agentleFS
aymericbeaumetaymericbeaumet/dotfiles/.agents/skills/blueprint/SKILL.md

blueprint

Skill22 starsChanged 2 months agoMITView on GitHub

Propose plan-only improvements to ~/.agents/blueprints from the current project. Use when the user asks to enrich, improve, update, or extract a blueprint.

68 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use assess, align 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.
  • AWSSkill

    assess

    Run a 5-domain CAF security posture assessment for an AWS service. Produces (1) assessment-summary.md — CAF-structured findings with GAPS tables, (2) sar-facts.json — extracted SAR data, (3) checkpoint-results.json — factual checkpoint verification. These feed into the research, validate, and generate phases.

    Also in 3 projects that use this

  • marylinSkill

    align

    Audit project structure, docs health, and lifecycle compliance. Use when a project feels disorganized, after major refactors, before onboarding a contributor, or periodically as a health check.

    Also in 3 projects that use this

  • sahinSkill

    execute

    Also in 5 projects that use this

  • LangChainSkill

    docker-patterns

    Best practices for Docker containerization and multi-stage builds

    Also in 3 projects that use this

  • lukeleekrSkill

    scout

    GitHub 레포 스카우터. 내 Claude Code + Codex App 환경을 분석하여 필요한 GitHub 레포를 자동 추천하거나, 키워드로 GitHub을 검색합니다. "scout", "스카우트", "깃헙 탐방", "레포 추천", "repo search" 등의 키워드에 반응합니다.

    Also in 3 projects that use this

  • genomewalkerSkill

    learn

    Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.

    Also in 7 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 66 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not write blueprints into the current project.

    line 21
  2. Distinctive:

    Ask which candidates to include when the selection has not already been confirmed.

    line 45
  3. Distinctive:

    Wait for selection before changing unconfirmed candidates.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 66 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

Blueprint

Stay in plan mode until the user confirms which candidates to include. Complete the comparison and prepare concrete proposed revisions before asking. Honor choices already confirmed in the session; apply those choices without asking again, and keep unconfirmed candidates as proposals.

Location

Blueprints live at:

~/.agents/blueprints/<KIND>.md

<KIND> is an uppercase short name such as CLI. Resolve that directory from the home directory. Do not write blueprints into the current project.

Task

  1. Resolve the current project root. If there is no Git repository, ask which project to inspect.
  2. List existing files in ~/.agents/blueprints/.
  3. Survey the current project. Read only what is needed to judge reuse:
    • stack and language manifests
    • CI workflows
    • README
    • direct dependencies
    • license
    • build, test, and release entry points
    • packaging
    • project AGENTS.md
  4. Choose the matching blueprint, or propose creating a new <KIND>.md when none fits.
  5. Diff durable project conventions against that blueprint.
  6. Classify every candidate:
    • Keep — already specified
    • Add — reusable and missing
    • Update — specified but drifted
    • Skip — product-specific, secret, machine-specific, or obvious from the repo
    • Ask — reusable value is unclear
  7. Present a short plan: target path, concrete proposed adds and updates, and material skips.
  8. Ask which candidates to include when the selection has not already been confirmed. Cover the relevant surveyed areas and every Ask item. Do not assume omitted areas should be copied.
  9. Wait for selection before changing unconfirmed candidates. If the user has already confirmed choices, apply only those revisions and check the resulting diff against the selection.

Include only when

  • The convention is stable and would help start or align another repo of the same kind.
  • It is not recoverable by reading a typical repository of that stack.
  • It is not product behavior, a secret, or a one-off workaround.

Output

Lead with the target blueprint path. For a proposal, list Add / Update / Skip / Ask and end with the remaining selection question. After applying confirmed choices, summarize the revisions and any unresolved candidates.

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.