-direct.
5 skills
oh-my-gjc — focused Gajae Code suite with 5 skills and 5 commands. Skills: no-english, extragoal, insane-review, insane-search, gpt-image. Commands: /omg, /omg:setup, /omg:no-english, /omg:insane-review, /omg:gpt-image.
5 skills
Foreman by Turki Alshuaibi turns your agent into the foreman of a website build: it interviews you, forces the design and scope decisions, locks a visual system, writes the brief, then builds or hands it over, and verifies, ships and indexes the site. Survey, Blueprint and Stress test modes. A toolbelt of four standalone tools: board, punch list, palette and launch.
5 skills
Rolling context compression - old messages get summarized, recent messages stay verbatim. Never hit the context wall. Toggle it off per session with /rolling-context:off (or --global) when a session wants the full history - subagents follow the session that spawned them, and nothing already compressed is thrown away.
4 commands · hooks
Peer validation system using OpenAI Codex CLI. Two AI perspectives catch more issues than one.
1 skill · 1 command · 1 agent · hooks
Java JDWP debugger via MCP — set breakpoints, inspect runtime state, evaluate expressions, mutate variables, catch exceptions at throw site, trace execution with logpoints.
2 skills · 1 MCP server · hooks
Three skills (prove-the-premise, hobby-or-business, one-real-conversation) plus /validate-idea and /reality-check slash commands.
3 skills
Auto-generated session titles + per-session colors in the Claude Code statusline — tell parallel sessions apart at a glance.
2 commands · hooks
Agent Skills for Anytype setup, including a dedicated headless account for one LLM-sharing space, plus anyr and any-mcp workflows.
3 skills
Generate images and videos with Leonardo.Ai. Wraps the leonardo CLI and ships guides for every model family (Lucid, Phoenix, Flux, Motion 2, Veo 3, Kling, Hailuo, LTX, Seedance).
1 skill · 2 commands
Free and open source, LibreJustice gives your agent ~3.9 million French-language and European decisions and ~2.1 million legal articles in force and ~1.8 million historical versions, readable as they stood on any date and linked article by article. Four MCP tools over OAuth, two research skills.
2 skills · 1 MCP server
ABAP Cloud / RAP overlay plus three skills: rap-bo-design (build a full RAP BO via the official SAP ADT MCP generators), atc-remediation (walk ATC findings methodically), clean-core-check (audit clean core compliance). Self-contained; install the clean-abap plugin separately if you also want the universal Clean ABAP review and refactor skills. Targets BTP ABAP Environment and S/4HANA on-prem in the ABAP Cloud development model.
3 skills
Skills for working with AI. First up: /improve, which makes your Claude Code setup better after every conversation.
3 skills
Metin2 UI code generator — create and modify client UI from screenshots, descriptions, or existing scripts
1 skill · 1 command · 1 agent
NEAT's live semantic graph in Claude Code — the MCP graph tools, the graph-first search-nudge hook, and the skill, in one install.
1 skill · 1 MCP server · hooks
Search, read and edit your notes in Pinto Notes from Claude Code. Sign in once with /mcp.
2 skills · 1 MCP server
Starter template plugin for oh-my-gjc. Ships one slash command and one skill so you can see the full structure before authoring your own.
1 skill · 1 command
Create and resume session handoffs for multi-session work continuity.
2 commands
A 260-token system prompt that overrides three structural presumptions every RLHF-trained LLM inherits from training: that you want confirmation, that old scarcity still applies, that best practices are ceilings.
1 command · 1 agent
Semantic codebase search — natural language queries over code and docs using embeddings, tree-sitter parsing, and POEM multi-signal ranking
1 skill · 1 MCP server
Query logs, metrics, events, entities, problems, security vulnerabilities and SLOs from self-hosted Dynatrace Managed clusters, across one or many environments.
1 skill · 1 MCP server
Best-of-N parallel implementation — run multiple agents on the same spec, review each, pick or synthesize the best
2 skills
Evidence-backed technical review with dry wit.
1 skill · 1 agent
Universal Clean ABAP rules plus two skills: review and refactor. Skills load the rule set from CLAUDE.md on invocation — no always-on context cost beyond skill descriptions. Targets modern ABAP only — BTP ABAP Environment or S/4HANA on-prem in the ABAP Cloud development model.
2 skills
Аудит и правка русских текстов от ИИ-стиля; под-скилл antiplagiat.
2 skills