agentleFS
AlpacaLabsLLCAlpacaLabsLLC/skills-for-architects/skills/proposal/SKILL.md

proposal

Skill390 starsChanged 54 days agoMITView on GitHub

Draft and register project proposals, protect issued terms, and record explicitly evidenced commercial lifecycle changes. Sending messages is separate authorization.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use audit.

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.
  • OpenAISkill

    audit

    Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Before acting, read the host contract, this component's declaration (skill:proposal), and applicable workspace semantics.

    line 16

“Common” is measured: kept by at least 6 in 10 of the 14 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

/as:proposal

Before acting, read the host contract, this component's declaration (skill:proposal), and applicable workspace semantics. Load only the required modes from the shared catalog.

<!-- architecture-studio:harness-compatibility -->

Use the host adapter and available native tools or ordinary task-specific code. Operation names identify the semantic work in the workspace model, not installed functions or a script API. Resolve canonical context before durable work. No Arch Studio runner, package installation or executable reconstruction is required. Existing exact authorization persists; ask only for material missing information or missing permission.

Own documents of kind proposal. Resolve the project; never create a global proposal register. Use the proposal template, keeping exactly one nonempty issued-terms marker block. Capture normal-case title, date, explicit local revision, scope/fees/exclusions and user-selected terms. Unknowns remain TO CONFIRM; their presence is context, not an invented workflow gate. Use human Rev. NN and a safe received/authored filename; confirmed lineage uses supersedes.

Before changing records

Before persistent changes, follow the native mutation sequence: Inspect → Prepare → Verify preparation → Apply → Verify result → Complete. Inspect pending work first. Finish and verify preparation before the first canonical write: separately reread every saved original and prepared file, check its complete actual bytes, establish durable saving, and inspect actual permissions, ownership and ACLs. Merely writing recovery files does not finish verification. Apply only that verified set. Mark complete only after fresh readback validates the entire affected result and its relationships. Read-only requests and inline drafts need no publication sequence.

For proposal creation, prepare the complete proposal and DOCUMENTS.csv together, including destination absence. Lifecycle changes affect DOCUMENTS.csv; the proposal's actual raw bytes and issued-terms seal are read guards. Additional rendered outputs are separate registered documents with their own complete affected set. Do not publish a proposal first and prepare its register afterward.

The harness prepares the terms from authorized inputs and current applicable originals, then proposal.create registers the authored source under confirmed coordinates. Do not copy external clause libraries or portray local summaries as current legal authority. Assembled terms include: “These clauses are drafting guidance, not legal advice; have a licensed attorney review before signing.”

proposal.list/status/verify read the actual registered record and protected terms. proposal.send only records supplied send date/evidence and seals the exact issued terms; it never emails or uploads. proposal.set-status records accepted/declined/superseded with explicit evidence/date. Acceptance may seal a draft directly when an earlier send was not recorded; no mandatory proposal→agreement→invoice sequence is imposed. Never infer acceptance, payment or project status from activity.

Once sealed, changed terms require a new registered revision, not replacement of the stored checksum. Lifecycle evidence stays in registry history outside the issued block. Preserve malformed input and checksum failures without guessing repair. HTML letters may use a confirmed firm template or bundled proposal-letter template, but the registered Markdown terms remain canonical; register additional outputs as documents.

Agreement promotion cites the accepted proposal ID and protected checksum without copying it. Tasks/time/invoices and project facts retain their owners. Fresh readback and actual inspection support completion; a recorded send event does not prove that any message was actually sent.

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.