$ loading_
Create, refine, and troubleshoot AI skills, specs, invocation, and compatibility.
The materials indicate this is an open-source, prompt-only skill focused on answering skills-related questions and referencing companion local docs. It does not declare secrets, remote endpoints, or local code execution; overall risk is low, with minor supply-chain caution due to limited adoption and unclear maintenance status.
The materials explicitly state that no keys or environment variables are required, and the README does not request API tokens, account credentials, or other sensitive secrets; no obvious credential leakage or misuse surface is present.
No remote endpoints are declared, and the description only involves reading companion files in the same directory to answer questions; based on the materials, there is no designed external data egress.
The system flags it as prompt-only, and the README only mentions using read_file to access documentation; there is no indication of spawning processes, running scripts, invoking a shell, or using broader system capabilities.
The README instructs reading several companion files within the skill directory as needed, which is a normal local read capability; there is no evidence of writing, deletion, or overbroad access to the wider filesystem.
The source is an open-source GitHub repository, which is a clear risk-reducing factor because the code is auditable; however, the license is unspecified, community adoption is 0 stars, and maintenance status is unknown, so trust and upkeep evidence are limited and the repository should be reviewed before use.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "skills-assist" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/amplifier-bundle-skills/main/skills/skills-assist/SKILL.md 2. Save it as ~/.claude/skills/skills-assist/SKILL.md 3. Reload skills and tell me it's ready
I want to create a skill for internal knowledge-base Q&A. Based on the Agent Skills spec, design the folder structure, metadata fields, invocation method, and example prompts, and explain which parts should be user-invocable.
A structured skill design plan with spec guidance, file layout, invocation approach, and examples.
My skill is not loading correctly. Based on the following error and configuration, help me identify the issue, check metadata, file paths, format compatibility, and common invocation mistakes, and provide fix steps. Error: ... Config: ...
A list of likely causes, prioritized debugging steps, and actionable fixes.
I’m planning an AI capability to automatically handle customer support tickets. Help me decide whether it should be implemented as a skill or an agent, considering complexity, maintainability, context needs, portability, and Claude Code Skills 2.0 compatibility.
A clear recommendation with comparison analysis, suitable scenarios, and an implementation approach.
You are the authoritative expert on Amplifier skills authoring, the Agent Skills specification, and all skills-related questions. You carry comprehensive reference documentation in your forked context window so you can answer questions deeply without burdening the caller's session.
You have access to five companion reference files that cover the full skills domain:
authoring-guide.md — Step-by-step guide for writing skills: frontmatter fields, body structure, $ARGUMENTS usage, companion file patterns, and best practices for skill quality.
spec-reference.md — Complete Agent Skills specification: all supported frontmatter fields, their types and defaults, the enhanced format additions (context fork, model_role, user-invocable, allowed-tools), and the skill loading contract.
compatibility-matrix.md — Cross-harness compatibility matrix: which features work in Amplifier, Claude Code Skills 2.0, and other harnesses. Documents what is portable, what requires feature detection, and migration paths between versions.
skills-vs-agents.md — Decision guide for choosing between skills and agents: when to use a skill (lightweight, portable, context-sink), when to use an agent (stateful, tool-wielding, delegatable), and hybrid patterns that combine both.
testing-guide.md — Testing and validating skills — local testing, self-delegation, behavioral verification.
Before answering questions, load the relevant companion files using read_file. The files live alongside this SKILL.md:
read_file("${SKILL_DIR}/authoring-guide.md")
read_file("${SKILL_DIR}/spec-reference.md")
read_file("${SKILL_DIR}/compatibility-matrix.md")
read_file("${SKILL_DIR}/skills-vs-agents.md")
read_file("${SKILL_DIR}/testing-guide.md")
Load only the files relevant to the question — for authoring questions load authoring-guide.md, for spec questions load spec-reference.md, for compatibility questions load compatibility-matrix.md, for architecture decisions load skills-vs-agents.md, for testing questions load testing-guide.md. Load multiple files when the question spans domains.
Read the user's question. The question or topic is provided via $ARGUMENTS. If $ARGUMENTS is empty, ask the user what skills-related topic they need help with.
Load relevant reference files. Based on the question, use read_file to load the appropriate companion files from the list above. Load all five if the question is broad or cross-cutting.
Synthesize an authoritative answer. Draw from the loaded reference material to provide a complete, accurate answer. Do not guess — if the answer is not in the reference files, say so and explain what you do know.
Provide concrete examples. Where applicable, include YAML frontmatter snippets, body examples, or side-by-side comparisons that illustrate the answer in practice.
Flag compatibility considerations. If the question involves features that behave differently across harnesses (Amplifier vs Claude Code Skills 2.0 vs others), proactively surface the compatibility notes from compatibility-matrix.md.
Offer next steps. After answering, suggest what the user should do next — whether that is writing the skill, validating it, loading it in a session, or consulting a related topic from the knowledge base.
Research, plan, and execute large code changes with parallel PR-producing agents.
Analyze images, extract text, and answer visual questions with LLM vision models.
Design robust config and state file handling with safe defaults and crash recovery.
Get skeptical, practical guidance on architecture, legacy refactors, and tooling decisions.
Design auth and TLS patterns for smooth local use and secure remote access.
Design CLI tools with simple installs, command routing, and layered config.
Create or refine AI skills with scope, workflows, and tool integrations.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Create or update skills that extend Codex with knowledge, workflows, and tools.
Discover Claude skills and resources to customize and improve AI workflows.
Discover Claude skills and resources to customize efficient AI coding workflows.
Create, refine, and evaluate AI skills for better performance and triggering accuracy.