agentleFS
Harry-kpHarry-kp/vortix/.claude/skills/ideate/SKILL.md

ideate

Skill757 starsChanged 48 days agoMITView on GitHub

Decide with the maintainer what Vortix builds next — review open proposals one by one, or explore a new idea (evidence, options, smallest useful version, cost), and leave each decision on GitHub as an `approved` issue with testable acceptance criteria, a `proposal`, or a `deferred` issue with the reason. Use whenever the maintainer wants to brainstorm, asks "what should we build next", "is X worth building", "review the proposals", or scopes a feature, even without the word "ideate".

36 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval 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.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • phanghonghaoSkill

    poster

    HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.

    Also in 4 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 1

    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:

    No topic given: list the open proposal issues, oldest first, each with one line on its problem and the recommendation.

    line 14
  2. Distinctive:

    How others solve it: Look at WireGuard's and OpenVPN's own tools and the nearest competitors, only when that informs the scope.

    line 23
  3. Very specific:

    Undecided: leave it as proposal, with the open question in a comment.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 33 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

Ideate

This is one of the two points where the maintainer decides; autopilot does everything else. The outcome of the session is labels and issue text that autopilot can build from with no further questions.

1. Pick the topic

  • No topic given: list the open proposal issues, oldest first, each with one line on its problem and the recommendation. Go through them with the maintainer.
  • A topic or issue given: work on that.

2. For each idea, bring evidence

Give short points, not prose:

  • The problem, and who has it. Link the issues, reactions, comments and discussions showing that real users hit it. Say plainly if nobody has.
  • How others solve it. Look at WireGuard's and OpenVPN's own tools and the nearest competitors, only when that informs the scope.
  • Two or three options, each with its cost: code and files touched, TUI density at 80×24 (CLAUDE.md "TUI density"), upkeep, and what it rules out later. Recommend one, or recommend not building it.
  • Items in "Removed on purpose" (CLAUDE.md): say so. Reviving one is a product decision for the maintainer.

3. Record the decision on the issue

The maintainer chooses; nothing is labelled approved without their yes in this session.

  • Build: rewrite the issue body so a builder needs nothing else:

    • Problem: one or two lines.
    • Scope: in, and explicitly out.
    • Acceptance criteria: observable, testable statements, each mapped to where its test goes: plan.rs/state.rs, a render test, tests/suite/, or P0 if only a live machine can show it.
    • Surfaces: CLI flags, keys, JSON fields, settings and docs that change.

    Label it approved, and remove proposal and deferred.

  • Not now: label it deferred, remove proposal, and comment the reason plus what would change the answer.
  • Undecided: leave it as proposal, with the open question in a comment.

End with the decisions in one line each, with links.

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.