Skip to content
Agentmart
Submit a tool

update

Human-facing skill for updating an existing Darwin skill or any nested resource within a skill directory.

Skill by tykowale

IndexedMIT
Write a review

Chalk Labs

Need help deploying update?

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/tykowale-update

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

Human-facing skill for updating an existing Darwin skill or any nested resource within a skill directory.

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/update

What's inside

Skill name
update
Description
Human-facing skill for updating an existing Darwin skill or any nested resource within a skill directory.
License
MIT
Instructions
85 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Update

This is a human-facing skill.

Use it when the user wants to update:

- a top-level skill definition
- a nested file inside a skill directory
- supporting references such as examples, prompts, templates, or checklists under a skill

## Purpose

Update Darwin's skill system with the smallest correct change while preserving a narrow human-facing interface.

Prefer improving nested resources before broadening the top-level skill surface.

## Inputs

- target skill or nested file
- requested change
- constraints
- success criteria

## Outputs

- clarified scope
- approved update plan
- updated skill or nested resource
- verification evidence
- short debrief with any Darwin learning

## Dependencies

- `using-darwin`
- `verification-before-completion`
- `debrief-and-learn`

## Failure Modes

- changes are made to the wrong skill layer
- the update broadens the human-facing interface unnecessarily
- nested references drift out of sync with the top-level skill
- implementation starts before approval
- verification is missing or stale

## Verification

- confirm the target file and requested outcome before editing
- prefer editing the smallest file that can satisfy the request
- read the final files and confirm the change matches the request
- verify any touched skill still follows the skill contract

## Clarification Rule

Ask at most 3 clarifying questions before presenting a plan.

Questions should focus on:

- exact target to update
- desired behavior or wording change
- whether the change belongs in the top-level skill or a nested resource

## Planning Rule

After clarification, present a concise plan that includes:

- what will be updated
- why that target is the smallest useful place to change
- the edit steps
- how the result will be verified

## Approval Rule

Do not modify files until the user approves the plan.

## Output To The User

Keep the interaction simple:

- a small number of clarifying questions
- a clear plan to approve or reject
- concise progress updates
- a short summary of what changed and why

From tykowale/darwin, MIT.

More from tykowale/darwin

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Apr 4, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from tykowale

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 update 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 update?

CallGet help
Cite this page

update skill. Agent Mart. https://agentmart.dev/skills/tykowale-update (last updated 2026-10-24)