ask-claude SKILL.md skillA

ask-claude from stevepolitodesign/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add stevepolitodesign/skills/ask-claude@git:20261014.fe9e53f

Pins git:20261014.fe9e53f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
stevepolitodesign/skills
Path
ask-claude/SKILL.md
Versions recorded
1
Latest version
git:20261014.fe9e53f, committed Oct 14, 2026
Size
8,070 bytes
Repository stars
5
License
none declared

Recommend the best way to have Claude do something, checked against Anthropic's current docs, then write the prompt and run it once approved. Use when someone asks how they should prompt you, what the best way to ask for something is, or which Claude feature fits a job (CLAUDE.md, skill, hook, subagent, workflow, plan mode, /goal, MCP, headless, the API), even if they don't name a feature.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Ask Claude

Two questions sound different and are the same question: how should I ask Claude to
do this?

- "Users can't sign up." The answer is a way of working (reproduce first, plan or
  don't, what proves it's fixed) and a prompt that says it.
- "Run rubocop after every edit." The answer is a feature. A line in CLAUDE.md gets
  followed most of the time. A hook runs every time. Picking wrong means it quietly
  doesn't happen.

Either way, end with a prompt the user approves before anything runs.

```
task
  |
  v
1. look ...... the code and setup the task touches
2. read ...... the docs that apply, fetched now
3. ask ....... only what neither can tell you
4. recommend . the approach, why, and the prompt, shown for approval
5. run ....... here, as written
```

Two ways this fails. The answer comes from memory, and recommends a feature that's
been renamed, or misses the one released last month that fits better. Or the prompt
restates the task in more words and adds nothing the agent couldn't have guessed.

## 1. Look

The task is `$ARGUMENTS`, or ask for one.

Skim the README, the routes, the area the task names, recent commits there. You're
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add stevepolitodesign/skills/ask-claude@sha256:47efb6c6515d90ef

The line at the top of this page pins the label git:20261014.fe9e53f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_sgfr52ffbq4tmcyn.svg)](https://markdownregistry.com/a/art_sgfr52ffbq4tmcyn)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 14, 2026.

versioncommittedcommitsizeaudit
git:20261014.fe9e53f latest2026-10-14 fe9e53f 8,070 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8070 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

stevepolitodesign/skills · 5 stars · license none declared · pushed 2026-10-14 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_sgfr52ffbq4tmcyn
GET https://markdownregistry.com/api/v1/resolve?ref=stevepolitodesign/skills/ask-claude
GET https://markdownregistry.com/api/v1/blob/47efb6c6515d90efb99d9b86a7c89776bf0cdf6161872d1cf59931c1c60a3f64

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from stevepolitodesign/skills

commit SKILL.md skill
stevepolitodesign/skills · commit/SKILL.md · Commit the current changes as atomic commits, recording risks, tradeoffs, and alternatives considered.
git:20260925.01f2dea · audit A · 5 stars
diff-explainer SKILL.md skill
stevepolitodesign/skills · diff-explainer/SKILL.md · Builds a shareable HTML walkthrough of the current changes, highlighting risks, tradeoffs, and alternatives considered.
git:20260924.62cef2e · audit A · 5 stars
domain-model SKILL.md skill
stevepolitodesign/skills · domain-model/SKILL.md · Turn a described business process into a domain model.
git:20260915.6a51426 · audit A · 5 stars
eli5 SKILL.md skill
stevepolitodesign/skills · eli5/SKILL.md · Explain something to someone who knows nothing about it.
git:20260916.9c9c896 · audit A · 5 stars
implement-with-tdd SKILL.md skill
stevepolitodesign/skills · implement-with-tdd/SKILL.md · Implement a SPEC, plan, or feature outside-in, with TDD.
git:20260916.114dbbf · audit A · 5 stars
multi-lens-review SKILL.md skill
stevepolitodesign/skills · multi-lens-review/SKILL.md · Review a change for defects, then against its spec, its codebase's conventions, the domains trying to emerge from it…
git:20260926.c0ccd57 · audit A · 5 stars
pr SKILL.md skill
stevepolitodesign/skills · pr/SKILL.md · Open a pull request whose description you write yourself, with a suggested title and a light proofread.
git:20260925.20cc0dd · audit A · 5 stars
preparatory-refactor SKILL.md skill
stevepolitodesign/skills · preparatory-refactor/SKILL.md · Identify opportunities to introduce a refactor that would make a feature easy to implement.
git:20260926.c0ccd57 · audit A · 5 stars
rubber-duck SKILL.md skill
stevepolitodesign/skills · rubber-duck/SKILL.md · Start a rubber duck session.
git:20260926.c0ccd57 · audit A · 5 stars
ship SKILL.md skill
stevepolitodesign/skills · ship/SKILL.md · Implement, veryify and review a feature based on its SPEC.
git:20261005.9d75f07 · audit A · 5 stars
slice SKILL.md skill
stevepolitodesign/skills · slice/SKILL.md · Cut a feature or idea down to one full-stack slice.
git:20260926.c0ccd57 · audit A · 5 stars
trace SKILL.md skill
stevepolitodesign/skills · trace/SKILL.md · Run a scenario and record what actually happened.
git:20260928.afcb292 · audit A · 5 stars

Every file in stevepolitodesign/skills

Other files named ask-claude

ask-claude SKILL.md skill
hiroro-work/claude-plugins · skills/ask-claude/SKILL.md · Asks Claude CLI for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating…
git:20260626.678ec80 · audit A · 47 stars
ask-claude SKILL.md skill
yeaight7/agent-powerups · skills/ask-claude/SKILL.md · Use when a Codex or generic local agent needs a focused second opinion from Claude CLI without MCP routing.
git:20260429.498f026 · audit A · 6 stars

Browse by kind, by grade A, or by owner.