Personal-style writing with explicit rules, advisory corpus tendencies, scoped persistent preferences and exact-final-text checks. Authenticated Claude/Codex runtime; optional whole human examples.
0 on GitHubby Connor Englandv0.10.1MITupdated 3 days agowriting
/
Plugin prose-author from marketplace vonnegut in ConnorBritain/vonnegut. Commands read from the repo's manifest — 3 days ago.
What it installs
Skills (4)
prose-corpus
This skill should be used when the user wants to bring their existing writing into their human corpus — from a Substack export, a Google Docs export folder, a Markdown vault (Obsidian, Logseq, a folder of notes) or an mbox of sent mail — asks what is in an export, asks how far their corpus is from t
prose-draft
Draft, rewrite, or continue prose using personal writing examples and explicit style preferences. Use for short replies, notes or outlines turned into prose, passage rewrites, and writing in a chosen personal style. Supports preference-only help without a corpus; does not promise resemblance or fact
prose-repurpose
This skill should be used when the user wants one finished piece turned into other forms - a newsletter issue, a LinkedIn post, a thread, a talk abstract - in their own voice, each drafted through the production runtime under that form's medium profile and preference scope, checked mechanically agai
prose-style-tune
Discover, save, scope, compare, version, or undo personal writing-style preferences; inspect opt-in numerical writing history and changes over time. Use for persistent style rules, guided comparisons, history ingestion, baselines, export, or deletion. Observations and user choices stay separate.
Subagents (4)
voice-draft
Drafts, rewrites, or continues prose from an authorized brief, explicit preferences, an optional voice profile and selected whole human examples. Use for personal-style writing with or without a learned profile. Never receives the tell catalog, applies preferences to storage, or certifies its own ou
voice-feedback-interpret
Interprets one writing correction or controlled style choice as narrow preference operations or a clarification question. Works with voice-preferences/2 and an optional voice-profile/3. Never edits observed evidence, saves preferences, or applies its own proposal.
voice-profile-render
Describes cited writing behavior from supplied whole human-authored samples for deterministic voice-profile/3 assembly. Use to create or refresh a personal-style profile, including explicitly limited evidence from short samples. Does not draft prose, invent counts, or turn sample tendencies into man
voice-rhetoric-measure
Read-only rhetorical annotation of supplied author prose under a fixed rubric. Produces located estimates for qualification, analogy, reader address, and paragraph roles; never rewrites, evaluates quality, or defines an author's identity.
Two read-only critics and one revising transformer for prose. prose-voice-critic: does this sound like the author, judged against their own corpus, with every finding required to cite how they write instead. prose-fidelity-critic: did a revision keep the facts, quotes, qualifications and claim strength of the original, judged against a deterministic scan that is authoritative on presence. prose-reviser: applies a plan of edits and emits a change log the fidelity critic then judges — out-of-plan edits impossible by construction. Never judges quality, never claims anything about who wrote something.
Outlines for prose: turn a brief into a checkable outline with thesis, claims, evidence slots and open questions (or acts, beats and turns for fiction); read a draft back into the outline it implies with a deterministic scan; diff two outline revisions by node; keep outlines per project in the shared writing-identity registry with undo. Proposes and measures; never drafts prose and never scores it.
Continuity for multi-file prose projects: a deterministic cross-file index of names, defined terms, attributes, dates and repeated passages with locations; a diff that pairs what differs; a per-project bible in the shared writing-identity registry, proposed from the index and confirmed entry by entry; and a read-only critic that reports contradictions citing two locations or nothing. Never fact-checks against the world and never saves without approval.
Deterministic prose measurement: a catalogued scan for AI writing tells plus the cadence metrics a model cannot estimate about its own output. Register-aware, calibrated against your own corpus, and report-only — signals for an author about their own draft, never a verdict about who wrote something. Ships no rewriter, by design.
Provenance for prose: take sources in (a URL, a file, a PDF's text), keep a dossier of quotable passages with locations and a claims ledger (claim, source, quote, the writer's confidence) in the shared writing-identity registry with undo, and check a draft deterministically — every ledger quote verbatim against its source, every link, every sentence that makes a claim no entry backs. Hands quote provenance to the fidelity critic. Never says a claim is true, never ranks sources, never saves without approval.
AgentDB (external: maintained in ruvnet/agentdb, pinned to commit 27678c3, plugin 3.6.0): agentdb's own standalone MCP server pinned to [email protected] (vector memory with get/list/update/delete for records, patterns and skills, hybrid keyword + vector episode search and an opt-in local cross-encoder, an opt-in aidefence injection guard on memory writes, reflexion, skills, outcome feedback, capabilities report), a memory-specialist agent, 3 skills, /agentdb-status, and the agentdb mod guard that keeps secrets out of memory and refuses delete/reset unless allowed. Complements ruflo-agentdb, which reaches AgentDB through ruflo's server
Provision direct cloud access (Vertex AI, Bedrock, or LLM gateway) for the Claude Microsoft 365 add-in. Generates the customized manifest, walks through Azure admin consent, and writes per-user config via Graph extension attributes.
Founder-mode executive team plugin: 13 cs-* C-suite agents (CFO, CMO, CRO, CPO, COO, CHRO, CISO, Chief of Staff, General Counsel, Chief Data Officer, Chief AI Officer, Chief Customer Officer, VP of Engineering) with distinct cognitive voices, plus 21 /c-level-agents:* slash commands — forcing-question office hours (CFO/CMO/CPO/CRO/CTO/CISO/GC/CDO/CAIO/CCO/VPE reviews), strategic sprint pipeline (brief → boardroom → decide → execute → post-mortem), and meta routing (/c-level-agents:founder-mode auto-router, /cs-onboard, /c-level-agents:cross-eval multi-model consensus, /c-level-agents:freeze cooldown lock). Wraps the 33 c-level skills with cognitive gearing, persona voice, and artifact-driven handoffs. The business-domain answer to YC Garry Tan's gstack.
22 skills · 13 agents
alirezarezvani/claude-skills 29,725
Maintain prose-author?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.