wardawgmalvicious/agent-config

Skills, coding rules, hooks, a subagent and MCP templates for coding agents — day-to-day Microsoft Fabric, Power BI and Azure work.

This repository also configures its own agents. See what agent-config tells them →

1Stars on the repository
44Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

author-skill

01

wardawgmalvicious/agent-config

Skill Claude Code

Author a new skill for this repo end to end — take a topic, check for existing coverage, drill the official docs behind it, write a filled handoff brief to docs/handoffs/, then draft the SKILL.md and run the post-draft checks. Use when asked to write, author, create, or scaffold a new skill, or when a drift-audit…

not rated 1 changed yesterday A 212 tokens original MIT

code-review

02

wardawgmalvicious/agent-config

Skill Claude Code

Review code for correctness, naming conventions, style, error handling, security, and scaling concerns. Use when reviewing code, checking a diff, auditing a function, or asking about code quality. Covers Python, PySpark, SQL, KQL, DAX, and data-engineering patterns.

not rated 1 changed 10d ago A 61 tokens original MIT

commit

03

wardawgmalvicious/agent-config

Skill Claude Code

Splits working-tree changes into logical, self-consistent commits (ordering so nothing dangles, stepping files that straddle commits through intermediate states), writes conventional-commit messages (feat/fix/docs/refactor/chore) with motivation in the body, stages explicit paths only, uses git mv for renames, never…

not rated 1 changed yesterday A 162 tokens original MIT

drift-audit

04

wardawgmalvicious/agent-config

Skill Claude Code

Audit registered upstream docs sources for drift since a prior commit SHA or date — detect new GA / preview features, syntax additions, deprecations, and harness or tooling changes that affect existing skills, rules, CLAUDE.md, settings.json, hooks, or the MCP templates. Sources live in a registry…

not rated 1 changed yesterday A 217 tokens original MIT

drift-handoff

05

wardawgmalvicious/agent-config

Skill Claude Code needs its repo

Turn a completed drift-audit report into handoff briefs on disk. Use immediately after a /drift-audit run, or when the user asks to prepare handoffs, write up the findings, or capture the recommended actions from an audit. Writes one directory per run — docs/audits/ / / — holding the audit report verbatim as…

not rated 1 changed yesterday A 154 tokens original MIT

drift-update

06

wardawgmalvicious/agent-config

Skill Claude Code needs its repo

Execute the handoff briefs a /drift-handoff run wrote to docs/audits/ / / — apply each brief's edits, run its own verification steps, and stamp it done. Reads briefs from disk and never from the conversation, so it runs cold in a fresh session (preferred) or warm straight after /drift-audit and /drift-handoff. Walks…

not rated 1 changed yesterday A 174 tokens original MIT

fabric-database

07

wardawgmalvicious/agent-config

Skill Claude Code

Use when working with Fabric SQL Database — the Azure SQL Database hosted inside a Fabric workspace. Key point: this is a DIFFERENT engine from Fabric Warehouse and does NOT share its restrictions. nvarchar/datetime/money/triggers/ALTER COLUMN/recursive CTEs/FOR XML/temporal tables/full-text search all work. Entra ID…

not rated 1 changed 6d ago A 104 tokens original MIT

fabric-eventhouse

08

wardawgmalvicious/agent-config

Skill Claude Code

Use for Microsoft Fabric Eventhouse / KQL Database. Covers connection (cluster URI via kqlDatabases REST, kusto.kusto.windows.net audience, az rest temp-file for | escaping), authoring (.create-merge for safe schema evolution, ingestion inline/set-or-append/from-storage ;impersonate, streaming policy, CSV/JSON…

not rated 1 changed 2d ago A 251 tokens original MIT

fabric-eventstream

09

wardawgmalvicious/agent-config

Skill Claude Code

Use for Microsoft Fabric Eventstream — the streaming-ingestion item routing CDC / Event Hubs / Kafka / IoT / HTTP / MQTT events into Lakehouse, Eventhouse, Activator, or derived streams, and producing events to a schema-associated custom endpoint. Covers source connectors (Azure SQL / SQL MI / PostgreSQL / MySQL /…

not rated 1 changed 6d ago A 237 tokens original MIT

wardawgmalvicious/agent-config

Skill Claude Code

Use for Microsoft Fabric Real-Time Dashboards (KQLDashboard item) — authoring or editing RealTimeDashboard.json by hand or via Git: file anatomy (queries[] holds all KQL text; tiles reference it by queryRef.queryId; baseQueries are {id, variableName, queryId} wired through usedVariables), load-time validation (every…

not rated 1 changed yesterday A 234 tokens original MIT

fabric-rest-api

11

wardawgmalvicious/agent-config

Skill Claude Code

Use when calling the Microsoft Fabric or Power BI REST APIs, authenticating to them or running the Fabric CLI fab — tokens and audiences, az login and az rest, a service principal's tenant settings and workspace roles, workspaces and items, item IDs, definitions, long-running operations, pagination, jobs and…

not rated 1 changed 5d ago A 128 tokens original MIT

fabric-security

12

wardawgmalvicious/agent-config

Skill Claude Code

Use for the Fabric security/permission model. Covers the layers (workspace roles Admin/Member/Contributor/Viewer, item-level Read/ReadData/ReadAll, OneLake security data access roles, SQL GRANT/DENY/REVOKE), Admin/Member/Contributor bypass of RLS/CLS/DDM, least-privilege pattern (item share + SQL GRANT; a Viewer…

not rated 1 changed 5d ago A 191 tokens original MIT

fabric-spark

13

wardawgmalvicious/agent-config

Skill Claude Code

Use for Spark in Microsoft Fabric: a notebook (a .Notebook folder), PySpark or Spark SQL, a lakehouse and its tables, a Spark job definition or environment; a Spark job that is slow, queued or failed, Livy sessions or the Spark History Server; error handling in notebook code; a materialized lake view (MLV); or AI…

not rated 1 changed 6d ago A 83 tokens original MIT

fabric-tmdl

14

wardawgmalvicious/agent-config

Skill Claude Code

TMDL (Tabular Model Definition Language) authoring rules for Fabric and Power BI semantic models. Use when editing .tmdl files, adding measures or columns to a semantic model, defining relationships or calculation groups, working in a PBIP definition/ folder, configuring Direct Lake partitions, writing a model's AI…

not rated 1 changed 6d ago A 129 tokens original MIT

wardawgmalvicious/agent-config

Skill Claude Code

Use for Microsoft Fabric Variable Library — config-as-code for parameterizing notebooks and pipelines per environment. Covers definition parts (variables.json, settings.json, valueSets/ .json — no format field, omit it), variable types (String, Boolean, Number, Integer, DateTime, Guid, ItemReference…

not rated 1 changed 5d ago A 233 tokens original MIT

wardawgmalvicious/agent-config

Skill Claude Code

Use for monitoring Fabric Warehouse queries — OPTION (LABEL = '...') for tracking, the queryinsights schema (execrequestshistory, execsessionshistory, longrunningqueries, frequentlyrunqueries), 30-day retention, 15-minute appearance lag, the Invalid object name gotcha on newly-created warehouses, and diagnosing…

not rated 1 changed 6d ago A 102 tokens original MIT

fabric-warehouse

17

wardawgmalvicious/agent-config

Skill Claude Code

Use for T-SQL against Fabric Warehouse (NOT Fabric SQL Database — see fabric-database). Covers unsupported types (nvarchar/datetime/money/xml/tinyint/hierarchyid), unsupported features (FOR XML, recursive CTEs, triggers, CREATE USER, cursors), MERGE (GA Jan 2026), ALTER COLUMN (preview), schema evolution (ADD nullable…

not rated 1 changed 5d ago A 272 tokens original MIT

learn

18

wardawgmalvicious/agent-config

Skill Claude Code

Routes a session learning into the durable guidance that should have covered it — a SKILL.md and its references/, a path-scoped rule, a CLAUDE.md — rather than into auto-memory. Reconstructs which skills and rules were actually loaded instead of asking, checks existing coverage before writing, verifies the learning…

not rated 1 changed yesterday B 175 tokens original MIT

wardawgmalvicious/agent-config

Skill Claude Code needs its repo

Use when working with PBIP (Power BI Project) folders — the text-based developer format that replaces binary .pbix. Covers folder layout (.SemanticModel/, .Report/, definition/, StaticResources/), entry-point files (.pbip, .pbir, .pbism, .platform), byPath vs byConnection (thick vs thin report), .pbism version 4.2 /…

not rated 1 changed 5d ago A 211 tokens original MIT

wardawgmalvicious/agent-config

Skill Claude Code

Use for any work on a Power BI report in PBIR format, a .Report folder: building one on a published semantic model, laying out its pages and visuals, filters, bookmarks, themes and conditional formatting, by the pbir CLI (pbir-cli) or by hand-editing visual.json, page.json, pages.json, report.json…

not rated 1 changed 6d ago A 120 tokens original MIT

wardawgmalvicious/agent-config

Skill Claude Code

Use for Microsoft Fabric Data Pipeline item definitions in Git — pipeline-content.json, .platform, .schedules. Covers the envelope (properties.activities, plus the parameters, variables and libraryVariables the REST schema omits), dependsOn conditions, the activity-type enum and Fabric-specific typeProperties…

not rated 1 changed 5d ago A 225 tokens original MIT

wardawgmalvicious/agent-config

Skill Claude Code

Audit an existing Power BI or Fabric semantic model and report on its shape, relationship health, memory cost and downstream readiness — a review of a finished model, not authoring guidance. Use when asked to audit, review, assess or health-check a semantic model, to judge whether one is a real star schema, to explain…

not rated 1 changed 6d ago A 193 tokens original MIT

land

23

wardawgmalvicious/agent-config

Skill Claude Code

Takes a committed branch from local to merged — pushes it, confirms which GitHub account each tool actually acts as in this repo, opens the PR through the one that matches (github-mcp where loaded, gh where its login is confirmed), then integrates it into main, reports CI, and deletes the merged branch locally and on…

not rated 1 changed yesterday B 178 tokens original MIT

test-skill

24

wardawgmalvicious/agent-config

Skill Claude Code needs its repo

Validate a drafted skill — write its trigger fixtures, update the activation contract table, run the static and real-path activation tests, then behaviourally test it in a cold session against a --safe-mode baseline. Reads its inputs from disk — brief or shipped frontmatter — so it runs cold. Encodes the traps that…

not rated 1 changed yesterday A 204 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: