ask-ai SKILL.md skillA

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

Install it, pinned
mdr add idaibin/skills/ask-ai@git:20261016.27f8aa1

Pins git:20261016.27f8aa1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
idaibin/skills
Path
skills/ask-ai/SKILL.md
Versions recorded
9
Latest version
git:20261016.27f8aa1, committed Oct 16, 2026
First version recorded
Aug 21, 2026
Size
5,060 bytes
Repository stars
6
License
Apache-2.0

Prepare or obtain a requested external-AI result for review, research, images, cross-review/互审, or a saved instruction such as 进行三方会审.

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 AI

## Entry Gate

Coordinate one explicitly requested, attributable external-AI result. First apply the Codex-first gate; then freeze basis, recipient, authorization, payload boundary, evidence needs, and stop condition. Package-only preparation never authorizes sending.

## Route Map

| Request condition | Read | Result |
| --- | --- | --- |
| Provider/transport/conversation selection | [provider routing](references/provider-routing.md), [provider adapter](references/provider-adapter.md), and applicable provider reference | Verified route or safe stop |
| Package-only review composition | [review prompts](references/review-prompts.md) | Redacted review package; no send/capture/feedback route |
| Research composition | [research profiles](references/research-profiles.md) | Bounded research package/profile |
| Returned external content is being inspected | [untrusted content](references/untrusted-content.md) | Quarantined attributed result |
| An authorized round completed and feedback recording is enabled | [feedback recording](references/feedback-recording.md) | Reconciled feedback record |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add idaibin/skills/ask-ai@sha256:063e706d78b6a9cf

The line at the top of this page pins the label git:20261016.27f8aa1, 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_kl46gjlftwvmycry.svg)](https://markdownregistry.com/a/art_kl46gjlftwvmycry)

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

Versions

The registry has recorded 9 versions of this file, between Aug 21, 2026 and Oct 16, 2026, about one every 7 days.

versioncommittedcommitsizeaudit
git:20261016.27f8aa1 latest2026-10-16 27f8aa1 5,060 BA view · diff
git:20260917.5cfe6d92026-09-17 5cfe6d9 4,837 BA view · diff
git:20260915.786dca62026-09-15 786dca6 4,980 BA view · diff
git:20260915.3d7652b2026-09-15 3d7652b 5,025 BA view · diff
git:20260910.bcfbdae2026-09-10 bcfbdae 13,716 BA view · diff
git:20260825.ab7b1dd2026-08-25 ab7b1dd 13,600 BA view · diff
git:20260825.9f688232026-08-25 9f68823 13,577 BA view · diff
git:20260825.693f6842026-08-25 693f684 17,924 BA view · diff
git:20260821.55738772026-08-21 5573877 16,168 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 (5060 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

idaibin/skills · 6 stars · license Apache-2.0 · pushed 2026-10-31 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_kl46gjlftwvmycry
GET https://markdownregistry.com/api/v1/resolve?ref=idaibin/skills/ask-ai
GET https://markdownregistry.com/api/v1/blob/063e706d78b6a9cfc418834005652ede9aff17fd80c2f2ac1d18a716bb27c2eb

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 idaibin/skills

AGENTS.md AGENTS.md file
idaibin/skills · AGENTS.md
git:20261028.13cd0a1 · audit A · 6 stars
CLAUDE.md CLAUDE.md file
idaibin/skills · CLAUDE.md
git:20260715.9c7f648 · audit B · 6 stars
AGENTS.md@evals/fixtures/live-agent-dev-frontend AGENTS.md file
idaibin/skills · evals/fixtures/live-agent-dev-frontend/AGENTS.md
git:20260825.89e0fad · audit A · 6 stars
AGENTS.md@skills AGENTS.md file
idaibin/skills · skills/AGENTS.md
git:20260915.3d7652b · audit A · 6 stars
CLAUDE.md@skills CLAUDE.md file
idaibin/skills · skills/CLAUDE.md
git:20260715.9c7f648 · audit B · 6 stars
api-spec SKILL.md skill
idaibin/skills · skills/api-spec/SKILL.md · Design or validate API wire contracts after business acceptance, or reconstruct API source evidence as an observed…
git:20261027.597900d · audit A · 6 stars
dev-frontend SKILL.md skill
idaibin/skills · skills/dev-frontend/SKILL.md · Implement frontend UI changes in the existing stack. Route change-based reviews to repo-review and existing-surface…
git:20261028.15e45f5 · audit A · 6 stars
dev-java SKILL.md skill
idaibin/skills · skills/dev-java/SKILL.md · Implement Java source and Java-owned Maven or Gradle changes.
git:20261024.5c473ea · audit A · 6 stars
dev-rust SKILL.md skill
idaibin/skills · skills/dev-rust/SKILL.md · Implement, port, or refactor Rust source, including native Rust UI, in the existing Cargo workspace.
git:20261024.c756a4b · audit A · 6 stars
dev-tests SKILL.md skill
idaibin/skills · skills/dev-tests/SKILL.md · Plan risk-based coverage and execute functional acceptance across backend, APIs, pages, UI, business logic and…
git:20261028.08afd8b · audit A · 6 stars
dev-typescript SKILL.md skill
idaibin/skills · skills/dev-typescript/SKILL.md · Implement non-browser TypeScript or JavaScript changes for Node.js, Bun, or Deno.
git:20261026.51560c7 · audit A · 6 stars
domain-modeling SKILL.md skill
idaibin/skills · skills/domain-modeling/SKILL.md · Resolve shared business terms, rules, and lifecycle ambiguity; use product-spec for feature-local behavior.
git:20260917.5cfe6d9 · audit A · 6 stars

Every file in idaibin/skills

Other files named ask-ai

ask-ai SKILL.md skill
farming-labs/docs · examples/astro/.agents/skills/ask-ai/SKILL.md · Configure the Ask AI (RAG-powered AI chat) in @farming-labs/docs. Use when enabling AI chat, setting mode (search vs…
git:20260309.c3e6c67 · audit B · 53 stars
ask-ai SKILL.md skill
farming-labs/docs · skills/farming-labs/ask-ai/SKILL.md · Configure the Ask AI (RAG-powered AI chat) in @farming-labs/docs. Use when enabling AI chat, setting mode (search vs…
git:20260801.728cb8b · audit B · 53 stars

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