research SKILL.md skillA

research from alexisbalayre/claude-code-config is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add alexisbalayre/claude-code-config/research@git:20260917.e147a85

Pins git:20260917.e147a85 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
alexisbalayre/claude-code-config
Path
.claude/skills/research/SKILL.md
Versions recorded
1
Latest version
git:20260917.e147a85, committed Sep 17, 2026
Size
760 bytes
Repository stars
3
License
MIT

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

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

Spin up a **background agent** to do the research, so you keep working while it reads.

Its job:

1. Investigate the question against **primary sources** (official docs, source code, specs, first-party APIs), not a secondary write-up of them. Follow every claim back to the source that owns it.
2. Write the findings to a single Markdown file, citing each claim's source.
3. Save it to `docs/research/<slug>.md` (slug from the question), creating the folder if needed, and say where.

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_hz7vzbkbidru75so/a6bb80907fdc2cbecd5b9f6c3c3963de0c071f8684ddd67e2dfa3320d1488898.json

Then /plugin install research@markdownregistry-hz7vzbkbidru75so in Claude Code. It installs git:20260917.e147a85, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add alexisbalayre/claude-code-config/research@sha256:a6bb80907fdc2cbe

The line at the top of this page pins the label git:20260917.e147a85, 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_hz7vzbkbidru75so.svg)](https://markdownregistry.com/a/art_hz7vzbkbidru75so)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in alexisbalayre/claude-code-config/research since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of research from somewhere else? Ask it: where did my research come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Sep 17, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260917.e147a85 latest2026-09-17 e147a85 760 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

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 (760 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

alexisbalayre/claude-code-config · 3 stars · license MIT · pushed 2026-11-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_hz7vzbkbidru75so
GET https://markdownregistry.com/api/v1/resolve?ref=alexisbalayre/claude-code-config/research
GET https://markdownregistry.com/api/v1/blob/a6bb80907fdc2cbecd5b9f6c3c3963de0c071f8684ddd67e2dfa3320d1488898

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 alexisbalayre/claude-code-config

README Claude Code subagent
alexisbalayre/claude-code-config · .claude/agents/README.md
git:20261017.c5ad833 · audit A · 3 stars
architecture-explainer Claude Code subagent
alexisbalayre/claude-code-config · .claude/agents/architecture-explainer.md · Use PROACTIVELY when the user asks why or how about the system architecture — component boundaries, data flow, request…
git:20260917.a589e3f · audit A · 3 stars
comment-pruner Claude Code subagent
alexisbalayre/claude-code-config · .claude/agents/comment-pruner.md · Autonomously prune bad comments from code added in the current session. Dispatched by the comment-pruner Stop hook when…
git:20260917.a589e3f · audit A · 3 stars
convention-checker Claude Code subagent
alexisbalayre/claude-code-config · .claude/agents/convention-checker.md · Use PROACTIVELY to verify files follow area-specific coding standards before committing. MUST BE USED after editing…
git:20260917.a589e3f · audit A · 3 stars
migration-reviewer Claude Code subagent
alexisbalayre/claude-code-config · .claude/agents/migration-reviewer.md · Use PROACTIVELY after any change to database schema definitions (ORM models, schema files) or to migration files (new…
git:20260917.a589e3f · audit A · 3 stars
review-context Claude Code subagent
alexisbalayre/claude-code-config · .claude/agents/review-context.md · Reviews changed code for spec contradictions, protocol violations, and infrastructure anti-patterns. Spawned by the…
git:20260811.6af4418 · audit A · 3 stars
review-conventions Claude Code subagent
alexisbalayre/claude-code-config · .claude/agents/review-conventions.md · Audits changed files for compliance with the project's documented rules and accepted ADR decisions. Spawned by the…
git:20260917.a589e3f · audit A · 3 stars
review-correctness Claude Code subagent
alexisbalayre/claude-code-config · .claude/agents/review-correctness.md · Reviews changed code for logic and behavior defects that deterministic tooling cannot catch, including behavioral…
git:20261017.279b6aa · audit A · 3 stars
review-docs Claude Code subagent
alexisbalayre/claude-code-config · .claude/agents/review-docs.md · Reviews the quality, accuracy, and usefulness of prose a change introduces. Strict on low-value comments and…
git:20260917.a589e3f · audit A · 3 stars
review-maintainability Claude Code subagent
alexisbalayre/claude-code-config · .claude/agents/review-maintainability.md · Reviews changed code for structural regressions that make the codebase harder to maintain. Spawned by the pr-ci-review…
git:20261017.c5ad833 · audit A · 3 stars
review-security Claude Code subagent
alexisbalayre/claude-code-config · .claude/agents/review-security.md · Reviews changed code for real, reachable security issues at system boundaries. Spawned by the pr-ci-review skill.
git:20261017.279b6aa · audit A · 3 stars
review-spec Claude Code subagent
alexisbalayre/claude-code-config · .claude/agents/review-spec.md · Checks a change against the issue or spec it implements, for requirements missing, partial, or built wrong, and for…
git:20261017.c5ad833 · audit A · 3 stars

Every file in alexisbalayre/claude-code-config

Other files named research

research SKILL.md skill
mattpocock/skills · skills/engineering/research/SKILL.md · Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use…
git:20261029.7739eae · audit A · 327,521 stars
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 · 40,827 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:20261110.ca6464f · audit A · 5,886 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 · 3,119 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 · 931 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 · 679 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 · 576 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 · 486 stars

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