Skill Tracer
Skills › Skills For Real Engineers › loop-me

loop-me

skill · 32 lines · MIT · skills/in-progress/loop-me/SKILL.md

The facts

Its description

Grill me about specs for the workflows I want to build, within this workspace.

The description the agent reads to decide when to use it.

From its settingsline 3

When it starts

This skill is not picked from conversation: it sets disable-model-invocation, so a person has to invoke it explicitly (as /loop-me), optionally naming a workflow to design or leaving it blank so the agent goes looking for one.

A model's summary of when it is used.

A model's reading

Who can start it

Only you

Only you can start it. The agent never picks it on its own.

From its settingsline 4

What it takes when started

A workflow to design, or nothing to go find one

What to type after its name when you start it.

From its settingsline 5

What it leads to

Other skills this one hands off to, calls, requires or offers instead, as a model read them.

A model's reading

Licence

MIT, from LICENSE

The terms its author shares it under, which let it be shown here.

From the repositorylicence text
Other files in this skill (1) Close

The text

Open on GitHub

Most marks come from matching words in the file, so treat them as pointers.

1---
2name: loop-me
3description: Grill me about specs for the workflows I want to build, within this workspace.
4disable-model-invocation: true
5argument-hint: "A workflow to design, or nothing to go find one"
6---
7
8Run a stateful `/grilling` session whose only output is **workflow** specs. Use the grilling discipline (relentless, a round of questions at a time, a recommended answer attached to each) aimed at the vocabulary and goal below. Create, edit, and delete specs as the grilling resolves things.
9

Run a stateful /grilling session whose only output is workflow specs. Use the grilling discipline (relentless, a round of questions at a time, a recommended answer attached to each) aimed at the vocabulary and goal below. Create, edit, and delete specs as the grilling resolves things.

Raw lines 1 to 9
Names a skill grilling :8
10## The loop lens
12A **loop** is a recurring pattern in the user's life: their career, their week, their morning, a single repeated activity. Picturing a life as loops within loops reveals how predictable its activities really are, which is what makes them worth **delegating**. Use the lens to find loops worth specifying, and propose ones the user hasn't noticed.
14A **workflow** is the spec of one loop, made real. You run a workflow on a loop: the loop is its running instantiation. Workflows live in `workflows/*.md` and are the source of truth.

The loop lens

A loop is a recurring pattern in the user's life: their career, their week, their morning, a single repeated activity. Picturing a life as loops within loops reveals how predictable its activities really are, which is what makes them worth delegating. Use the lens to find loops worth specifying, and propose ones the user hasn't noticed.

A workflow is the spec of one loop, made real. You run a workflow on a loop: the loop is its running instantiation. Workflows live in workflows/*.md and are the source of truth.

Raw lines 10 to 15
16## Vocabulary
18A shared language, reached for only when a workflow calls for it: never a checklist. **Mandate nothing structural**: a workflow needs no AI, no checkpoint, and no schedule unless the grilling shows it does.
20- **Trigger**: what fires each run, an **event** (a new email, a new issue) or a **schedule** (every morning). Event-triggering is usually the more efficient.
21- **Checkpoint**: a human-in-the-loop point where the user is asked to verify or decide. Some workflows have none and run autonomously; some use no AI at all.
22- **Push right**: defer the checkpoint as far as it will go. Do maximal work before involving the human, so they are asked once, late, with everything prepared.
23- **Brief**: what a checkpoint presents, a tight, decision-ready summary (what was produced, why, and a link down to the asset itself), never the raw output. The user reads a brief, not a draft. Speed of review is imperative.

Vocabulary

A shared language, reached for only when a workflow calls for it: never a checklist. Mandate nothing structural: a workflow needs no AI, no checkpoint, and no schedule unless the grilling shows it does.

  • Trigger: what fires each run, an event (a new email, a new issue) or a schedule (every morning). Event-triggering is usually the more efficient.
  • Checkpoint: a human-in-the-loop point where the user is asked to verify or decide. Some workflows have none and run autonomously; some use no AI at all.
  • Push right: defer the checkpoint as far as it will go. Do maximal work before involving the human, so they are asked once, late, with everything prepared.
  • Brief: what a checkpoint presents, a tight, decision-ready summary (what was produced, why, and a link down to the asset itself), never the raw output. The user reads a brief, not a draft. Speed of review is imperative.
Raw lines 16 to 24
25## Definition of done
27A workflow spec is done when an implementer agent could build it without asking a single question. Grill until then; nothing is done while a question remains.

Definition of done

A workflow spec is done when an implementer agent could build it without asking a single question. Grill until then; nothing is done while a question remains.

Raw lines 25 to 28
29## The workspace
31- `workflows/*.md`: one spec per workflow.
32- `NOTES.md`: raw notes on the user's world, the tools they use, the channels they process, and their own terminology for both. When it is empty or thin, interview them about their world before specifying anything. Sharpen fuzzy terms into canonical ones as they surface, and record them here.

The workspace

  • workflows/*.md: one spec per workflow.
  • NOTES.md: raw notes on the user's world, the tools they use, the channels they process, and their own terminology for both. When it is empty or thin, interview them about their world before specifying anything. Sharpen fuzzy terms into canonical ones as they surface, and record them here.
Raw lines 29 to 32

From mattpocock/skills at 4ae2317, 2026-10-31. Skills read by DeepSeek V4.1 Flash on 2026-11-04. Summary and techniques by Claude Opus 5.5 on 2026-11-06.