10 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
aiwgjmagly/aiwg1
md-exporter-pluginsbowenliang123/markdown-exporter1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplaceEngineer an agent's forgetting, not just its remembering. Four deterministic stdlib scripts implement the four lenses of agent memory: a cost profiler that splits construction from query spend and reports cost per correct answer (construction energy exceeds total query energy across 300 queries in the Stanford characterization); an architecture picker that scores the four paradigm families — long-context, flat RAG, structure-augmented RAG, agentic — disqualifies on hard constraints, names the cost the winning choice makes you pay, and refuses to pick when the top two tie; a density auditor that classifies every record in a memory directory or JSONL export as FACT / SKILL / LOG / PROSE, finds near-duplicates, and flags stale wording; and a forgetting-policy linter that fails any design with no forgetting rule. Ships cs-memory-engineer agent, /cs-memory-engineering and /cs-forgetting-audit commands, 4 references, and a seven-question forcing worksheet.
When your bar comes asking "show me how you billed AI-assisted work" — and ABA 512, Florida 24-1, California, New York, and DC all have opinions out — you need an artifact that survives review. billable-time produces it. From your Claude Code session logs, it drafts reviewable time entries plus a printable HTML audit packet with: SHA-256 chain of evidence (source files + matter.yml + active disclosure pack + verifiable artifact self-hash), attorney identity and signature block, a bar-opinion disclosure pack with starter language for five jurisdictions, and content-aware deterministic narratives derived from filename and tool shape — never from prompt text by default. The tool refuses to bill on its own. --strict mode refuses to ship the artifact if any audit invariant fails (broad routes, missing attorney, missing/unverified disclosure). Comes as a Node CLI and a self-contained browser version (no backend; JSONL never leaves the page). 15 invariant tests verify the contract. AGPL-3.0.
Fetch Bilibili (哔哩哔哩) video comments for UP主 self-analysis. Collect, download, export, and analyze comments on a Bilibili video (BV号 / URL / UID), producing JSONL + summary.json suitable for further analysis (sentiment, keywords, audience trends). Read-only; does not post/edit/delete.
Developer reference for building applications, tools, and agents on the Pi Durable agent harness (@earendil-works/pi-durable) and the pi-ai model layer. Use when writing or debugging code that imports @earendil-works/pi-durable or pi-ai: assembling a Harness over memory/SQLite/JSONL/Durable Object storage, submitting input and waiting for answers, defining tools with TypeBox schemas and structured output, calling tools from tools, hooks and guards, durable tasks with checkpoints and ownership, subagents and child tasks, documents and migrations, code mode, tool search, per-conversation environments, compaction, recovery after a crash, storage and environment conformance tests, or choosing models and providers. Also use for durable-runtime behavior questions: what survives a restart, why an input stayed queued, why a task is blocked or orphaned, how abort cascades, or what the Pico5 specification requires.
Fetch and export public X (Twitter) data with a self-contained Python CLI built on the twikit library — no developer API keys, just the user's own login cookies. Covers user profiles, a user's tweets/replies/likes, single tweets, threads, search, followers/following, home/bookmark timelines, with JSON/JSONL/CSV/SQLite output and resumable pagination. Use whenever the user wants to scrape, download, collect, archive, monitor, or analyze tweets or X/Twitter accounts, export a timeline or follower list to a file or dataset, pull X data for research, or build a tweet corpus — even if they don't name the tool. Requires the user's own X login cookies (auth_token + ct0, or username/password login).
Project scaffolding and eight-axis code review with contextual validation and JSONL output
Corpus-to-dataset pipeline for AI training data curation. Ingests sources, synthesizes examples, generates DPO/KTO preference pairs, applies decontamination, and exports to Alpaca/ShareGPT/ChatML/JSONL/Parquet with provenance. Optional Python runtime (aiwg-training CLI) for scale.
Transform Markdown text to DOCX, PPTX, XLSX, PDF, PNG, HTML, MD, CSV, JSON, JSONL, XML files, and extract code blocks in Markdown to Python, Bash,JS and etc files.
Collect public comments from Bilibili, Xiaohongshu, Douyin, Kuaishou, Weibo, Tieba and Zhihu, then generate an interactive HTML report plus CSV/JSONL data.
data
Translate EPUB (.epub) ebooks to another language by unpacking the EPUB container, extracting XHTML block-level fragments into JSONL translation units, translating them via the OpenAI Responses API (e.g. gpt-5.1 / gpt-5-mini) while preserving markup, updating language metadata, and repackaging a valid EPUB (mimetype-first and uncompressed). Use when Codex needs to translate and rebuild EPUB files.
