agentleFS
cnoe-iocnoe-io/ai-platform-engineering/.claude/skills/speckit.sync-template/SKILL.md

speckit.sync-template

Skill438 starsChanged 53 days agoApache-2.0View on GitHub

You MUST consider the user input before proceeding (if not empty). Valid arguments: --check (preview only, no writes), --force (apply without prompting), a specific version string like v1.2.0. You are syncing this repository with the upstream cisco-eti/repo-template. Follow these steps exactly. 1. Use the GitHub API to find the latest release of the upstream repo: GET https://api.github.com/repos/<source>/releases/latest 2. Extract tag_name (e.g., v1.1.0) and assets (find the ZIP asset and manifest.json asset). 3. If the user specified a version in $ARGUMENTS,…

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 3 are distinctive, and 10 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 10

    Very specific

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

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

    If .specify/upstream.yml does not exist, halt and tell the user: "This repo has no .specify/upstream.yml.

    line 28
  2. Very specific:

    Use the GitHub API to find the latest release of the upstream repo: GET https://api.github.com/repos/<source>/releases/latest

    line 32
  3. Very specific:

    If the user specified a version in $ARGUMENTS, use that version instead of latest.

    line 35
  4. Very specific:

    If equal: report "Already at latest version <version>.

    line 37
  5. Very specific:

    Start with changed_files from the manifest.

    line 50
  6. Very specific:

    Remove any file listed in .specify/upstream.yml overrides — these are skipped.

    line 51
  7. Very specific:

    If --check was passed, stop here.

    line 72
  8. Very specific:

    If semver_bump is "major":

    line 74
  9. Distinctive:

    Ask the user: "Do you want to proceed?

    line 78
  10. Distinctive:

    After a successful sync:

    line 95
  11. Very specific:

    If any docs/plan/ files were updated: "Tip: Review the updated docs/plan/ files.

    line 97
  12. Very specific:

    If any .claude/skills/ or .agents/skills/ were updated: "New or updated skills are available.

    line 98
  13. Distinctive:

    If the bump was MAJOR: "MAJOR sync applied.

    line 99

≈ “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
<!-- Sync with upstream repo-template updates --><!-- AUTO-GENERATED — DO NOT EDIT --><!-- Source: .specify/templates/commands/sync-template.md --><!-- Regenerate: make generate-agent-files -->

description: Sync with upstream repo-template updates scripts: sh: scripts/bash/sync-template.sh "$ARGUMENTS"

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty). Valid arguments: --check (preview only, no writes), --force (apply without prompting), a specific version string like v1.2.0.

Outline

You are syncing this repository with the upstream cisco-eti/repo-template. Follow these steps exactly.

Step 1 — Read current state

  1. Read .specify/upstream.yml.
    • Extract source (e.g., cisco-eti/repo-template), version (current applied version), overrides (list of files to skip).
  2. If .specify/upstream.yml does not exist, halt and tell the user: "This repo has no .specify/upstream.yml. Initialize it first using the template at cisco-eti/repo-template."

Step 2 — Discover latest release

  1. Use the GitHub API to find the latest release of the upstream repo: GET https://api.github.com/repos/<source>/releases/latest
  2. Extract tag_name (e.g., v1.1.0) and assets (find the ZIP asset and manifest.json asset).
  3. If the user specified a version in $ARGUMENTS, use that version instead of latest.
  4. Compare tag_name to current version:
    • If equal: report "Already at latest version <version>. Nothing to do." and stop (unless --force was passed).

Step 3 — Read the manifest

  1. Download manifest.json from the release assets.
  2. Parse:
    • semver_bump: "major", "minor", or "patch"
    • changed_files: list of files changed in this release
    • breaking_files: list of files with breaking changes
    • changelog_url: link to view details

Step 4 — Determine what to apply

  1. Start with changed_files from the manifest.
  2. Remove any file listed in .specify/upstream.yml overrides — these are skipped.
  3. Remaining files = apply set.
  4. Intersect apply set with breaking_files → breaking set (files in apply set that are also breaking).

Step 5 — Preview (always show before writing)

Print a summary table:

Upstream version: v1.0.0 → v1.1.0 (MINOR bump)

Files to apply:
  docs/plan/SKILLS.md                      [updated]
  .claude/skills/speckit.new-skill/SKILL.md    [added]

Files skipped (overrides):
  docs/plan/CONSTITUTION.md                [override — local version preserved]

Breaking changes: none

If --check was passed, stop here. Do not write any files.

If semver_bump is "major":

  • Print: "⚠️ MAJOR version bump — this includes constitutional or breaking changes."
  • Print the list of breaking files with a note about each.
  • Ask the user: "Do you want to proceed? Constitutional changes require human review. (yes/no)"
  • If no: stop.

Step 6 — Apply files

  1. Download and extract the release ZIP.
  2. For each file in the apply set: a. If the local file does not exist: write it directly (new addition). b. If the local file exists: show a unified diff, then overwrite it.
  3. Update .specify/upstream.yml:
    • Set version to the new version tag (strip the v prefix: 1.1.0)
    • Set pinned_at to today's date (ISO 8601)
    • Leave overrides unchanged.
  4. Report: "Sync complete. Applied <N> files. Version updated to <version>."

Step 7 — Post-sync guidance

After a successful sync:

  • If any docs/plan/ files were updated: "Tip: Review the updated docs/plan/ files. If the ARCHITECTURE.md or CONSTITUTION.md was updated, compare with your project-specific overrides."
  • If any .claude/skills/ or .agents/skills/ were updated: "New or updated skills are available. Run /speckit.specify --help or check .claude/skills/ for changes."
  • If the bump was MAJOR: "MAJOR sync applied. Verify your override files are still consistent with the new template base."

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.