공개 Claude Code 마켓플레이스의 플러그인 45개입니다. 각 플러그인은 함께 설치되는 스킬, 슬래시 명령, 에이전트, 훅 또는 MCP 서버를 묶습니다.
필터와 일치하는 45개의 플러그인을 표시합니다.
awesome-journal-skillsbrycewang-stanford/Awesome-Journal-Skills2
claude-code-workflowswshobson/agents1
mikefluffMikefluff/skills1
aiwgjmagly/aiwg1.claude-plugin/marketplace.json이 포함된 repo를 제출하면 모든 plugin을 목록에 추가합니다.
marketplace 제출Engineer 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.
Twelve-skill bundle covering The American Historical Review (AHR) manuscript lifecycle — historiographical intervention, archival source criticism, interpretation, Chicago-style prose, and the review and submission process for a humanities flagship.
academicTwelve-skill bundle covering the Journal of the American Academy of Religion (JAAR) manuscript lifecycle for humanities scholarship in the academic study of religion — argument, primary texts and traditions, theory and method, and reflexive scholarly prose.
academicHuman-verification gate for an agent loop: builds a single-file review page (the page itself makes no network request; a reviewed HTML artifact's own https: assets still load), collects batched feedback as structured batch.v1 data instead of chat prose, and refuses to close while a BLOCKER is open, the reviewer is unnamed, or nobody has reviewed. Non-blocking, headless-guarded, round-capped. Stdlib-only.
Convert a rambling description of a desired outcome into one polished, autonomous /goal prompt ready to paste into a fresh session. Extracts deliverable/quantity/stakes/tools/destination, asks at most one question batch, verifies every named resource against the live environment, writes a 150-350 word prose prompt with the seven-part anatomy, and self-checks six binary criteria before delivering. The output is a single copy-paste prompt, never the build itself.
Audit and rewrite prose that reads as machine-generated, across READMEs, changelogs, PR descriptions, docs, and blog copy, with detect-only, rewrite, and edit-in-place modes.
45 skills: a clean-prose engine with an offline linter, wrappers for viral posts, essays, cold email and landing copy, and orchestrators that carry a job from research question to published carousel or reel.
contentTools for reading, parsing, validating, and executing OpenProse programs from AIWG workflows
Typed, calibrated decisions instead of prose: renew-or-churn, escalate-or-hold, ship-or-slip, hire-or-pass — each with a state schema, defined options, and thresholds a program or a person can act on
Venue-aware academic writing: reflection passes, abstracts, related work, literature reviews, prose polish, and author/venue style matching grounded in verified citations.
All 30 maintainer skills and 9 agent profiles: humanize and localize prose, triage, reproduce and verify bugs, review PRs, debug ML training, profile performance, bisect regressions, audit CVEs, generate changelogs, evaluate SemVer version bumps, isolate scratchpads, fix type errors, isolate faults, conduct adversarial reviews, route architect-editor edits, generate conventional commits, resolve merge conflicts, prune context, and prepare releases.
productivityTen skills and eight agents that run a job application and feed what the review finds back into your profile. The skills: onboard, search and score roles, find a referrer and draft the ask, interview for undocumented experience, build the resume and letter, adversarially review them, de-slop the prose, restyle the templates, report the queue and its calibration, and answer what to run next.
productivitySix skills for scientific writing: edit research prose, structure an IMRaD manuscript, run the writing process, handle peer review and publication ethics, draft grants and letters, and write for general audiences.
writingVerification-first methodology for the Kosovo Specialist Chambers and Specialist Prosecutor's Office (The Hague, applying Kosovo law). Citations are verified against scp-ks.org before use; appeal registry numbers are cited only once confirmed. Covers Thaçi et al., Mustafa, Pjetër Shala and Gucati & Haradinaj. Research aid, not legal advice.
Apply elite legal writing techniques drawn from Justice Kagan, Boies & Olson, and other top advocates to any legal document — briefs, submissions, letters, opinions, memos, or persuasive correspondence. Covers both prose craft (clarity, concrete examples, parallel construction, voice, strategic quoting) and architectural strategy (argument sequencing, framing, openings, endings), plus a dedicated section on detecting and removing AI-sounding patterns from legal prose. Use whenever drafting, editing, or sharpening any legal document that needs to genuinely persuade, not just be technically correct.
Uses deterministic prose checks to flag overly complex coding-agent responses and ask for one clearer rewrite.
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.
Runs a server-enforced STRIDE threat model and LINDDUN privacy threat model over a system described in prose, screens named dependencies against live CVE/KEV/EPSS data, and builds a cited screen of which EU security obligations (GDPR, NIS2, CRA, AI Act) may apply and which need determination - every regulatory statement fetched from officially published text through the Ansvar Gateway connector at answer time, with scope, role, and application-date limits stated. Never answered from model memory; never a compliance verdict.
Transforms reading-oriented prose into listening-optimized text for flat, neutral vocal delivery — TTS, podcasts, audiobooks, CLE audio. Carries a legal layer: case citations, section symbols, subsection lettering, Latin terms and footnotes are unspeakable as written, so a brief, opinion, statute, contract or memo needs them expanded, restructured or stripped before it can be listened to — and quoted authority is never rewritten. Use when converting written content for audio, preparing oral argument by ear, producing CLE or client-facing audio, or making a document listenable on a commute. Triggers on "make this listenable," "convert for audio," "optimize for reading aloud," "prepare for TTS," "make an audio version," "podcast script," "read this aloud." Supports English, French, Spanish, Italian, German and Portuguese; outputs plain text, ElevenLabs audio tags, or SSML for Amazon Polly, Google or Azure.
Turns a legal question, a set of draft questions, or source material such as a statute, jury instruction, rubric, contract checklist, or coding manual into a battery of narrow questions that TypeSafe's Jev, a fast classifier that returns probabilities rather than prose, can answer reliably across many documents. The skill breaks conclusions such as negligence, felony murder, or standing into element-level questions, writes the governing rule into each question, and delivers the questions alone, in Jev's request format or in plain English. Built for legal work that asks the same questions of many texts: coding statutes across jurisdictions, coding opinions or case files for empirical research, checking contracts against a review checklist, screening intake narratives, and grading student work against a rubric. Use when asked to write Jev questions, build a classifier for legal documents, or turn a legal test into yes-or-no questions. Running the questions requires Jev access; writing th
