Skip to content
SkillModel-led518 tokens in use

loop-me

Get grilled about the recurring loops in your work and end up with workflow specs ready to delegate.

328,764 stars on the repository MIT Licensemattpocock/skills · skills/in-progress/loop-me
claude plugin install mattpocock-skills@claude-plugins-official
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing loop-me costs

20tokens idle
518tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts and code blocks. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Fair
  • Frontmatter8/15
  • Structure9/25
  • Examples0/15
  • Output15/15
  • Size15/15
  • Resources0/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

Loop me runs a stateful grilling session whose only output is workflow specs. It treats a life as loops within loops, finds recurring patterns worth delegating, and proposes ones you have not noticed. Questions come a round at a time, each with a recommended answer.

Specs live in workflows/*.md and are done when an implementer agent could build them without asking a question.

What You Get

  • One workflow spec per loop in workflows/*.md
  • A NOTES.md that records your world, tools and own terminology
  • Triggers identified as events or schedules
  • Checkpoints pushed as late as possible, each with a decision-ready brief

Common Use Cases

  • Specify an inbox-processing workflow that fires on each new email
  • Design a morning routine that prepares a brief for you to review
  • Find repeated activities in a career or week that could be delegated

What Makes It Unique

It mandates nothing structural: a workflow needs no AI, checkpoint or schedule unless the grilling shows it does. It uses the loop lens to propose workflows you had not noticed, and its definition of done is that an implementer could build the spec with no further questions.

Under The Hood

A SKILL.md with no scripts that builds on the grilling skill. It creates, edits and deletes markdown files in the workspace, namely workflows/*.md and NOTES.md, and interviews you about your world first when the notes are thin.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers