agentleFS
hridaya423hridaya423/devingoal/skills/goal/SKILL.md

goal

Skill2 starsChanged 49 days agoMITView on GitHub

Set a persistent goal Devin pursues across turns until an independent judge verifies completion

51 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

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 47 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When several goals exist, aim every goalctl call: "$GOALCTL" --goal <name> <cmd> (default is the first slot).

    line 25
  2. Very specific:

    Never end a turn on a success claim alone.

    line 26

“Common” is measured: kept by at least 6 in 10 of the 47 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

The user invoked /goal with the arguments shown after this prompt. goalctl is this plugin's CLI — resolve it once per session:

GOALCTL=$(find "$HOME/.config/devin" "$HOME/.local/share/devin" "$PWD" -name goalctl -type f 2>/dev/null | head -1)

Route on the first word of the arguments:

  • empty or status → run "$GOALCTL" status, report the output (lists every goal when several exist; /goal status <name> shows one)
  • pause → "$GOALCTL" pause — no name pauses all; /goal pause <name> pauses one
  • resume → "$GOALCTL" resume, then continue the goal(s); /goal resume <name> resumes one and binds it to this session (how you adopt a goal parked by another thread — goals only auto-loop in the session that owns them)
  • clear → "$GOALCTL" clear — no name clears all; /goal clear <name> clears one
  • edit <text> → "$GOALCTL" edit <text>; with several goals: /goal edit <name> <text>
  • anything else → the objective. Each /goal starts a goal in its own slot — a second /goal while one is active starts a SECOND goal, not an error. When the UserPromptSubmit hook is installed globally it has already run goalctl start — check "$GOALCTL" status: if active, just pursue the objective. If no goal exists (hook not installed), run "$GOALCTL" install --project then "$GOALCTL" start <the full argument text> and pursue it.

While a goal is active:

  • Work in checkpoints. Keep the goal's report.md current (.devin/goal/report.md for the default slot, .devin/goal/<name>/report.md for named slots): what is done, what remains, evidence. It survives compaction and the judge reads it.
  • When several goals exist, aim every goalctl call: "$GOALCTL" --goal <name> <cmd> (default is the first slot). "$GOALCTL" status lists them.
  • Never end a turn on a success claim alone. When every requirement is verifiably satisfied, run "$GOALCTL" done "<evidence>" (add --goal <name> when several exist) first — an independent judge checks the claim against real repo state when you stop. A rejected claim continues the goal.
  • When all agent-doable work is complete and the only remainder is waiting on something you cannot control — a human merging a PR, CI finishing, a reviewer, a third party — run "$GOALCTL" waiting "<what is awaited>" and stop. Do NOT poll or monitor external status in a loop; the judge verifies the waiting claim and the goal ends as waiting (resumable later with /goal resume). If work you can still do remains, keep working instead.
  • Same genuine blocker with no path forward without user input → "$GOALCTL" blocked "<reason>". Three consecutive blocked claims end the goal as blocked.
  • A Stop hook may return a continuation reason — follow it.

OBJECTIVE:

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.