agent-research SKILL.md skillA

This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.

agent-research from hua-bang/pulse-agent is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add hua-bang/pulse-agent/agent-research@v1.1.0

Pins v1.1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
hua-bang/pulse-agent
Path
.pulse-coder/skills/agent-research/SKILL.md
Versions recorded
1
Latest version
v1.1.0, committed Feb 18, 2026
Size
5,284 bytes
Repository stars
30
License
MIT

Strict research and design workflow for general coding-agent loops with evidence-backed benchmarking, iterative user discussion, and explicit execution handoff.

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

# Agent Research & Design Skill (Strict, English)

## Goal

This skill is for systematically researching and designing a general Agent Loop / Coding Agent capability model, ensuring:
1. Atomic capabilities are clearly defined and implementable.
2. Benchmarking against mainstream implementations (pi-mono / OpenCode / Claude Code) is evidence-backed.
3. The proposed design is discussion-ready and iteration-friendly.
4. No implementation starts before explicit user confirmation.

---

## Non-Negotiable Rules

1. **Research first, design second, execution last.**  
   Do not move into implementation before research + design convergence.

2. **All key claims must be source-traceable.**  
   Every important claim must include URL citations. If not, mark as assumption/speculation.

3. **Separate facts from interpretation.**  
   Explicitly label output as:
   - `Fact`
   - `Inference`
   - `Proposal`

4. **Minimum research depth is mandatory.**
   - At least **8 rounds** of search, at most **12 rounds**.
   - At least **12 unique source URLs**.
   - Must cover **3 required targets**: pi-mono, OpenCode, Claude Code.

5. **Atomic capabilities must follow a standard schema.**
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add hua-bang/pulse-agent/agent-research@sha256:31fd6d359f4b342b

The line at the top of this page pins the label v1.1.0, 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_nmwujl6ljio2uufz.svg)](https://markdownregistry.com/a/art_nmwujl6ljio2uufz)

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

Versions

The registry has recorded 1 version of this file, committed on Feb 18, 2026.

versioncommittedcommitsizeaudit
v1.1.0 latest2026-02-18 2c79833 5,284 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 (5284 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

hua-bang/pulse-agent · 30 stars · license MIT · pushed 2026-11-01 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_nmwujl6ljio2uufz
GET https://markdownregistry.com/api/v1/resolve?ref=hua-bang/pulse-agent/agent-research
GET https://markdownregistry.com/api/v1/blob/31fd6d359f4b342b94569791a1c1a9d06ce68c668dd3ac9e57079a2e1f9850a4

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 hua-bang/pulse-agent

branch-naming SKILL.md skill
hua-bang/pulse-agent · .pulse-coder/skills/branch-naming/SKILL.md · Intelligent branch naming based on changes, context, and best practices
v1.1.0 · audit A · 30 stars
code-review SKILL.md skill
hua-bang/pulse-agent · .pulse-coder/skills/code-review/SKILL.md · Perform comprehensive code review including code quality, security, performance, and best practices
v1.0.0 · audit A · 30 stars
deep-research SKILL.md skill
hua-bang/pulse-agent · .pulse-coder/skills/deep-research/SKILL.md · Conduct high-quality multi-round research with explicit evidence tracking, source scoring, and synthesis.
v2.0.0 · audit A · 30 stars
fix-pulse-agent-issue SKILL.md skill
hua-bang/pulse-agent · .pulse-coder/skills/fix-pulse-agent-issue/SKILL.md · Diagnose and implement a verified fix for one Pulse Agent GitHub issue in the pulse-agent repository.
v1.1.0 · audit A · 30 stars
git-workflow SKILL.md skill
hua-bang/pulse-agent · .pulse-coder/skills/git-workflow/SKILL.md · Standard git workflow for handling changes on the current branch - add, commit, push, then auto-run MR generation when…
v1.6.0 · audit A · 30 stars
mr-generator SKILL.md skill
hua-bang/pulse-agent · .pulse-coder/skills/mr-generator/SKILL.md · Automatically generate concise MR titles and descriptions based on current branch diff
v1.3.0 · audit A · 30 stars
perf-report SKILL.md skill
hua-bang/pulse-agent · .pulse-coder/skills/perf-report/SKILL.md · Run the canvas-workspace performance evaluation, publish the latest static dashboard through the local nginx/Cloudflare…
git:20260712.f866026 · audit A · 30 stars
project-roadmap SKILL.md skill
hua-bang/pulse-agent · .pulse-coder/skills/project-roadmap/SKILL.md · Analyze the current Pulse Coder project/repository and turn vague or concrete needs into prioritized requirements…
v1.0.0 · audit A · 30 stars
refactor SKILL.md skill
hua-bang/pulse-agent · .pulse-coder/skills/refactor/SKILL.md · Refactor code to improve structure, readability, and maintainability without changing behavior
v1.0.0 · audit A · 30 stars
session-digest SKILL.md skill
hua-bang/pulse-agent · .pulse-coder/skills/session-digest/SKILL.md · Summarize sessions across a multi-day range by paging session_summary in chunks, output bilingual, and write back…
v1.0.0 · audit A · 30 stars
twitter-reader SKILL.md skill
hua-bang/pulse-agent · .pulse-coder/skills/twitter-reader/SKILL.md · Analyze X/Twitter accounts, tweets, and trends through the installed Twitter MCP tools
v1.0.0 · audit A · 30 stars
AGENTS.md AGENTS.md file
hua-bang/pulse-agent · AGENTS.md
git:20261021.7ea6378 · audit A · 30 stars

Every file in hua-bang/pulse-agent

Other files named agent-research

agent-research SKILL.md skill
hua-bang/pulse-agent · apps/remote-server/.pulse-coder/skills/agent-research/SKILL.md · Strict research and design workflow for general coding-agent loops with evidence-backed benchmarking, iterative user…
v1.1.0 · audit A · 30 stars

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