Skip to content
Agentmart
Submit a tool

goal

Executes an approved goal package from ai-artifacts/goals.

Skill by iurysza

IndexedMIT★ 5
Write a review

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/iurysza-goal

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

Executes an approved goal package from ai-artifacts/goals. Use when the user provides a goal.md path or asks to implement a goal created by setup-goal.

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 and code. 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/goal

What's inside

Skill name
goal
Description
Executes an approved goal package from ai-artifacts/goals. Use when the user provides a goal.md path or asks to implement a goal created by setup-goal.
License
MIT
Metadata
category: planning-architecture
Instructions
47 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Execute Goal

Execute an approved package at `ai-artifacts/goals/<slug>/goal.md`. Invoking this skill with a package is approval to begin implementation; it is not permission to rediscover scope or rewrite the contract.

## Load the contract

1. Read repository instructions first.
2. Require an explicit `goal.md` path from the user. Do not guess the latest or nearest package.
3. Read `goal.md` and resolve its links relative to the package directory.
4. Require and read `facts.md`, `facts.meta.json`, `plan.md`, and `dev-log.md`.
5. Read `intent.md` when the package contains or links it. Older approved packages without `intent.md` remain valid.
6. Stop if a required file is missing, a link is broken, fact metadata does not match the accepted facts, or a product, scope, architecture, security, or destructive decision remains unresolved.

Accepted facts are the implementation contract. Do not edit `intent.md` when present, `facts.md`, or `facts.meta.json` during execution. Do not revise `plan.md` unless the user explicitly sends the package back to setup or replanning.

## Execute

1. Briefly state the goal, approved scope, and execution approach.
2. Follow the approved plan in order. Use the narrowest implementation that satisfies every accepted fact.
3. Preserve unrelated work. Keep one writer per worktree unless parallel work is deliberately isolated.
4. Append concise entries to `dev-log.md`: completed work, changed files, validation, blockers, and remaining work. Never rewrite prior entries or claim work not performed.
5. Run every verification required by `plan.md`.
6. For each fact whose `automatedVerification` is `true`, run or add a concrete automated check. Record a blocker instead of pretending a check passed.
7. Record manual evidence for facts that cannot be verified automatically.

If implementation exposes a new material decision or contradicts an accepted fact, stop and ask the user. Do not silently expand scope or mutate the contract.

## Delegation

Delegate only when the host supports it and the role is directly useful. Every delegated task must name the exact `goal.md` path and instruct the worker to load the package. Never ask another agent to infer which goal applies.

Use isolated worktrees for parallel writers. Read-only research and review may run in parallel without sharing write ownership.

## Finish

Before declaring completion, compare the implementation and evidence against every accepted fact and the done condition in `goal.md`.

Report:

- implemented behavior;
- changed files;
- checks run and outcomes;
- manual verification;
- blockers or remaining work;
- `dev-log.md` path.

From iurysza/agent-skills, MIT.

More from iurysza/agent-skills

Signals

Stars
5
Forks
0
Open issues
0
Last commit (this folder)
Oct 10, 2026 (18 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from iurysza

Cite this page

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