agentleFS
Sign inStart free
guangzanguangzan/monorail/skills/rail/SKILL.md

rail

Skill5 starsChanged 4 months agoMITView on GitHub

Ask which rail skill or flow fits. Router over the rail pack.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Carchar91/recipient-aware-ai★ 4same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository12 other files it gives its agents.

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:

    If the window breaks mid-chain, durable align.md / spec.md still feed the next skill when the user resumes.

    line 30

≈ “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

Rail

A flow is a path through skills. Most work follows the main chain.

Main chain: idea → ship

  1. /rail-setup — once per repo (all rail docs under docs/monorail/)
  2. /rail-align — light grilling → writes align.md
  3. /rail-spec — write docs/monorail/<feature>/spec.md from align.md (refuses empty context)
  4. /rail-slice — write tasks/NN-*.md with blockers
  5. /rail-build — user-triggered as /rail-build <feature-slug>; runs frontier tasks serially in one session by default (implemented inline in the main session; a fresh implementer sub-agent only on a hand-off trigger — unfamiliar/wide territory or degraded context). When the planning-session context is already heavy, open a fresh session for the build. Concurrent builds require separate git worktrees (see rail-build)

Planning chain (auto-continue)

align → spec → slice is one planning chain. When a stage finishes successfully in this session, continue the next stage in the same session by reading and following that skill's SKILL.md — do not stop and ask the user to type the next /rail-*. Two exceptions: /rail-spec confirms the test seam once before writing spec.md and waits for the answer; then spec → slice is gated — after writing spec.md, /rail-spec stops and asks once (continue slicing now / revise the spec / pause) and never slices without that confirmation.

Align writes align.md → continue /rail-spec → gate → continue /rail-slice (on confirm) Standalone /rail-spec writes spec.md → gate; /rail-slice ends the planning chain (suggest /rail-build <feature-slug> only)

Do not auto-continue into /rail-build — build stays user-triggered as /rail-build <feature-slug>: the planning chain ends at slice so you can review the task list before implementation starts. Prefer a fresh session when the planning context is already heavy; otherwise the same session is fine. Once a build starts, it runs tasks serially in that session — finishing one task continues to the next frontier task with no context-clearing between tasks (tasks run inline by default; a fresh implementer sub-agent takes over only when territory is unfamiliar/wide or the run's context degrades). Builds ask nothing: defaults are run to queue-clear with one commit per task; the user states any deviation (review pause, no-commit, narrower run) in their command. If the run's context degrades mid-build, /rail-pass or a fresh sub-agent / session resumes it. To run several builds at once, set up one git worktree per task first — more sessions on the same cwd are not parallel-safe.

Stop auto-continue when: the user asked to stop after this stage; context is near limits (use /rail-pass); or an adequacy / fail-closed gate says stop.

If the window breaks mid-chain, durable align.md / spec.md still feed the next skill when the user resumes.

In-pack handoffs only

Handoffs (auto-continue or suggest) use the next rail skill by exact name (/rail-align, /rail-spec, /rail-slice, /rail-build, …). Do not substitute lookalike skills from other packs (e.g. /to-spec for /rail-spec, /to-tickets / /to-issues for /rail-slice) even if those are installed in the same agent.

Side paths

  • No codebase → /rail-grill
  • Context full / branch session → /rail-pass
  • Hard bug → /rail-debug
  • Review a branch / PR / WIP → /rail-review (opt-in; not part of build)

Vocabulary underneath

  • /rail-tdd — red-green-refactor (also used inside build)

Not in this pack (yet)

triage, standalone wayfinder, architecture-improve tours — use other packs or wait for a later rail version.

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