agentleFS
roborracleroborracle/agent-workflow-kit/skills/unstuck/SKILL.md

unstuck

Skill0 starsChanged 3 months agoMITView on GitHub

Break implementation loops by forcing architectural rethinking when stuck on a failing approach.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Not variations of the same pattern — fundamentally different architectures.

    line 22
  2. Distinctive:

    No more iterations on the old approach

    line 45
  3. Very specific:

    If the new approach also fails after 2 attempts, run /unstuck again with updated context

    line 47

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “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

Unstuck — Break Implementation Loops

Stuck on: $ARGUMENTS


Stop iterating on the current approach. Rethink its architecture.

Step 1: Autopsy the Current Approach

  • What's actually failing? (Be specific — error message, behavior, symptom)
  • Why can't the current approach work? (Root cause, not symptom)
  • What architectural assumption is flawed?

Step 2: Generate 5 Radically Different Strategies

Not variations of the same pattern — fundamentally different architectures.

For each:

  1. [Strategy Name] — one-line description
    • Key change: what makes this fundamentally different
    • Complexity: Simple / Medium / Complex
    • Success likelihood: Low / Medium / High

Step 3: Pick One

Select the simplest approach with highest success likelihood.

  • Why this one
  • What new problems it might introduce
  • What to watch for

Step 4: Execute

  1. [Action 1]
  2. [Action 2]
  3. [Action 3]
  4. [Validation — how to prove it works]

Rules:

  • No more iterations on the old approach
  • New architecture only
  • If the new approach also fails after 2 attempts, run /unstuck again with updated context

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.