Skip to content
Agentmart
Submit a tool

bounds-automate-me

Create or update a scoped skill that captures how the user likes agents to work, from their explicit preferences and bounded evidence of repeated decisions.

Skill by boundsj

IndexedMIT
Write a review

Chalk Labs

Need help deploying bounds-automate-me?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/boundsj-bounds-automate-me

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Create or update a scoped skill that captures how the user likes agents to work, from their explicit preferences and bounded evidence of repeated decisions. Use when the user asks to turn their working style into a reusable skill.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/bounds-automate-me

What's inside

Skill name
bounds-automate-me
Description
Create or update a scoped skill that captures how the user likes agents to work, from their explicit preferences and bounded evidence of repeated decisions. Use when the user asks to turn their working style into a reusable skill.
License
MIT
Instructions
23 lines in SKILL.md · view on GitHub

Files (4)

  • LICENSE.txt
  • NOTICE.md
  • SKILL.md
  • skill-shape.md · references/

SKILL.md (first lines)

# Bounds automate me

Turn the user's accepted working conventions into one concise skill agents can follow. The request authorizes drafting or updating that skill in the scope the user chose; it does not authorize global configuration edits, installation, publication, or rollout.

If a working-style skill for this user already exists in scope, update it in place unless they asked to start fresh. Keep uncontradicted sections and prefer evidence newer than its last edit.

## Gather bounded evidence

1. Explicit preferences in this request and conversation come first.
2. Then only sources the user names, such as a development log, particular sessions, or one project's records, within a stated window. Don't search unrelated projects or histories. If an optional integration is unavailable, say what you could not read.
3. Look for repeated decisions: corrections made more than once, restated constraints, what the user accepted as done, how they want updates. A one-task instruction is not a convention. When a preference was reversed, follow the latest accepted decision.

Ask only for intent evidence cannot show, in one short round with concrete options. Don't re-ask for approval already given.

## Draft

Read [skill shape](references/skill-shape.md) for sections, wording, and the privacy check. Write decision criteria, not event logs; include a section only where the user has a specific rule; name other skills instead of copying them. Generalize practices; keep transcripts, private quotations, identifiers, project names, account details, addresses, paths, and credentials out.

## Deliver

Write the skill where the user asked or where the project's skill convention puts it; otherwise return it in the conversation. Report the evidence window and sources read or unreachable, which rules came from explicit statements versus repeated observations, what you dropped as one-off, and open questions. Ask the user whether it reads like how they work. Reuse explicit delivery authorization already given; otherwise propose installation, enabling on other hosts, or publication separately.

From boundsj/bounds-skills, MIT.

More from boundsj/bounds-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 17, 2026 (14 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from boundsj

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get bounds-automate-me running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying bounds-automate-me?

CallGet help
Cite this page

bounds-automate-me skill. Agent Mart. https://agentmart.dev/skills/boundsj-bounds-automate-me (last updated 2026-10-24)