agentleFS
Sign inStart free
kvantatechkvantatech/RedLine/.github/skills/open-draft-pr/SKILL.md

open-draft-pr

Skill1 starsChanged 3 months agoMITView on GitHub

Type: skill (1 model narration) · Used by: perf-author · Status: STUB (P0 scaffold — not yet implemented) - Input: the verified script (graduated from drafts/<team>/<profile>/) plus context (environment, what changed). - Target: the team's upstream repo (the "shelf" — e.g. ui-deployments), branch perf-author/<team>-<profile>. Never the agent repo, never inside live/*. On merge, the source leaves the factory drafts/ (the team repo becomes the home-of-record). - Output: a DRAFT PR with a clear title and body summarizing the script. NEVER…

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    NEVER commit to main; NEVER auto-merge.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

open-draft-pr

Open a DRAFT PR with the authored script — never commit to main.

Type: skill (1 model narration) · Used by: perf-author · Status: STUB (P0 scaffold — not yet implemented)

Prompt

Open a DRAFT pull request carrying the authored or leveled-up k6 script.

  • Input: the verified script (graduated from drafts/<team>/<profile>/) plus context (environment, what changed).
  • Target: the team's upstream repo (the "shelf" — e.g. ui-deployments), branch perf-author/<team>-<profile>. Never the agent repo, never inside live/*. On merge, the source leaves the factory drafts/ (the team repo becomes the home-of-record).
  • Output: a DRAFT PR with a clear title and body summarizing the script.

NEVER commit to main; NEVER auto-merge. A human reviews and merges.

No push access? Use the manual-export fallback (planning agent/DELIVERY-MODEL.md §3): hand the team the proven script.js + perf-gate.yaml + an informational baseline copy; the team commits on their own branch and merges via their own reviewer. The PE never touches their main.

Tools

GitHub MCP

Data

  • Reads: the graduated script (from drafts/<team>/<profile>/); live/ (read-only, for PR context — which environment the script targets)
  • Writes: a DRAFT PR in the team's upstream repo (not this agent repo; not live/*)

Notes

Activation: P5. Workflows are proposals only — no irreversible action mid-run. Hard rule: DRAFT PR only, no direct commits to main and no auto-merge. The human is the merge gate.

Frozen skill registry: AGENTS.md in this repo

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.

Check your setup, free