research SKILL.md skillB

research from zhongkaifu/tensorsharp is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add zhongkaifu/tensorsharp/research@git:20261015.4e92754

Pins git:20261015.4e92754 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
zhongkaifu/tensorsharp
Path
TensorAgent/skills/research/SKILL.md
Versions recorded
4
Latest version
git:20261015.4e92754, committed Oct 15, 2026
First version recorded
Sep 2, 2026
Size
9,134 bytes
Repository stars
651
License
BSD-3-Clause

Use for web searches and current information lookups, finding sources, and fact-checking without being given any URLs. Network switch must be on; no API key.

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

The user asks a question. This finds the sources, reads them, and writes down what
they say with a link to each. **You do not need a URL to start** — that was the
whole problem with the version this replaces, and it is the thing a person asking
for research is least able to supply.

```sh
cd <the skill directory>/scripts

# The usual case: one command, question in, dossier out.
python3 research.py "how close is the Kessler syndrome" --out notes.md
cat notes.md
```

Then answer from `notes.md`, citing the URLs in it.

## The four scripts

| To | Run |
| --- | --- |
| Go from a question to a dossier | `research.py` |
| See where the sources would come from, without reading them | `discover.py` |
| Read one page you already have the URL of | `fetch_page.py` |
| Ask what the collected sources agree on | `analyze.py` |

### research.py — question in, dossier out

```
python3 research.py "how does a tokamak confine plasma" --out notes.md
python3 research.py "ggml quantisation formats" --sources papers,web --pages 6 --out notes.md
python3 research.py "battery degradation" --site nature.com --out notes.md
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add zhongkaifu/tensorsharp/research@sha256:83d5a767a9a8a67f

The line at the top of this page pins the label git:20261015.4e92754, 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_rlqoermzqphsffpy.svg)](https://markdownregistry.com/a/art_rlqoermzqphsffpy)

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

Versions

The registry has recorded 4 versions of this file, between Sep 2, 2026 and Oct 15, 2026, about one every 14 days.

versioncommittedcommitsizeaudit
git:20261015.4e92754 latest2026-10-15 4e92754 9,134 BB view · diff
git:20260910.a776e7a2026-09-10 a776e7a 9,264 BB view · diff
git:20260904.58845252026-09-04 5884525 9,731 BB view · diff
git:20260902.94346ec2026-09-02 94346ec 6,650 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No prompt-injection phrasing (matched: ignore your previous instructions)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9134 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 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

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

zhongkaifu/tensorsharp · 651 stars · license BSD-3-Clause · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_rlqoermzqphsffpy
GET https://markdownregistry.com/api/v1/resolve?ref=zhongkaifu/tensorsharp/research
GET https://markdownregistry.com/api/v1/blob/83d5a767a9a8a67fa1c81d11c6f92a01cf02299c02e064d8742ad73b82e56e33

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 zhongkaifu/tensorsharp

AGENTS.md AGENTS.md file
zhongkaifu/tensorsharp · AGENTS.md
git:20260917.c28115c · audit A · 651 stars
benchmark SKILL.md skill
zhongkaifu/tensorsharp · InferenceWeb.Tests/Fixtures/MultiAgent/SKILL.md · Read independent service evidence for the multi-agent benchmark.
git:20260924.62d2787 · audit A · 651 stars
algorithmic-art SKILL.md skill
zhongkaifu/tensorsharp · TensorAgent/skills/algorithmic-art/SKILL.md · Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users…
git:20260902.e91e7ca · audit B · 651 stars
canvas-design SKILL.md skill
zhongkaifu/tensorsharp · TensorAgent/skills/canvas-design/SKILL.md · Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user…
git:20260902.e91e7ca · audit A · 651 stars
doc-coauthoring SKILL.md skill
zhongkaifu/tensorsharp · TensorAgent/skills/doc-coauthoring/SKILL.md · Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation…
git:20260902.e91e7ca · audit A · 651 stars
documents SKILL.md skill
zhongkaifu/tensorsharp · TensorAgent/skills/documents/SKILL.md · Read and write real documents on the device - PDF, XLSX, DOCX, PPTX and CSV. Turn a photo or picture into a PDF…
git:20260908.ff90b63 · audit A · 651 stars
find-skills SKILL.md skill
zhongkaifu/tensorsharp · TensorAgent/skills/find-skills/SKILL.md · Find, inspect and install skills for a requested task. Use when the user asks for a skill or wants new capabilities…
git:20261015.4c83789 · audit A · 651 stars
frontend-design SKILL.md skill
zhongkaifu/tensorsharp · TensorAgent/skills/frontend-design/SKILL.md · Design distinctive UI with intentional aesthetics and typography. Read the workflow first; save HTML with the offered…
git:20261015.4e92754 · audit A · 651 stars
grill-me SKILL.md skill
zhongkaifu/tensorsharp · TensorAgent/skills/grill-me/SKILL.md · Interview the user to stress-test a plan or decision, one independent set of questions at a time.
git:20261015.4e92754 · audit A · 651 stars
grill-with-docs SKILL.md skill
zhongkaifu/tensorsharp · TensorAgent/skills/grill-with-docs/SKILL.md · Interview a plan, record agreed terms and decisions, and return saved document links before questions. Tested with…
git:20261015.4e92754 · audit A · 651 stars
handoff SKILL.md skill
zhongkaifu/tensorsharp · TensorAgent/skills/handoff/SKILL.md · Write a concise handoff from the conversation so another agent can continue; redact sensitive values. Tested with…
git:20261015.4e92754 · audit A · 651 stars
internal-comms SKILL.md skill
zhongkaifu/tensorsharp · TensorAgent/skills/internal-comms/SKILL.md · A set of resources to help me write all kinds of internal communications, using the formats that my company likes to…
git:20260902.e91e7ca · audit A · 651 stars

Every file in zhongkaifu/tensorsharp

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
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
research SKILL.md skill
boshu2/agentops · plugin/skills/research/SKILL.md · Answer one cited question about code, history, claims or patterns. Use when: asked how it works, why it changed…
git:20261022.0ffc108 · audit A · 450 stars

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