research SKILL.md skillA

research from bmtrnavsky/disciplined-vibe-coding is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add bmtrnavsky/disciplined-vibe-coding/research@git:20261027.93e47a5

Pins git:20261027.93e47a5 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
bmtrnavsky/disciplined-vibe-coding
Path
skills/research/SKILL.md
Versions recorded
3
Latest version
git:20261027.93e47a5, committed Oct 27, 2026
First version recorded
Sep 13, 2026
Size
1,658 bytes
Repository stars
14
License
a license file GitHub does not identify

Use before building anything novel, modifying unfamiliar code, ranking unfamiliar tech, or whenever a library/API is involved. Logs every consultation to `.pipeline/read.log`. (Lineage: godmode/reference-engine, godmode/github-search, agent-skills/api-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

# Research — read it before you build on it

## Prime directive
Documentation and prior art come first; implementation theory comes second.

## Steps (in order)
1. **Docs on every dependency** — quickstart, API ref, pitfalls. Docs tools over parametric memory. Never write against an API from memory.
2. **Log every consultation** to `.pipeline/read.log` (what, when, why). Audit trail; feeds read-check hook.
3. **Prior art before invention** — "could an existing tool/model/service do this?" is required. Provider-managed over hand-rolled.
4. **Read before modifying** — file, imports/callers, tests.
5. **Carry sources forward** into plan citations.

## Cognitive traps
- "This pattern is standard" — version drift breaks "standard" code.
- "Searching wastes tokens" — a failed implement-debug-revert cycle costs ten times a read.
- "Reading code is researching" — code says what it does; docs say what it's supposed to do.

## Guardrails
- No API in a plan without docs consulted.
- No new dependency without existing-solution check.

## Rung scaling (economy ladder)

Full-spec and above: all five steps every time. Micro-spec: steps 1, 2,
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add bmtrnavsky/disciplined-vibe-coding/research@sha256:02709f2f52ca771e

The line at the top of this page pins the label git:20261027.93e47a5, 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_g6a3epvwr7iogfje.svg)](https://markdownregistry.com/a/art_g6a3epvwr7iogfje)

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

Versions

The registry has recorded 3 versions of this file, between Sep 13, 2026 and Oct 27, 2026, about one every 22 days.

versioncommittedcommitsizeaudit
git:20261027.93e47a5 latest2026-10-27 93e47a5 1,658 BA view · diff
git:20261025.a1e86e02026-10-25 a1e86e0 1,360 BA view · diff
git:20260913.7de97942026-09-13 7de9794 1,354 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 (1658 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

bmtrnavsky/disciplined-vibe-coding · 14 stars · license a license file GitHub does not identify · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_g6a3epvwr7iogfje
GET https://markdownregistry.com/api/v1/resolve?ref=bmtrnavsky/disciplined-vibe-coding/research
GET https://markdownregistry.com/api/v1/blob/02709f2f52ca771e6e25c4ae319474e5cf56f6ec181a19f8ce1a81cd6a4959dc

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 bmtrnavsky/disciplined-vibe-coding

disciplined-vibe-coding SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · plugins/disciplined-vibe-coding/SKILL.md · Run any coding task through Intake, Define, Economy gate, Plan, Teardown, Build, Verify, Commit — with Wayfinder…
v0.2.0 · audit A · 14 stars
brainstorm SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/brainstorm/SKILL.md · Use after intake when a confirmed direction has approach-level design choices. 2-3 options per fork, batch independent…
git:20261027.93e47a5 · audit A · 14 stars
debug SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/debug/SKILL.md · Use whenever behavior is wrong, tests fail, or the user reports a bug. Docs-first root-cause triage, observation mode…
git:20261027.93e47a5 · audit A · 14 stars
execute SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/execute/SKILL.md · Use in Build to run an approved plan. Direct work or up to 5 workers; orchestrator exclusively owns git, plan/roadmap…
git:20261027.93e47a5 · audit A · 14 stars
intake SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/intake/SKILL.md · Use at the very start of any coding task or project. Interviews, classifies scale AND stakes, resolves direction forks…
git:20261027.5b28691 · audit A · 14 stars
plan SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/plan/SKILL.md · Use to plan one milestone (or small task) into atomic steps: paths, outputs, pass/fail checks, rollback/dry-run for…
git:20261027.5b28691 · audit A · 14 stars
test-first SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/test-first/SKILL.md · Use during Build for testable logic. Failing test before implementation (light RGR). Declared exemptions over faked…
git:20261027.93e47a5 · audit A · 14 stars
verify SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/verify/SKILL.md · Use before done-claims, milestone completion, releases. Fresh evidence — terminal, user-attested, integrity, plus…
git:20261027.5b28691 · audit A · 14 stars
version SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/version/SKILL.md · Use for commits at Build checkpoints, and releases/bumps/changelogs in Verify. Narrative commits, semver…
git:20261028.1e22c39 · audit A · 14 stars
write-docs SKILL.md skill
bmtrnavsky/disciplined-vibe-coding · skills/write-docs/SKILL.md · Use whenever writing docs/notes/changelogs/plans/roadmaps/prose for the user. Pragmatic ASD-STE100. Governs question…
git:20261027.93e47a5 · audit A · 14 stars

Every file in bmtrnavsky/disciplined-vibe-coding

Other files named research

research SKILL.md skill
yeachan-heo/oh-my-claudecode · skills/research/SKILL.md · Investigate an open question and return grounded, sourced findings
git:20260818.3222f6d · audit A · 40,492 stars
research SKILL.md skill
vinvcn/mattpocock-skills-zh-cn · skills/engineering/research/SKILL.md · 对照高可信一手来源调研问题,并把发现保存为仓库中的 Markdown 文件。适用于用户想调研主题、收集文档或 API 事实,或把阅读工作委托给后台代理时。
git:20260704.c71ad54 · audit A · 5,433 stars
research SKILL.md skill
alsk1992/cloddsbot · src/skills/bundled/research/SKILL.md · Research prediction markets - base rates, resolution rules, historical data
git:20260127.930cd97 · audit A · 3,052 stars
research SKILL.md skill
sethgammon/citadel · skills/research/SKILL.md · Focused research investigations. Converts questions into structured findings with confidence levels and source…
git:20260810.9641280 · audit A · 929 stars
research SKILL.md skill
zhongkaifu/tensorsharp · TensorAgent/skills/research/SKILL.md · Use for web searches and current information lookups, finding sources, and fact-checking without being given any URLs…
git:20261015.4e92754 · audit B · 651 stars
research SKILL.md skill
oliver-kriska/claude-elixir-phoenix · plugins/elixir-phoenix/skills/research/SKILL.md · Research Elixir/Phoenix/Ecto topics or evaluate Hex libraries (--library). Use when learning about libraries, patterns…
git:20260929.c08ad14 · audit A · 572 stars
research SKILL.md skill
boshu2/agentops · skills/research/SKILL.md · Answer one cited question on code, history, claims or patterns. Use when: asked how it works, why it changed, if a…
git:20261026.1b5f59a · audit A · 450 stars
research SKILL.md skill
aiskillstore/marketplace · pending/warpdotdev/research/SKILL.md · Delegate noisy investigation to one or more subagents so the orchestrator's context stays clean, then work from the…
git:20260904.fce3b5e · audit A · 450 stars

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