agentleFS
Sign inStart free
MorganOnGitHubMorganOnGitHub/tackle/skills/investigating-in-parallel/SKILL.md

investigating-in-parallel

Skill0 starsChanged 46 days agoMITView on GitHub

Use when facing several independent problems, such as unrelated test failures or separate subsystems, that could be investigated at the same time without sharing state

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When problems are truly independent, one focused agent per problem finishes faster than working through them in sequence, and each agent …

    line 8

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Investigating in Parallel

When problems are truly independent, one focused agent per problem finishes faster than working through them in sequence, and each agent stays focused on its own problem.

Scale it

  • Two small problems: usually faster to handle yourself in sequence.
  • Three or more independent problems, or slow investigations: dispatch in parallel.

How

  1. Group by root domain, not by symptom. Failures in the same subsystem, or ones that could share a cause, belong to one agent.
  2. Check independence. Would the agents edit the same files or share a resource (database, port, fixture)? If so, run them in sequence.
  3. Give each agent a self-contained brief:
    • Scope: one file, subsystem or failure set
    • Evidence: the exact error messages and test names
    • Constraints: what it must not change
    • Output: root cause, what it changed, and how it verified the change
  4. Dispatch together, then integrate: read each summary and diff, look for overlapping edits, and run the full suite on the combined result.

Skip or shorten when

  • The failures might be related. Investigate together first, because one fix may clear several.
  • You don't yet know what's broken. Exploration needs one coherent view.
  • The harness has no subagents. Work through them in sequence using the same briefs as a checklist.

Done means

Each agent's change has been read, conflicts are resolved, and the full suite passes on the combined result.

Next

  • debugging-systematically for any problem an agent couldn't explain
  • verifying-before-claiming

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free