agentleFS
iuryszaiurysza/agent-skills/skills/goal/SKILL.md

goal

Skill5 starsChanged 12 days agoMITView on GitHub

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.

47 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use origin, update-cli-config and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • 0mlkrizzz655335vSkill

    origin

    origin CLI 管理。安装、登录、更新、修复 origin.cursor.com 的 CLI。"disabled-environments:

    Also in 3 projects that use this

  • PandelisZSkill

    update-cli-config

    View and modify Cursor CLI configuration settings in ~/.cursor/cli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.

    Also in 4 projects that use this

  • 0mlkrizzz655335vSkill

    review-bugbot

    缺陷导向代码审查。用 Bugbot 子代理找 bug。

    Also in 3 projects that use this

  • 32103210Skill

    migrate-to-skills

    Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.

    Also in 4 projects that use this

  • 32103210Skill

    update-cursor-settings

    Modify Cursor/VSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.

    Also in 4 projects that use this

  • MicrosoftSkill

    automate

    Propose an automation from a completed task or a new idea, then create it after approval. Use when the user asks to create an automation or wants scheduled local or cloud agent work.

    Also in 4 projects that use this

  • +1 more from 32103210
  • +3 more from 0mlkrizzz655335v

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 43 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read repository instructions first.

    line 14
  2. Very specific:

    Read goal.md and resolve its links relative to the package directory.

    line 16
  3. Very specific:

    Read intent.md when the package contains or links it.

    line 18
  4. Distinctive:

    Stop if a required file is missing, a link is broken, fact metadata does not match the accepted facts, or a product, scope, architecture, …

    line 19
  5. Distinctive:

    Follow the approved plan in order.

    line 26
  6. Very specific:

    Run every verification required by plan.md.

    line 29
  7. Distinctive:

    If implementation exposes a new material decision or contradicts an accepted fact, stop and ask the user.

    line 33
  8. Distinctive:

    Use isolated worktrees for parallel writers.

    line 39
  9. Very specific:

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

    line 43

“Common” is measured: kept by at least 6 in 10 of the 43 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.