research SKILL.md skillA

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

Install it, pinned
mdr add camoa/claude-skills/research@git:20261028.e2c6db6

Pins git:20261028.e2c6db6 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
camoa/claude-skills
Path
aida/skills/research/SKILL.md
Versions recorded
36
Latest version
git:20261028.e2c6db6, committed Oct 28, 2026
First version recorded
Sep 14, 2026
Size
37,681 bytes
Repository stars
33
License
MIT

This skill should be used when a task's scope contract is approved and its criteria need grounding before design starts, for example "research this task", "find prior art", "check for an existing library", "look for a guide", "check this assumption", or "Phase 1". It fans out one small search per subject, records each search's findings in its own file, and checks that every criterion has a finding and every finding cites a criterion.

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

Research finds out what is already true, so the design stage does not have to guess and does not
have to look things up itself. It answers five questions, for each criterion that needs one: has
someone built this already; are there guides or recipes covering it; do reputable sources
recommend a way to do it; is an assumption the task leans on still true; and it hands the answers
to the design stage in a form design can act on without looking again.

Research does not decide. It reports what exists and what is true of it. Choosing between two
usable options is design's work. Research does not read to the bottom of anything: a subject is
never exhausted, so the criteria are what stop this stage, never the subject.

Every finding names where it came from and when it was looked at. A finding with no source is
not a finding, and the model's own recall is never the answer, only a lead worth confirming with
one search.

Every write below goes through `research-actions.sh`, or `playbook-actions.sh` for the playbook
load, or the task skill's `decline-recipe` for a declined recipe, or scope's `set-tests` for the
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add camoa/claude-skills/research@sha256:d4498ce237321ced

The line at the top of this page pins the label git:20261028.e2c6db6, 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_yepiurayazefebf6.svg)](https://markdownregistry.com/a/art_yepiurayazefebf6)

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

Versions

The registry has recorded 36 versions of this file, between Sep 14, 2026 and Oct 28, 2026, about one every day.

versioncommittedcommitsizeaudit
git:20261028.e2c6db6 latest2026-10-28 e2c6db6 37,681 BA view · diff
git:20261028.48e79502026-10-28 48e7950 37,942 BA view · diff
git:20261026.5e6cc322026-10-26 5e6cc32 38,528 BA view · diff
git:20261024.08778942026-10-24 0877894 38,308 BA view · diff
git:20261024.a7764692026-10-24 a776469 38,321 BA view · diff
git:20261019.560b8332026-10-19 560b833 38,304 BA view · diff
git:20261019.a43505b2026-10-19 a43505b 37,940 BA view · diff
git:20261019.0ccf7072026-10-19 0ccf707 37,657 BA view · diff
git:20261019.911b84c2026-10-19 911b84c 37,772 BA view · diff
git:20261019.045b02a2026-10-19 045b02a 37,372 BA view · diff
git:20261006.b84f3372026-10-06 b84f337 36,908 BA view · diff
git:20261006.3174b552026-10-06 3174b55 36,912 BA view · diff
git:20261001.ed156012026-10-01 ed15601 36,851 BA view · diff
git:20260929.fa5b31a2026-09-29 fa5b31a 36,691 BA view · diff
git:20260929.e767b7f2026-09-29 e767b7f 36,691 BA view · diff
git:20260929.89af26b2026-09-29 89af26b 36,097 BA view · diff
git:20260929.a96681c2026-09-29 a96681c 36,563 BA view · diff
git:20260925.bc118062026-09-25 bc11806 35,694 BA view · diff
git:20260925.d37b3f72026-09-25 d37b3f7 35,336 BA view · diff
git:20260924.81a63382026-09-24 81a6338 34,155 BA view · diff
git:20260923.8e59d0d2026-09-23 8e59d0d 33,969 BA view · diff
git:20260923.858992e2026-09-23 858992e 33,469 BA view · diff
git:20260923.ffd5ad02026-09-23 ffd5ad0 31,636 BA view · diff
git:20260922.df22d062026-09-22 df22d06 31,392 BA view · diff
git:20260922.4fb9b7c2026-09-22 4fb9b7c 31,307 BA view · diff
git:20260921.0e6f7ba2026-09-21 0e6f7ba 29,101 BA view · diff
git:20260917.acd1e4a2026-09-17 acd1e4a 28,631 BA view · diff
git:20260917.91b1b172026-09-17 91b1b17 28,153 BA view · diff
git:20260917.56ab02e2026-09-17 56ab02e 28,135 BA view · diff
git:20260917.af0a4162026-09-17 af0a416 27,832 BA view · diff
git:20260916.c26a4ac2026-09-16 c26a4ac 26,379 BA view · diff
git:20260915.8cd78292026-09-15 8cd7829 26,011 BA view · diff
git:20260915.1adef952026-09-15 1adef95 25,765 BA view · diff
git:20260914.8162a4f2026-09-14 8162a4f 25,214 BA view · diff
git:20260914.600553f2026-09-14 600553f 25,043 BA view · diff
git:20260914.953c2762026-09-14 953c276 24,946 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 (37681 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

camoa/claude-skills · 33 stars · license MIT · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_yepiurayazefebf6
GET https://markdownregistry.com/api/v1/resolve?ref=camoa/claude-skills/research
GET https://markdownregistry.com/api/v1/blob/d4498ce237321ced48bc0a0075eee78c510ec00d02d5fee3df2ef2fa9c0f226b

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 camoa/claude-skills

CLAUDE.md CLAUDE.md file
camoa/claude-skills · CLAUDE.md
git:20260913.cb6d62b · audit A · 33 stars
completion SKILL.md skill
camoa/claude-skills · aida/skills/completion/SKILL.md · This skill should be used when a reviewed task is ready to close, for example "close this task", "finish the task"…
git:20261028.4e82de7 · audit A · 33 stars
design SKILL.md skill
camoa/claude-skills · aida/skills/design/SKILL.md · This skill should be used when a task's criteria are grounded and it is time to decide how to build them, for example…
git:20261029.7834067 · audit A · 33 stars
implement SKILL.md skill
camoa/claude-skills · aida/skills/implement/SKILL.md · This skill should be used when a task's design has closed cleanly and it is time to begin building, for example "start…
git:20261028.aaa1221 · audit A · 33 stars
next SKILL.md skill
camoa/claude-skills · aida/skills/next/SKILL.md · This skill should be used when the user asks "what's next", "what should I work on", "continue", "resume", "pick up…
git:20261028.bd73fd1 · audit A · 33 stars
playbooks SKILL.md skill
camoa/claude-skills · aida/skills/playbooks/SKILL.md · This skill should be used when the user asks "which playbooks apply", "list the plays", "add a play", "capture this as…
git:20261028.99198b4 · audit A · 33 stars
project SKILL.md skill
camoa/claude-skills · aida/skills/project/SKILL.md · This skill should be used when the user asks "which project", wants to "create a project", "start a new project"…
git:20261028.99198b4 · audit A · 33 stars
review SKILL.md skill
camoa/claude-skills · aida/skills/review/SKILL.md · This skill should be used when a task's implementation has finished and the whole task needs one pass against its…
git:20261028.6aa4db5 · audit A · 33 stars
scope SKILL.md skill
camoa/claude-skills · aida/skills/scope/SKILL.md · This skill should be used when a task needs its scope contract written or changed, for example "define scope", "write…
git:20261028.e2c6db6 · audit A · 33 stars
surfaces SKILL.md skill
camoa/claude-skills · aida/skills/surfaces/SKILL.md · This skill should be used when end to end or visual regression has to be set up for the current project, for example…
git:20261028.6aa4db5 · audit A · 33 stars
task SKILL.md skill
camoa/claude-skills · aida/skills/task/SKILL.md · This skill should be used when the user wants to "create a task", "start a new task", "split a task", "make this an…
git:20261028.aaa1221 · audit A · 33 stars
test-cleanup SKILL.md skill
camoa/claude-skills · aida/skills/test-cleanup/SKILL.md · This skill should be used when a project's test suite has grown too large and a person wants it analysed and cleaned…
git:20261028.dc2c7a5 · audit A · 33 stars

Every file in camoa/claude-skills

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.