Skill reviews

AgentX forum: create posts, comments, likes, reposts, follows, attachments. Use when posting to the Starchild AgentX forum, not Twitter (e.g. share a project on AgentX, comment on

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Convert local Markdown files to Feishu (Lark) documents with automatic image uploading. Uses the feishu-docx CLI tool.

• References files that are not bundled: mermaid-architecture-overview.png
• The skill tells the model to perform an irreversible action with no human approval
• 1 referenced file(s) missing: mermaid-architecture-overview.png

Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

This skill should be used when the user wants to "run an evaluation", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize a

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Migrate a Grafana plugin to React 19 compatibility. Use when the user asks to update a plugin for React 19, prepare for React 19, fix React 19 compatibility, upgrade to React 19, m

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Programmatic canvas toolkit for creating, editing, and refining Excalidraw diagrams via MCP tools with real-time canvas sync. Use when an agent needs to (1) draw or lay out diagram

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Plan and execute Google Workspace operations across Docs, Sheets, Slides, Drive, Gmail, Calendar, Forms, Chat, and Admin SDK by choosing the right surface first: Apps Script, direc

• The skill tells the model to perform an irreversible action with no human approval
• 5 test cases, all positive: not one "should refuse" or "should ask first"
• No test case covers injection arriving through data

Migrate MSTest v1 or v2 test project to MSTest v3. Use when user says "upgrade MSTest", "upgrade to MSTest v3", "migrate to MSTest v3", "update test framework", "modernize tests",

• 10 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (21 tags): a typed call is more reliable

Command-line interface for Blender - A stateful command-line interface for 3D scene editing, following the same patterns as the GIMP CLI ...

• 10 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill

Command-line interface for Shotcut - A stateful command-line interface for video editing, built on the MLT XML format. Designed for AI ag...

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (10 tags): a typed call is more reliable
• No condition that starts the skill

Salesforce Data Cloud Prepare phase. TRIGGER when: user creates or manages Data Cloud data streams, DLOs, transforms, or Document AI configurations, or asks about ingestion into Da

• References files that are not bundled: ../sf-datacloud-connect/SKILL.md, ../sf-datacloud-harmonize/SKILL.md, ../sf-datacloud-retrieve/SKILL.md
• The skill tells the model to perform an irreversible action with no human approval
• 6 referenced file(s) missing: ../sf-datacloud-connect/SKILL.md, ../sf-datacloud-harmonize/SKILL.md, ../sf-datacloud-retrieve/SKILL.md

Use when user requests diagrams, flowcharts, sequence diagrams, class diagrams, component diagrams, ER diagrams, architecture charts, or visualizations — including generating a dia

• 11 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Use when the user requests diagrams, flowcharts, architecture diagrams, ER diagrams, UML / sequence / class diagrams, network topology, ML/DL model figures (Transformer/CNN/LSTM),

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes. Also checks prerequisit

• References files that are not bundled: ../agents-build/references/vpc.md, ../agents-harden/references/limits.md, ../agents-build/references/memory.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 21 top-level sections: this looks like several domains in one skill

MUST be used whenever fixing performance issues in a Flows app. This skill finds AND fixes performance problems — re-renders, inefficient queries, missing pagination, unbounded fet

• 12 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Set up NuGet trusted publishing (OIDC) on a GitHub Actions repo — replaces long-lived API keys with short-lived tokens. USE FOR: trusted publishing, NuGet OIDC, keyless NuGet publi

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (5 tags): a typed call is more reliable

You must use this when producing any research prose — literature reviews, syntheses, analyses, methodology descriptions, discussion sections, abstracts, or any written output inten

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (6 tags): a typed call is more reliable
• Does not say what the result is

Teneo CLI — 39 commands for browse & query network agents, send commands to agents, room management, deploy & manage your own agents, wallet management, daemon & updates. Query net

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 21 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Encrypted backup and restore for OpenClaw Agent workspace files (SOUL.md, MEMORY.md, IDENTITY.md, AGENTS.md, TOOLS.md). Uses tar + openssl (AES-256-CBC) encryption and soul-upload.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo",

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (4 tags): a typed call is more reliable
• Does not say what the result is

Identifies anti-patterns specific to amplihack philosophy. Use when reviewing code for quality issues or refactoring. Detects: over-abstraction, complex inheritance, large function

• 13 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill

Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relatio

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Comprehensive security and correctness audit of a branch's changes. Use for thermo nuclear, thermonuclear, or deep review requests, or branch/PR diff audits focused on bugs, breaki

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Build and manage advisory fee billing operations from fee schedule design through calculation, collection, revenue recognition, and compliance disclosure. Use when the user asks ab

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Prepare Azure apps for deployment (infra Bicep/Terraform, azure.yaml, Dockerfiles). Use for create/modernize or create+deploy; not cross-cloud migration (use azure-cloud-migrate).

• References files that are not bundled: references/services/sql-database/bicep.md, references/services/functions/durable.md, references/specialized-routing.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval