agentleFS
poradaporada/domfiles/skills/.dom-sensible-contribution-flow/SKILL.md

dom-sensible-contribution-flow

Skill7 starsChanged 4 days agoMITView on GitHub

Use whenever `sensible-contribution-flow` applies.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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:

    When creating or reusing a fork for a contribution, keep origin pointing to the fork and upstream pointing to the verified upstream …

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Contribution Flow

Load sensible-contribution-flow and apply these personal contribution defaults under the global Explicit user direction policy. The base owns the contribution lifecycle and its authorization checkpoints.

Fork Remotes

When creating or reusing a fork for a contribution, keep origin pointing to the fork and upstream pointing to the verified upstream repository. Reconcile existing remote names during authorized local setup under the base’s Configure Git Remotes rules, preserving existing branch tracking relationships.

Implementation Review

Read and apply super-review’s SKILL.md from the same installed skills root for the coordinator’s implementation review of initial contributions and implementation revisions, including documentation changes. Pass the base workflow’s review scope and established authority to it. Leave the base’s design review and standalone read-only review routes unchanged.

Unless the user selects different stages or waives review, use the initial stage to satisfy the base’s review before commit preparation. For requests limited to working tree changes, select only that stage. Otherwise, select the full sequence, with the base’s commit preparation serving as super-review’s committed-target preparation. Carry the base’s commit authorization, packaging, message, and shared pull request history constraints into that operation. After later changes, apply super-review’s continuation requirements before declaring readiness.

Under External services and Agent communication, include super-review’s selected recipients and processing providers through T3 Code, required follow-ups, replacements, repeated final reviews, and disclosure of task-required repository material and non-secret context in the contribution’s existing execution checkpoint. Reuse explicit authorization that already covers those effects. When no checkpoint is otherwise needed, resolve only the uncovered reviewer exchange authorization before implementation. Loading this overlay doesn’t authorize disclosure.

Adjacent Opportunities

Apply global Task refinement and Preserve Adjacent Opportunities with upstream fit in mind:

  • Current PR: Include accepted improvements when they fit upstream expectations for this contribution. Sharing files or having a small diff doesn’t establish that fit.
  • Separate PR idea: Surface an independently useful opportunity whose distinct outcome, design decision, or review burden makes it a better separate contribution. Explain the separation without implementing it or opening another PR.
  • Do not pursue: Set aside opportunities whose benefit doesn’t justify the work.

Include accepted work in the contribution’s commit planning and review coverage, preserving its packaging constraints and shared pull request history rules.

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.