agentleFS
Sign inStart free
afaraha8403afaraha8403/balakit/.agents/skills/unmatched-workflow/SKILL.md

unmatched-workflow

Skill1 starsChanged 10 days agoMITView on GitHub

Design a rigorous, auditable playbook when no narrower skill fits: a large migration, multi-part change, or work a human will review after stepping away. Apply when no playbook matches, the work is a migration, or they will be gone while the work runs. Use inception when the deliverable is the plan. Use deep-deliberation to choose among options without implementing. Use kit-workflows for a known bug-fix, feature, or refactor. Use blinded-eval to prove a skill change.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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 no playbook fits, the deliverable before any code is the workflow: phases that scale rigor to the task.

    line 31
  2. Distinctive:

    Run the loop: each unit is an experiment — hypothesis, smallest change, measure on the real artifact, keep or revert.

    line 38
  3. Distinctive:

    Verify the whole against the Phase 1 predicate on the real product.

    line 39

≈ “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

Unmatched workflow

Leading words: falsifiable done-predicate, hypothesis loop, VERIFIED NOT VERIFIED INCONCLUSIVE.

When no playbook fits, the deliverable before any code is the workflow: phases that scale rigor to the task. Inconclusive is not a pass.

Copy these steps into the todo list verbatim. Skip with skip: <reason>.

  1. Frame: falsifiable done-predicate, scope, rigor level (one-way doors get more). Present before a long run.
  2. Design the workflow: atomic units, riskiest-unknown first, verification harness before features. The first unit that writes code is the harness, not a product edit. Deleting the old API is out of scope unless the Phase 1 predicate names it. Write the phase list down.
  3. Run the loop: each unit is an experiment — hypothesis, smallest change, measure on the real artifact, keep or revert.
  4. Verify the whole against the Phase 1 predicate on the real product.

Verdicts

Each unit: VERIFIED, NOT VERIFIED, or INCONCLUSIVE. Do not hide a negative.

Pair delegated work with a parent read of the artifacts. If a worker games the gate, harden the contract. If the gate is wrong, fix the gate in its own change.

Reply contract

The playbook you designed, the rigor level and why, what is verified against the predicate, and what is still open.

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