workflow-from-chats

An agent skill by cursor, from cursor/plugins. Tags: analysis, brainstorming, documentation, skill, workflow.

What it does

Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add cursor/plugins --skill workflow-from-chats

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/cursor/plugins
cp -r plugins/cursor-team-kit/skills/workflow-from-chats ~/.claude/skills/workflow-from-chats

Safety box score

Grade A, minimal risk: 9 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill reads recent Cursor chat transcripts, including parent and subagent conversations, to extract durable preferences and turn them into workflow guidance. It does not ship executable code or networked behavior, but it does handle private conversational data, so the main concern is accidental exposure of sensitive chat content or transcript paths.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	`SKILL.md` contains only markdown guidance; there are no scripts, shell commands, or code-evaluation steps.
Network access	0 (none)	No download, upload, API call, or remote-host communication is specified anywhere in the skill.
Filesystem reach	1 (low)	The workflow requires reading recent chat transcripts and subagent transcripts from local storage, with explicit mention of not exposing transcript paths.
Secrets & credentials	1 (low)	The skill may encounter secrets, customer data, private chat content, or credentials in transcripts, and it explicitly warns not to expose them.
Privilege & persistence	0 (none)	There is no sudo, service installation, shell/profile editing, or other system-wide change requested.
Instruction hijack surface	0 (none)	The text gives normal workflow instructions only; it does not ask the agent to ignore higher-priority rules, hide behavior, or follow external instructions.
Irreversible actions	0 (none)	The skill only analyzes chats and proposes artifacts; it does not send messages, deploy, publish, or take irreversible actions.
Transparency	0 (none)	The repository content is plain text markdown with no binaries, decoded blobs, or generated/obfuscated code.

Before installing

Confirm your chat transcripts are stored locally and review what the agent can read from that store.
Make sure you are comfortable with a skill that inspects private conversations, including subagent transcripts.
Check whether your environment ever records secrets in chat, since the skill may encounter them while mining preferences.

Rated 2026-10-20 by an automated review of 1 file from the skill's repository.

Source

Repository: cursor/plugins (all skills from this repository)
Path: cursor-team-kit/skills/workflow-from-chats/SKILL.md
Branch: main
Collection: cursor
Updated: 2026-09-23

automate-me — Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill".
principle-guard-the-context-window — Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning.
recall — Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents).
show-me-your-work — Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result).
to-questionnaire — Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
to-spec — Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.