Skip to content
Agentmart
Submit a tool

bounds-create-verification

Create and execute a project-local verification recipe and small feature map using the project's existing tools to launch, health-check, drive, capture…

Skill by boundsj

IndexedMIT
Write a review

Chalk Labs

Need help deploying bounds-create-verification?

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-create-verification

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 and execute a project-local verification recipe and small feature map using the project's existing tools to launch, health-check, drive, capture evidence, and clean up.

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-create-verification

What's inside

Skill name
bounds-create-verification
Description
Create and execute a project-local verification recipe and small feature map using the project's existing tools to launch, health-check, drive, capture evidence, and clean up.
License
MIT
Instructions
21 lines in SKILL.md · view on GitHub

Files (4)

  • LICENSE.txt
  • NOTICE.md
  • SKILL.md
  • recipe.md · references/

SKILL.md (first lines)

# Bounds create verification

Inspect the project before asking the user: its real user surface, run/build commands, dependencies, authentication needs, fixtures, and existing test or driving tools. Preserve useful specialists and native host tools. Identify how to isolate ports, processes, data, and profiles from active work.

Find an existing verification recipe first. Extend it if appropriate. Otherwise use the project's documentation convention, falling back to `docs/verification/README.md` with `features.md` alongside it. A discoverable local skill is optional when the project already uses one; keep its files inside that project. Never write a project recipe into this shared bundle or a global skill home.

Read [recipe shape](references/recipe.md) when authoring. Fill it with observed commands and checks, not guessed placeholders:

- **Launch:** setup, isolated runtime, readiness signal, and owned resources. A short-lived CLI needs no background server.
- **Doctor:** a read-only check of the intended instance, version, prerequisites, and health before driving.
- **Drive:** user-facing actions through existing tools and stable handles, with explicit expected results.
- **Evidence:** commands, results, host/tool versions, revision including dirty state, coverage, and durable artifact paths. Capture the action and its effect.
- **Cleanup:** release only resources this run owns, on failure too. Evidence lives outside disposable runtime state and survives teardown.

Add a small feature map, usually three to five important behaviors or fewer for a small project. For each, name the user entrypoint, prerequisites, action, expected observation, and verification status. Mark unexercised paths explicitly.

Execute the recipe end to end for at least one mapped behavior. Run Doctor after surprises; repair recipe errors and retry a failed step once before reporting a blocker. Verify evidence still exists after cleanup. A recipe not executed is a draft; a build or source read alone does not prove user behavior.

Report coverage and remaining prerequisites. A startup or product defect outside scope is a finding, not permission for a broad repair. Point to `bounds-maintain-verification` for later upkeep without scheduling it.

From boundsj/bounds-skills, MIT.

More from boundsj/bounds-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 4, 2026 (26 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-create-verification 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-create-verification?

CallGet help
Cite this page

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