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

rail-pass

Skill5 starsChanged 4 months agoMITView on GitHub

Compact the current conversation into a pass document for a fresh agent session.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Write a pass document so a fresh agent can continue.

    line 9
  2. Very specific:

    If light align finished decisions but align.md is not written yet: say so explicitly and make writing align.md the next-session goal (do …

    line 15
  3. Very specific:

    If align.md exists but spec.md / tasks are not done: next-session goal is continue the planning chain (/rail-spec.

    line 16
  4. Distinctive:

    If the user passed arguments, treat them as the next session focus

    line 24
  5. Distinctive:

    Do not continue implementing in this session after writing the pass document

    line 25

≈ “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 Pass

Write a pass document so a fresh agent can continue. Save under the OS temp directory or docs/monorail/<feature>/pass-<date>.md if a feature slug is active and the user prefers repo-local — ask once if unclear. Find active efforts with the shell (ls docs/monorail/); search tools skip gitignored paths.

Include

  • Goal of the next session
  • Decisions already made (pointers under docs/monorail/ — CONTEXT.md, ADRs, feature paths — do not duplicate)
  • If light align finished decisions but align.md is not written yet: say so explicitly and make writing align.md the next-session goal (do not start /rail-spec until it exists)
  • If align.md exists but spec.md / tasks are not done: next-session goal is continue the planning chain (/rail-spec; it stops for your go/no-go before /rail-slice) — do not ask the user to type each stage separately
  • Open questions
  • Suggested skills (/rail-align, /rail-spec, /rail-build <feature-slug>, …) — planning-chain skills auto-continue downstream (/rail-spec stops once for your go/no-go before slice); /rail-build runs tasks serially in one session by default (prefer a fresh session when the current context is already heavy; use this pass doc when a run's context genuinely degrades; concurrent builds need separate worktrees)
  • Exact file paths to read first (align.md, spec.md, task file, …)

Rules

  • Redact secrets and PII
  • If the user passed arguments, treat them as the next session focus
  • Do not continue implementing in this session after writing the pass document

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