Skip to content
Agentmart
Submit a tool

forge-research-loop

Use after forge bootstrap when user wants research tasks from a project .forge.md executed one by one.

Skill by aldorado

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/aldorado-forge-research-loop

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use after forge bootstrap when user wants research tasks from a project .forge.md executed one by one.

Use cases: research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/forge-research-loop

What's inside

Skill name
forge-research-loop
Description
Use after forge bootstrap when user wants research tasks from a project .forge.md executed one by one.
License
MIT
Instructions
31 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Forge Research Loop

Run research tasks from a project forge file one step at a time.

## Required flow

1. Ask for project folder path if unclear (absolute path).
2. Open project `*.forge.md` and list research items.
3. Execute exactly one research step.
4. After each step:
   - write findings into `*.forge.md`
   - update project `*.md` if scope/decisions changed
   - send short report
   - ask: continue with next step?
5. Wait for user confirmation.
6. After all research is done:
   - create `<project-folder>/agents.md`
   - add concise roles/work split based on findings
   - send done signal.

## File rules

- only edit files inside the chosen project folder
- keep forge as execution truth and idea as intent
- fail fast on missing files and report exact path

## Reporting style

short, concrete, no implementation until user says continue.

From aldorado/visor, MIT.

More from aldorado/visor

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Feb 21, 2026 (8 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from aldorado

Cite this page

forge-research-loop skill. Agent Mart. https://agentmart.dev/skills/aldorado-forge-research-loop (last updated 2026-10-24)