agentleFS
scolladonscolladon/craft/skills/propose/SKILL.md

propose

Skill2 starsChanged 34 days agoMITView on GitHub

Craft phase 10 - pre-PR gate, push, and PR creation per repo policy. Blocked until validation triage is complete.

11 other projects use a version of this.

Adopted by

Most recently taken up by

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 10 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:

    Prose-lint the drafted body (advisory): Before invoking the port, write the drafted body to a temp file and scan it under the same posture …

    line 31

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

craft:propose

Preamble (always runs — non-overridable)

  1. Manifest read (lint if standalone). Probe: remote? none → propose AND integrate no-op with a note (work stays on the local branch); the run ends after documentation.
  2. Cross-phase invariant check: the validation phase's run has landed or recorded a no-op, survivors are triaged, gates.phase is green. Not yet → wait; never create the PR early.

Procedure (default body — a manifest override: replaces everything below)

  1. Pre-PR gate (pr.pre-pr-gate if declared): contract = check + documented remediation + documented exceptions (both live in the manifest body or a phase context file — never memory). Run it; apply the remediation in its own conventional commit; re-gate.
  2. Consult push action (see docs/contributing/specs/policy.md for surface semantics). Obey the returned surface, then push -u origin <branch>.
  3. Consult propose action (see docs/contributing/specs/policy.md). Obey the returned surface:

    • ask (default, ADR-127) — hand the drafted body to the user and stop (pr.creator: user behaviour); on approval proceed with the PR creation, on decline record POLICY(ask:propose→declined) and block.
    • never — refuse; record POLICY(never:propose); phase no-ops.
    • always — create the PR without stopping; record POLICY(always:propose); supersedes the pr.creator: user stop (ADR-128 — Supersede).

    Prose-lint the drafted body (advisory). Before invoking the port, write the drafted body to a temp file and scan it under the same posture the ci.sh cadence uses: resolve the gate via node "${CRAFT_ROOT:-${CLAUDE_PLUGIN_ROOT}}/engine/bin/hygiene-gate.js" <manifest-path> (default advisory), then run node "${CRAFT_ROOT:-${CLAUDE_PLUGIN_ROOT}}/engine/bin/prose-lint.js" --gate <gate> --waiver-source <body-file> -- <body-file>. Fold any SLOP-FOUND(<file>): … lines into the run record and a hygiene note in the PR body; the hygiene.gate knob and the SLOP-WAIVE(<file>) waiver are honored (the body is its own waiver source, so a deliberate ban-list word can be waived in-body). The in-body waiver is its own line, SLOP-WAIVE(<body-file>): <reason>, starting at column 0 and outside any code fence; the token mid-sentence or inside a fence waives nothing. PR body only — never the ci.sh touched-docs cadence.

    Invoke the VCS port propose(title, body) (see docs/contributing/specs/vcs.md); the adapter owns the host CLI. Body: drafted in the documentation phase per templates/pr-body.md — a Background · Intuition · Code narrative, then a Provenance & verification trailer (decisions + ADRs, design path, divergences, pinned behaviours, test plan, run record).

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.