Plugins

Persistent memory brain that stops Claude from re-asking and re-deriving. Works with zero extras — SQLite FTS5 fallback if ChromaDB and Ollama are missing.

Grade a completed OpenSpec change with the Spec Quality Index (SQI) — a 0–100 score measuring how cheaply the spec implemented.

Grades a Claude Code session against the 7-dimension vibe-coding rubric; outputs scored JSON + Bahasa Indonesia coaching. v0.6.0 (anti-gaming): bobot rubrik direbalance (15/15/15/18/20/12/5); misses WAJIB ≥2 per sesi → total_score maks 98; score caps deterministik dari work_evidence (sesi pendek/tanpa friksi tertangani dibatasi); deteksi prompt sintetis dari first_user_prompt; scripts/validate.py jadi gerbang mekanis wajib sebelum upload; first_user_prompt dikirim ke leaderboard untuk audit; hard reject transcript non-Claude-Code. v0.5.0: dimensi delegation menilai orkestrasi skill & subagent secara terukur (D1 subagent / D2 skill / D3 MCP) dari sinyal ground-truth (toolUseResult, attributionSkill) yang sukar dipalsukan; sesi tanpa skill+subagent ≤6/15; digest.py emit tool_usage+signal_availability (→ raw_payload, tanpa perubahan BE); laundering compact ditutup; calibration anchor + evidence-first di prompt grader. v0.4.1: file sementara /tmp per-transkrip (fix baca digest basi lintas sesi). v0.4.0: prompt_analysis dikirim, plus usage_totals/type_counts/grademe_version. v0.3.0: mandatory live-session grading, digest.py preprocessing, session_name + compacted, endpoint venturo.pro.

Extract and analyze metrics referenced in Grafana dashboards

Skills and rules for developing and using the Grafana Assistant app and CLI.

Skills and rules for developing and using the Grafana Assistant app and CLI

Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required

Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.

Grafana dashboard creation, management, and quality review for Kubernetes deployments

MCP server for AI-assisted Grafana dashboard, datasource, alerting, and incident management

MCP server for AI-assisted Grafana dashboard, datasource, alerting, and incident management.

Jenkins plugin development with expert-level agents for implementing, reviewing, and testing plugins. Use whenever working on Jenkins hpi/jpi plugins, Pipeline steps, Jelly views, or preparing PRs for jenkinsci.

grāmatr for Claude Code — HTTP transport (browser OAuth).

grāmatr for headless/SSH/remote/devcontainer sessions — device-code auth, no browser loopback.

from The-Focus-AI/claude-marketplace

Grant proposal toolkit: NIH/NSF writing with mechanism-specific templates, structured review with scoring criteria, and figure quality assurance

Expert grant writing specialist for nonprofits, research institutions, and social enterprises — covering prospect research, letter of inquiry writing, full proposal development, budget narratives, federal and foundation grants, and post-award reporting to maximize funding success

面向非营利组织、研究机构和社会企业的资深资助申请书撰写专家——覆盖资助方调研、意向书撰写、完整提案开发、预算叙述、联邦与基金会资助，以及中标后报告，最大化筹款成功率

30+ skills covering the full grant lifecycle: project setup, specific aims, title, budget, significance, innovation, approach, letters of support, timelines, abstracts, biosketches, facilities, data management plans, compliance sections, math/LaTeX notation auditing, mock review, proofreading, references, format check, and resubmission.

NIH grant-funding intelligence skill. RePORTER/NOSI/study-section navigation, R01/R21/K-award strategy. Research-pack convention. Path-B from megaprompt 11.

NIH grant-funding intelligence skill. RePORTER/NOSI/study-section navigation, R01/R21/K-award strategy. Research-pack convention. Path-B from megaprompt 11.

Microsoft Graph Investigator — unified user investigation, mailbox forensics, activity timelines, device correlation, and forensic reporting across all M365 services

Standalone graphify knowledge-graph runner with Obsidian integration. Graph any corpus — a code directory via /graphify, a Supabase database via /graphify-supabase (native --postgres introspection preferred, MCP corpus emit fallback), or the Obsidian vault itself via /graphify-vault (docs-first keyed flow). Obsidian-format exports land back in the MoxyWolf Vault (Projects/<project>/06-Engineering/graphs/ per project, _Shared Knowledge/Vault Graph/ vault-wide) so they cross-link with real notes. Hosts the canonical graphify-core runner protocol (team OpenRouter key per DR-010, two-pass AST-then-label sandbox-safe split, keyless fallback); github-repo-analyzer delegates its Step 0 here.

Knowledge graph hybride — Neo4j + Qdrant + LangGraph. Fournit le MCP graph-server (store/retrieve/relate).

Map any folder (code/docs/PDFs/images/video) into a queryable knowledge graph — tree-sitter AST for code, semantic pass for the rest. From Graphify-Labs/graphify. NOT the same as this account's own anytechie-graphify bar-chart CLI.

Map any folder (code/docs/PDFs/images/video) into a queryable knowledge graph — tree-sitter AST for code, semantic pass for the rest. From Graphify-Labs/graphify. NOT the same as this account's own anytechie-graphify bar-chart CLI.

Map any folder (code/docs/PDFs/images/video) into a queryable knowledge graph — tree-sitter AST for code, semantic pass for the rest. From Graphify-Labs/graphify. NOT the same as this account's own anytechie-graphify bar-chart CLI.

Map any folder (code/docs/PDFs/images/video) into a queryable knowledge graph — tree-sitter AST for code, semantic pass for the rest. From Graphify-Labs/graphify. NOT the same as this account's own anytechie-graphify bar-chart CLI.

Map any folder (code/docs/PDFs/images/video) into a queryable knowledge graph — tree-sitter AST for code, semantic pass for the rest. From Graphify-Labs/graphify. NOT the same as this account's own anytechie-graphify bar-chart CLI.

Build custom HTML dashboards from real data. KB-aware queries, entity wrapping, cached data sources.