prompt-evaluation-runn…
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
Use when the user provides a MarkItDown-supported file or URL and converting it to Markdown first will make inspection easier, cheaper, or more reliable.
$ npx -y skills add yeaight7/agent-powerups --skill markitdown-file-intake --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/markitdown-file-intakeContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when the user provides a MarkItDown-supported file or URL and converting it to Markdown first will make inspection easier, cheaper, or more reliable.
name: markitdown-file-intake description: Use when the user provides a MarkItDown-supported file or URL and converting it to Markdown first will make inspection easier, cheaper, or more reliable.
Convert supported files or URLs into Markdown before inspection. This reduces token cost and makes binary or structured inputs easier to analyze.
Do not use when:
Required tool:
Check:
Get-Command markitdown -ErrorAction SilentlyContinue python -m markitdown --help
Install:
python -m pip install markitdown
Rules:
1. Check whether MarkItDown is available. 2. If missing, tell the user before attempting conversion. 3. Convert with Microsoft MarkItDown or the helper script in `references/`.
markitdown <path-or-url> -o output.md
powershell -ExecutionPolicy Bypass -File "references\convert_with_markitdown.ps1" -Source "<path-or-url>"
4. Confirm output path exists and file is non-empty. 5. Inspect the generated Markdown with narrow reads first. 6. Tell the user MarkItDown was used.
If MarkItDown is missing:
1. Say conversion did not happen. 2. Tell the user Microsoft MarkItDown is required. 3. Ask before installing it. 4. Show the install command. 5. Fall back to manual inspection when practical.
Curated power-ups for coding agents: skills, slash commands, MCP configs, hooks, AGENTS.md templates, and workflows for serious software engineering. Claude Code, Codex, Antigravity CLI, Cursor and more
Repo: yeaight7/agent-powerups
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
Use when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.
Use when designing, running, debugging, or hardening deterministic eval suites for agent skills, prompts, tool workflows, or MCP-backed cases.
Use when designing tool definitions for a new agent or subagent, an agent shows high retry rates, ambiguous tool invocations, or silent failures, or an…
Use when routing a prompt to a local provider CLI for a second opinion, review, or plan -- you are about to call a provider directly, need the response saved…
Use when starting work in an unfamiliar area of a codebase, spawning a subagent that needs targeted file context, a first search pass missed the relevant file,…