system-investigate SKILL.md skillA

system-investigate from yarlson/yarstack is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add yarlson/yarstack/system-investigate@git:20261017.2f2e03b

Pins git:20261017.2f2e03b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
yarlson/yarstack
Path
plugins/yarstack/skills/system-investigate/SKILL.md
Versions recorded
5
Latest version
git:20261017.2f2e03b, committed Oct 17, 2026
First version recorded
Aug 6, 2026
Size
8,333 bytes
Repository stars
3
License
MIT

Investigate an underdefined product, codebase, architecture, integration, or operational question through read-only repository tracing, bounded runtime evidence, and current public research. Use when the user wants to validate suspected behavior, explain why it occurs, compare plausible designs for existing behavior, or recommend the smallest safe change before planning or implementation; not for designing a new system or feature, which belongs to system-design.

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

# System Investigation

Own one investigation from the user's question to an evidence-backed verdict and practical next step. Treat the prompt as a hypothesis, repository and runtime evidence as authority, and implementation as out of scope.

## Establish the investigation

1. Extract the question, suspected behavior, affected system, decision it informs, and requested terminal result.
2. Stop and route to `system-design` when the question asks how to build behavior that does not exist yet, such as a greenfield system or a new capability. Investigate only behavior the repository, runtime, or public sources can show.
3. Write one explicit investigation goal and stopping condition. Use a persisted goal when the host supports it; mark it complete only after the evidence answers the question or proves a precise blocker.
4. State the working hypothesis without treating it as fact. Record plausible alternatives that would materially change the conclusion.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add yarlson/yarstack/system-investigate@sha256:72bfb5b7096ca439

The line at the top of this page pins the label git:20261017.2f2e03b, 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_wa62bm37wfqnejkl.svg)](https://markdownregistry.com/a/art_wa62bm37wfqnejkl)

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

Versions

The registry has recorded 5 versions of this file, between Aug 6, 2026 and Oct 17, 2026, about one every 18 days.

versioncommittedcommitsizeaudit
git:20261017.2f2e03b latest2026-10-17 2f2e03b 8,333 BA view · diff
git:20261017.f6694412026-10-17 f669441 8,298 BA view · diff
git:20260903.c5d000e2026-09-03 c5d000e 8,196 BA view · diff
git:20260903.27a87ef2026-09-03 27a87ef 7,737 BA view · diff
git:20260806.527073b2026-08-06 527073b 7,462 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 (8333 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

yarlson/yarstack · 3 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wa62bm37wfqnejkl
GET https://markdownregistry.com/api/v1/resolve?ref=yarlson/yarstack/system-investigate
GET https://markdownregistry.com/api/v1/blob/72bfb5b7096ca439c02b10fb8cc0af454a20f0e7fa2a1752ed81fa68e7d88df2

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 yarlson/yarstack

AGENTS.md AGENTS.md file
yarlson/yarstack · AGENTS.md
git:20261104.08c2224 · audit A · 3 stars
CLAUDE.md CLAUDE.md file
yarlson/yarstack · CLAUDE.md
git:20260717.2071067 · audit B · 3 stars
AGENTS.md@plugins/yarbrain/cli AGENTS.md file
yarlson/yarstack · plugins/yarbrain/cli/AGENTS.md
git:20261104.08c2224 · audit A · 3 stars
CLAUDE.md@plugins/yarbrain/cli CLAUDE.md file
yarlson/yarstack · plugins/yarbrain/cli/CLAUDE.md
git:20261103.b9ed862 · audit B · 3 stars
lesson-gate SKILL.md skill
yarlson/yarstack · plugins/yarbrain/skills/lesson-gate/SKILL.md · Judge one Yarbrain lesson by id as the independent gate and record the verdict. Use only inside a fresh-context gate…
git:20261104.08c2224 · audit A · 3 stars
lesson-record SKILL.md skill
yarlson/yarstack · plugins/yarbrain/skills/lesson-record/SKILL.md · Record reusable know-how from this session as a proposed Yarbrain lesson, report whether a used lesson worked, convert…
git:20261104.08c2224 · audit A · 3 stars
alternatives-explore SKILL.md skill
yarlson/yarstack · plugins/yarstack/skills/alternatives-explore/SKILL.md · Generate materially different approaches to a product, workflow, or system problem, compare them with the conventional…
git:20261017.2f2e03b · audit A · 3 stars
architecture-refine SKILL.md skill
yarlson/yarstack · plugins/yarstack/skills/architecture-refine/SKILL.md · Settle open product or system architecture decisions with the user, one question at a time, before a plan or contract…
git:20261017.2f2e03b · audit A · 3 stars
behavior-implement SKILL.md skill
yarlson/yarstack · plugins/yarstack/skills/behavior-implement/SKILL.md · Implement one observable behavior or bug fix with red-green-refactor, writing a focused test that fails first, the…
git:20261017.2f2e03b · audit A · 3 stars
bug-report-reproduce SKILL.md skill
yarlson/yarstack · plugins/yarstack/skills/bug-report-reproduce/SKILL.md · Reproduce a user, customer, or support-reported problem with synthetic data, prove the cause with a temporary test…
git:20261017.2f2e03b · audit A · 3 stars
change-cleanup-review SKILL.md skill
yarlson/yarstack · plugins/yarstack/skills/change-cleanup-review/SKILL.md · Review a complete change for unwanted scope, duplicate or leftover artifacts, churn or prose that hides the change…
git:20261017.2f2e03b · audit A · 3 stars
changes-explain SKILL.md skill
yarlson/yarstack · plugins/yarstack/skills/changes-explain/SKILL.md · Explain a pull request, commit range, branch, or local diff from a system-design perspective. Use for practical…
git:20261017.2f2e03b · audit A · 3 stars

Every file in yarlson/yarstack

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