Discipline with no external standard behind it, covering how an agent writes and how it works. The authority is ours, and each skill says so. bench/ in the repository holds the protocol for measuring what a skill does.
Plugin stylewright-craft from marketplace stylewright in rookslog/stylewright. Commands read from the repo's manifest — 1 month ago.
compressed-deliberationUse when a reply or a written file runs longer than the decision it serves. Symptoms are narrated progress, restated context, labelled verification sections, and caveat lists that bury the one item that matters.
de-slopUse when prose reads as machine-written, whatever produced it. Symptoms are a restated question, a triad where two items would do, a stack of qualifications, and a closing that re-says the page.
navigable-referencesUse when you name a file, a document, a decision, or a discussion the reader may want to open. Symptoms are a bare filename, a label with no path, and a recalled line number.
proportionate-executionUse when an agent runs a multi-step task on someone else's behalf. Symptoms are narrated routine steps, work nobody asked for, and a routine condition reported as an emergency.
subagent-returnsUse when a calling agent reads the final message you return. Triggers are a subagent final message, a return to a calling agent, a delegation report, and an agent-to-agent handoff. Symptoms are a restated task, narrated process, a shape the caller never asked for, and a count with no stated source.
plain-languageUse when writing for a general public audience that must act, such as public guidance, policy, eligibility text, forms, or web content.
simplified-technical-englishUse when writing, revising, or checking procedures, maintenance instructions, safety notices, product documentation, or technical explanations under ASD-STE100 for international readers.
Writing skills distilled from published standards. A grounding matrix accounts for every statement: it cites a numbered rule in the source, or it is marked as our own guidance, or as narrative. CI checks the trace.
7 skills
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
3 skills · 1 command · 1 agent · 1 MCP server
Rewrite AI-sounding text so it reads like the writer without changing what it says.
1 skill
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Connect Claude Code directly to your CockroachDB clusters for hands-on database work — explore schemas, write optimized SQL, debug queries, and manage distributed database clusters. This plugin provides 14 tools across two active MCP backends (self-hosted MCP Toolbox and managed CockroachDB Cloud MCP Server), three specialized agents (DBA, Developer, Operator), 32 skills across 6 operational domains, and built-in safety hooks.
34 skills · 3 agents · 3 MCP servers · hooks
OpenAPI specification generation, Mermaid diagram creation, tutorial writing, API reference documentation
3 skills · 1 command · 5 agents
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.
1 skill · 9 commands
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.