28 plugin dari marketplace Claude Code publik. Masing-masing membundel skill, slash command, agent, hook, atau MCP server yang di-install bersama.
Menampilkan 28 plugin yang sesuai dengan filter ini.
pm-claude-skillsmohitagw15856/pm-claude-skills2
agents-incagents-inc/skills2
claude-code-plugins-plusjeremylongshore/tons-of-skills-marketplace1
social-media-research-skillsScrapeCreators/social-media-research-skills1Kirim repo dengan .claude-plugin/marketplace.json dan kami akan mencantumkan setiap plugin.
Kirim marketplaceComplete Deepgram integration skill pack with 24 skills covering speech-to-text, real-time transcription, voice intelligence, and audio processing. Flagship tier vendor pack.
Answer questions about past agent runs from the recording, not from memory. Three read-only stdlib scripts over the session transcripts Claude Code and Codex already write: a finder that locates the run by repo, time window, touched file or command text; a timeline that numbers every step with its exit code, lists every file changed (flagging changes the agent never mentioned) and walks back from any step with each causal edge labelled recorded or inferred by a named rule; and a claim checker that tests a summary's claims (ran, passed, edited, not-edited, read) against the run and catches tests that passed before a later edit and exit codes that belong to the last command of a pipe. Secrets are always redacted. A UserPromptSubmit hook gives the agent this session's transcript path when a prompt asks about past work. Ships cs-run-forensics agent, /cs-run-forensics and /cs-check-claims commands and 3 cited references.
A four-tier memory ladder for Claude Code where promotion is earned by recurrence, not asserted by confidence. L0 raw transcripts are never injected; L1 candidate atoms are gitignored and recalled on lexical relevance per prompt; L2 project context loads each session start; L3 stable persona is always loaded. L1 to L2 needs three distinct sessions spanning two distinct calendar days (a stated claim needs two; a verified claim is the only single-observation path); L2 to L3 needs two projects and thirty days. Two gates refuse rather than guess: a claim altered by the redaction pass never promotes on evidence alone, and a contradicted claim freezes until a human resolves it. Three hooks run the loop unattended and every one fails open. Nothing reaches a committed CLAUDE.md without an explicit human adopt. Ships 5 stdlib scripts, 3 hooks, a cs-memory-curator agent, /cs-memory, a JSON schema, and a 69-check validator. Concept from TencentCloud/TencentDB-Agent-Memory (MIT); no upstream code
Grade an agent setup from real conversation history — a rebuild of warpdotdev/common-skills' skill-doctor (MIT). Harvests recent local Claude Code and Codex sessions scoped to one repo, condenses and secret-redacts transcripts (12-pattern redactor, chmod-0600 artifacts, nothing uploaded), has the agent judge each transcript against two verbatim-preserved rubrics (efficiency, code quality — labels only), then runs a deterministic aggregation gate that derives every number from the label tables, refuses scores for unsampled sessions and suggestions that cite no scored session, and renders one self-contained zero-JS HTML report (dark-mode, print-to-PDF). Proposed skill edits stay staged as diffs until an explicit per-skill yes; zero suggestions is a valid, reportable success. Ships cs-skill-retro agent, /cs-skill-retro command, 3 stdlib tools, 3 references citing 7 sources each.
Practical social media research workflows powered by ScrapeCreators: find outlier posts, mine comments, analyze transcripts, research competitors, and tear down ad libraries.
Token optimization for every stage of the agent journey: crush tool outputs before they enter context, navigate code by map instead of reading files, diet the output register, budget the window cache-aware, measure everything, and hand off sessions at 5% of transcript size
9 short commands (/setup, /list, /trans, /note, /wiki, /add, /page, /cheatsheet, /ralphtrans) for Tongji Look lecture transcription, supplementary material ingestion, course wiki generation, and GitHub Pages deployment.
educationClose the loop between what you keep asking your assistant for and reusable skills: scan your transcripts for recurring patterns, draft a skill in this library's format, test its triggers, and publish a complete release package
General-purpose AI productivity toolkit: browser automation, audio transcription, deep research, decision frameworks, fact-checking, file organization, prompt engineering, MCP server building, and more. 17 community skills in one install.
Audit sales call transcripts and CRM exports against GTM rubrics — deal stage, initiative frameworks (MEDDICC, BANT), industry vertical context. Every finding cites a quote.
Turn screen recordings into ready-to-file bug drafts, specs, backlogs and meeting actions — local Whisper transcript + keyframes + OCR + wall-clock evidence via the talkthrough MCP server.
Memory-defragment/cleanup engine for agent memory, TWO lanes: class-B (memory + governance files) gets the semantic wash — a free mechanical Quick pass plus a code-enforced fidelity gate blocking any STRUCTURED-token drop by diff (links, dates, versions, frontmatter; prose fidelity is the paid semantic layer's job), consent-gated Full pass, every cut snapshot-backed (whole-run rollback); class-A (transcripts — the estate) gets byte-identity ULTRA archiving, never semantic-edited. Honest frame: slows how fast memory-overhead grows — it does not eliminate memory cost. Zero-dependency, offline, no API keys.
Analyze a U.S. Supreme Court oral argument transcript for a lawyer who has not read it: each advocate's position, authorities discussed, the bench's concerns, tentative judicial leanings, possible dispositions, and advocacy strengths and weaknesses, with transcript pinpoints. Use for oral argument analysis, a SCOTUS argument report, or an assessment of how the justices approached a case. Requires readable transcript content; research, Python tallying, and document creation are optional, with disclosed fallbacks.
PlaceCall makes AI phone calls that book, confirm, and reach US businesses. It places a real outbound call and returns a structured outcome plus a full transcript. Sign in on first use, no API key needed.
productivityTurn a video, recording, voice memo, or media URL into an evidence packet — authoritative whisper transcript, timestamped frames, manifest — plus a routing recommendation. Six intents behind a mandatory purpose gate; the pipeline script is resumable and encodes the hard-won gotchas.
Hugging Face Inference SDK patterns for TypeScript/Node.js — InferenceClient setup, chat completion, text generation, streaming, embeddings, image generation, audio transcription, translation, summarization, and Inference Endpoints
Speech-to-text transcription and translation via OpenAI Audio API -- models, response formats, timestamps, prompting, streaming, chunking, and diarization
Use this skill for local FFmpeg/FFprobe media inspection, remuxing, transcoding, filtering, evidence-bounded video review, transcript-assisted editorial plans, edit decision lists, podcast/audio cleanup, rendering, and output acceptance. It emphasizes explicit stream selection, source preservation, build-aware commands, bounded evidence, and verified new outputs. Do not use it for libav API programming, opaque whole-video understanding, automatic publishing, rights clearance, DRM circumvention, professional broadcast/color certification, or HyperFrames-authored compositions; route those tasks to their owning capabilities.
Query Fireflies.ai meeting transcripts, meeting notes, summaries, contacts, channels, AI meeting analytics, AskFred, audio uploads, and webhook signatures through its GraphQL API. Use when a user mentions Fireflies, Fireflies.ai, meeting transcripts or notes stored in Fireflies, AskFred, or Fireflies webhooks. Do not use for local audio transcription, calendar management, or meetings that are not Fireflies data.
Use this skill to coach candidates and interviewers for job interviews: prepare truthful examples, critique interview transcripts, run interactive mock interviews and targeted practice, design structured questions and evidence-based scorecards, and improve candidate experience. Adapt to profession, seniority, and interview format. Do not use for journalism, user research, workflow discovery, general resume writing, clinical interviewing, or autonomous hiring decisions.
