Workflow from chats

Skill SID-SURANGE/cursor-team-ops/skills/community/workflow-from-chats

Scan the recent conversation for a repeated prompt pattern and produce a ready-to-commit SKILL.md. Triggered by "make this a skill", "extract this workflow", "save this as a skill".From its SKILL.md

Install

npx -y skills add SID-SURANGE/cursor-team-ops --skill workflow-from-chats

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.1 KB, 449 tokens by cl100k_base, as published. Nobody here has run it

⚡ Skill: workflow-from-chats

Purpose

Turn a repeated or valuable conversation pattern into a reusable, committable SKILL.md so the team never has to re-explain the same workflow.

Steps

1. Identify the pattern

Review the recent conversation (or the user-selected excerpt).
Look for:
- A multi-step workflow the user walked the agent through manually.
- A prompt the user re-typed with minor variations.
- A sequence of tool calls that produced a consistently useful outcome.
If ambiguous, ask: "Which part of this conversation should become the skill?"

2. Name and classify

Choose a short kebab-case name (e.g. fix-slow-query, generate-migration).
Pick a trigger phrase that would naturally recall this skill in future sessions.
Identify the skill's scope: does it belong in the team kit (~/.cursor/skills/) or the current project (.cursor/skills/)?

3. Draft the SKILL.md

Produce a file with this structure:

---
name: <kebab-case-name>
description: <One sentence. Include the trigger phrases.>
---

# Skill: <name>

## Purpose
<Why this skill exists — the pain it avoids.>

## Trigger phrases
- "<phrase 1>"
- "<phrase 2>"

## Steps
<Numbered steps extracted from the conversation. Be prescriptive, not descriptive.>

## Output
<What the skill produces — files created, commands run, verdicts returned.>

## Example
<Optional: a minimal before/after or sample invocation.>

4. Validate before writing

Confirm the steps are reproducible without the original conversation context.
Remove any project-specific details if the skill targets ~/.cursor/skills/.
Ensure trigger phrases are distinct from existing skills.

5. Write and report

Write the file to the correct location.
Report: skill name, file path, trigger phrases, and one-line description.

Output

A single SKILL.md ready to commit.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most automation workflows skills give in 449 tokens

Counted across 745 of the 1,008 authors here whose files we hold, read 2026-08-07

Write conventional commit messagesin 36 of 745, across 35 files
Delete branches after mergein 30 of 745, across 21 files
Make atomic commitsin 25 of 745, across 15 files
Write minimal code to pass testsin 22 of 745, across 10 files
Re-snapshot after navigation or DOM changesin 21 of 745, across 13 files
Use try-catch for error handlingin 20 of 745, across 8 files
Run tests before committingin 20 of 745, across 12 files
Write tests before implementationin 20 of 745, across 8 files
Configure branch protection rulesin 19 of 745, across 5 files
Explain the why in commit messagesin 19 of 745, across 9 files
Refactor code while tests remain greenin 19 of 745, across 6 files
Interact with elements using refsin 19 of 745, across 11 files

Said here and by no other author read

review the conversation for a workflow
ask which part to convert if ambiguous
pick a natural trigger phrase
identify the target skill scope
write prescriptive numbered steps
confirm steps are reproducible

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.