Intelligent toolchain orchestrator for Claude Code — recommends skills, plugins, MCPs, and agents for any task with dependency-aware ordering
Generate or rebuild the Obsidian vault knowledge base. Scans all installed skills, plugins, and MCPs, then uses LLM subagents to create rich skill cards and concept notes in the vault. Run after installing new plugins or to refresh the catalog.
Enable or disable the Skill Advisor hook and configure settings. Use /advisor-config disable to stop the nudge hook, /advisor-config enable to re-enable it, or /advisor-config status to check current state.
Record feedback about the last advisor pipeline execution. Helps the advisor learn which skills and combinations work best. Use after completing an /advisor pipeline.
Rebuild the Skill Advisor index by scanning all installed skills, plugins, MCP servers, and agents. Run this after installing new plugins or periodically to keep recommendations fresh.
First-run setup wizard — build index, download embeddings, curate pipeline-owners for installed plugins.
Enforcement gate that presents the advisor loadout for user approval with 4-option pattern (Sim/Nao/Alterar/Sugerir). Blocks execution until user explicitly chooses. Manages two decision moments (loadout approval + spec generation tool selection) with iteration limits.
Analyzes task context, reads skill cards from the Obsidian vault graph, and recommends an optimal loadout with execution order, context mapping between skills, and pipeline template matching. Returns structured JSON for the /advisor command to render and orchestrate.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
An FX Studio AI plugin for Claude Code
What's new in v0.5.0 (2026-04-27)
Architectural overhaul closing a 10-finding audit. Quality bar lifted from 7.5 → 9+/10 with zero functional regression.
- Hot-path hook 387 → 85 lines. Scoring/fusion/discovery/replay logic extracted into the pure module
lib/advisor-nudge-core.js. Hook is now a true I/O shim. Determinism is provable: same opts + fixednow()→ deeply equalSuggestionResult.- 4 architectural guards CI-enforced on every push and PR: DI-1 (constants module load is fs-pure), DI-2 (no domain code imports from builders), DI-3 (
package.jsonand.claude-plugin/plugin.jsonagree on SemVer), vault env single source (paths.jsno longer reads env directly).- Module-scoped
mtime + sizekeyed cache (lib/mtime-cache.js) memoizes embeddings/graph loaders for long-lived consumers; defeats stale-cache class on coarse filesystems (FAT32, sub-ms CI rebuilds).- Unified filesystem walker (
lib/walk.js) replaces two private walkers in build-index/build-catalog. Side effect: index now visible at 546 entries (up from 163) — the legacy walker was silently dropping skills past its visit-count cap.- Vault env single source.
SKILL_ADVISOR_VAULT_PATHis now canonical; legacySKILL_ADVISOR_VAULTworks with a one-time deprecation warning, removal in 0.6.0.- Performance gate (
npm run test:perf) — ceiling p95 ≤ 250ms + headroom 1.15× baseline, 300 spawns × 2 fixtures, ~60s. Defaultnpm teststays at ~2.3s for fast TDD iteration.- 812 tests (+24% from 654). Full perf gate green: short80 p95 ≈ 170ms, long500 p95 ≈ 157ms.
BREAKING (restorable). Default prompt-length threshold raised 5 → 12. Prompts of 5–11 characters that previously surfaced advisor nudges now silently early-exit. Restore the old behavior with
ADVISOR_PROMPT_LENGTH=5in your shell env.Deprecations (both targeting 0.6.0 removal):
SKILL_ADVISOR_VAULTenv var (useSKILL_ADVISOR_VAULT_PATH);build-index.inferCategoryre-export (uselib/category.inferCategory).See CHANGELOG.md for full migration notes.
TL;DR · Features · Obsidian · How it works · Quickstart · Commands · Changelog
You have 200+ skills installed. You use 10. Skill Advisor finds the other 190 — and knows which ones not to mix.
npx claudepluginhub fernandoxavier02/skill-advisorGenerate self-contained HTML artifacts when output is too dense for markdown chat — comparisons, plans, status reports, post-mortems, flowcharts, explainers, code/PR reviews, kanban boards, config editors, prompt tuners. Includes a curated 17-template library from Thariq Shihipar (Anthropic Claude Code team), 4 trading-domain renderers (backtest comparison, risk dashboard, signal audit, market regime), and 3 spec renderers (Kiro requirements/design/tasks auto-detected). Companion HTML for project .md files via PostToolUse hook and /gen-html slash command. Interactive validation artifacts with clipboard-based response channel (multi-item decision/checkbox/select/text). Self-contained outputs land in .claude/_html/artifacts/.
Generates mandatory engineering rules, architecture contracts, anti-pattern catalogs, and validation tests adapted to any project's stack. 6 focused skills: setup, detect-stack, map-architecture, generate-rules, mine-anti-patterns, validate-context.
Claude Code Swiss Army Knife — diagnose, configure, and build your Claude Code environment. Meta-skill /cc with triage menu + 9 specialized skills for context audit, MCP, hooks, agents, prompts, security, setup, and skill building.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.