claude

kb

Knowledge-worker companion over the Brain: cited answers and Markdown deliverables.

1 on GitHubby onetest-aiv0.9.0MITupdated 10 days ago
/

Plugin kb from marketplace applied-ai in onetest-ai/applied_skills. Commands read from the repo's manifest — 9 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (8)

  • ask

    Use when the user asks a factual or analytical question the knowledge base should ground — answers from the Brain with a fully cited response, decomposing into sub-claims, routing each to the right lane, and marking anything the Brain cannot support as "not modeled".

  • brief

    Use when the user wants a short cited memo on a topic from the Brain — gathers narrative, metrics, and relations; verifies claims; then proposes the write to the human for approval, emitting to docs/kb/ with a Sources section and a sources.json sidecar.

  • challenge

    Use when a claim needs adversarial testing against the Brain — finds contradicting evidence, verifies metrics at the stated grain, and surfaces silent gaps marked as "not modeled".

  • deck-fact-check

    Use when the user wants a draft PowerPoint deck (.pptx) — including its charts, diagrams and pictures — fact-checked against the Brain, with a native PowerPoint comment pinned to the claim's shape on every Blocker and Major finding (every defect on request in a Deep check), evidence links, and a fin

  • doc-fact-check

    Use when the user wants a draft Word document (.docx) — including its diagrams — fact-checked against the Brain, with a precise anchored Word comment on every Blocker and Major finding (every defect on request in a Deep check), evidence links, and a findings page listing every claim.

  • explore

    Use when the user wants to explore a topic across the Brain — traverses related documents and taxonomy, surfacing connections and gaps with full citations to source files and vault paths.

  • mode

    Use when the user asks to enable, disable, or check "ambient mode" for kb — turns ambient grounding mode on or off (or checks its status) for this project. When on, every prompt gets a short reminder to ground factual/numeric claims in the Brain via a UserPromptSubmit hook.

  • report

    Use when the user wants a long-form structured report on a topic from the Brain — gathers narrative, metrics, and relations; organizes into sections with a Table of Contents; verifies all claims; then proposes the write to the human for approval, emitting to docs/kb/ with full Sources and a sources.

Subagents (1)

  • verifier

    Read-only truth-check of a draft answer or artifact against the Brain — re-resolves every citation and re-computes every number, returning a per-claim verdict. Use before emitting any authored deliverable.

Hooks (2)

  • SessionStart

    sh ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/health-line.sh

  • UserPromptSubmit

    sh ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/ambient-reminder.sh

View source on GitHub

More from onetest-ai/applied_skills

All 4 plugins →

brain

claude

Build, maintain, and deploy the Brain: a local, truthful knowledge engine (RAG + taxonomy graph + deterministic marts) over docs + spreadsheets, served via a governed MCP.

10 skills

1

scribe

claude

Living documents over the Brain: scheduled, versioned, cited docx/pdf with claim-level lineage.

4 skills

1

taska

claude

A manager's Epic > Story > Task tree kept current from meetings, calendar and files: cited evidence, dependencies, staleness and asks.

4 skills

1

Similar plugins

Self-learning vector database — HNSW, FlashAttention-3, Graph RAG, hybrid search, DiskANN, and Brain AGI

4 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

amplitude

claudecodex

Use Amplitude as an expert analyst — instrument Amplitude, discover product opportunities, analyze charts, create dashboards, manage experiments, and understand users and accounts.

36 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.6 and GPT-5.4

8 skills · 3 commands · 3 agents

wshobson/agents 42,461

Tavily

claude

Build AI applications with real-time web data using Tavily's search, extract, crawl, and research APIs.

8 skills

anthropics/knowledge-work-plugins 35,601

gbrain

claudecodex

Personal knowledge brain for your coding agent — hybrid search, synthesis, and durable cross-session memory, plus a curated brain-first skill set.

80 skills · 1 MCP server · hooks

garrytan/gbrain 32,792

45 advanced engineering skills: agent designer, agent workflow designer, RAG architect, database designer + schema designer + SQL assistant, migration architect, observability designer, dependency auditor, changelog generator, API design reviewer, API test suite builder, CI/CD pipeline builder, MCP server builder, skill security auditor, skill tester, performance profiler, focused-fix, browser-automation, full-page-screenshot, git-worktree-manager, monorepo-navigator, codebase-onboarding, interview-system-designer, runbook-generator, spec-driven-workflow, secrets-vault-manager, env-secrets-manager, pr-review-expert, self-eval, tc-tracker, feature-flags-architect, kubernetes-operator, chaos-engineering, ship-gate, slo-architect (error-budget + multi-window burn-rate alerts per Google SRE Workbook), tech-debt-tracker, agent-regression-evals, coding-agent-rollout, commit-craft, agent-run-forensics and i18n-localization. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.

48 skills · hooks

alirezarezvani/claude-skills 29,725

Maintain kb?

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.

claude & codex plugins4 plugins