technical-research SKILL.md skillA

technical-research from i9wa4/dotfiles is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add i9wa4/dotfiles/technical-research@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
i9wa4/dotfiles
Path
skills/technical-research/SKILL.md
Versions recorded
5
Latest version
v1.0.0, committed Sep 4, 2026
First version recorded
Jul 5, 2026
Size
1,754 bytes
Repository stars
12
License
MIT

USE FOR: Verifying technical claims, comparing options, and investigating unfamiliar libraries/APIs/tools with cited, confidence-rated evidence. DO NOT USE FOR: implementation, opinion without evidence, or tasks better served by a narrower repo-specific skill (e.g. `data-platform`, `dev-platform-workflow`).

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

# Technical Research

Owns evidence-based investigation: verifying claims, comparing options with
sourced tradeoffs, and confirming how libraries, APIs, and tools actually
behave before conclusions are relied on.

## 1. Discipline

- Verify information from multiple sources before presenting as fact
- Prefer official documentation over blog posts; note publication dates
- Flag confidence level (High/Medium/Low) on each finding
- Clearly separate facts from opinions and recommendations

## 2. Workflow

1. Clarify scope: what exactly needs to be answered?
2. Search official docs first (WebSearch + WebFetch)
3. Check GitHub repos: issues, discussions, source code for implementation
   details

   ```sh
   # Clone to /tmp for analysis when needed
   git clone --depth 1 <repo-url> /tmp/<repo-name>
   ```

4. Cross-reference: do multiple sources agree? Flag contradictions.
5. Test when possible: run code, check versions, verify claims hands-on
6. When synthesis needs categories, labels, or first-use terms before final
   wording, use `clarify-concepts` after evidence acquisition and before
   drafting conclusions.

## 3. Source Priority

1. Official documentation and changelogs
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add i9wa4/dotfiles/technical-research@sha256:ff0f3b5bd9223ef9

The line at the top of this page pins the label v1.0.0, 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_humrmq6wmlhceecj.svg)](https://markdownregistry.com/a/art_humrmq6wmlhceecj)

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

Versions

The registry has recorded 5 versions of this file, between Jul 5, 2026 and Sep 4, 2026, about one every 15 days.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-09-04 4f5f1ca 1,754 BA view · diff
v1.0.02026-07-20 1b60f43 1,746 BA view · diff
v1.0.02026-07-05 c4dd57c 1,572 BA view · diff
v1.0.02026-07-05 6187b7b 2,174 BA view · diff
git:20260705.2c6f1c32026-07-05 2c6f1c3 2,145 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 (1754 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

i9wa4/dotfiles · 12 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_humrmq6wmlhceecj
GET https://markdownregistry.com/api/v1/resolve?ref=i9wa4/dotfiles/technical-research
GET https://markdownregistry.com/api/v1/blob/ff0f3b5bd9223ef9f7cac72ff3f21769e5dc077a115fd636ca4229b7e83acdab

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 i9wa4/dotfiles

AGENTS.md@nix/home-manager/agents/shared AGENTS.md file
i9wa4/dotfiles · nix/home-manager/agents/shared/AGENTS.md
git:20260709.dfe57d6 · audit A · 12 stars
clarify-concepts SKILL.md skill
i9wa4/dotfiles · skills/clarify-concepts/SKILL.md · USE FOR: Clarify concepts before names harden by fixing concrete referents, roles, sequence, candidate terms, and…
v1.0.0 · audit A · 12 stars
create-review-comment SKILL.md skill
i9wa4/dotfiles · skills/create-review-comment/SKILL.md · USE FOR: `$create-review-comment`, ai-create-review-comment, or terse PR-review-comment requests. Infers the PR and…
v1.0.0 · audit A · 12 stars
data-platform SKILL.md skill
i9wa4/dotfiles · skills/data-platform/SKILL.md · USE FOR: Repo-local BigQuery, Databricks, dbt, restricted BigQuery/dbt safety, and cloud auth workflows. DO NOT USE…
v1.0.0 · audit A · 12 stars
dev-platform-workflow SKILL.md skill
i9wa4/dotfiles · skills/dev-platform-workflow/SKILL.md · USE FOR: Implement, fix, add, or otherwise change any code in the current repository — read this BEFORE starting, and…
v1.0.0 · audit A · 12 stars
diagramming SKILL.md skill
i9wa4/dotfiles · skills/diagramming/SKILL.md · USE FOR: draw.io and Mermaid diagram authoring, preview, export, layout, color, and asset workflows in this repo. DO…
v1.0.0 · audit A · 12 stars
dotfiles SKILL.md skill
i9wa4/dotfiles · skills/dotfiles/SKILL.md · USE FOR: This dotfiles environment and agent harness: machine setup, Nix operations/recovery, missing tools, operating…
v1.0.0 · audit A · 12 stars
external-references SKILL.md skill
i9wa4/dotfiles · skills/external-references/SKILL.md · USE FOR: Reference-only provider-pack lookup and promotion decisions for Cloudflare, dbt, Azure, Databricks, AWS…
v1.0.0 · audit A · 12 stars
logbook SKILL.md skill
i9wa4/dotfiles · skills/logbook/SKILL.md · USE FOR: Non-code working artifacts: local markdown task trackers, plans, research notes, review packets, drafts…
v1.0.0 · audit A · 12 stars
plan-design SKILL.md skill
i9wa4/dotfiles · skills/plan-design/SKILL.md · USE FOR: Implementation plans and durable task tracking: reduce ambiguity, compare options, parallel investigation…
v1.0.0 · audit A · 12 stars
programming SKILL.md skill
i9wa4/dotfiles · skills/programming/SKILL.md · USE FOR: Programming/debugging: Bash, Python/Jupyter quality, Nix package workflow, Terraform with Checkov, Markdown…
v1.0.0 · audit A · 12 stars
subagent-review SKILL.md skill
i9wa4/dotfiles · skills/subagent-review/SKILL.md · USE FOR: Guardian/critic native multi-perspective review workflow, peer critic evidence, material-finding convergence…
v1.0.0 · audit A · 12 stars

Every file in i9wa4/dotfiles

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