agentleFS
metagit-aimetagit-ai/metagit-cli/skills/metagit-upstream-scan/SKILL.md

metagit-upstream-scan

Skill4 starsChanged 12 days agoMITView on GitHub

Use when a coding agent encounters likely upstream blockers and must find related workspace repositories, files, and probable root causes.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the current repo does not appear to contain the full fix and related repositories may hold the source issue.

    line 8
  2. Distinctive:

    Use this token-efficient wrapper for upstream discovery tasks:

    line 19
  3. Very specific:

    Read workspace repository map from active .metagit.yml.

    line 29
  4. Very specific:

    Run metagit_workspace_index to verify repo availability and sync state.

    line 30
  5. Very specific:

    Use metagit_workspace_search with category preset (terraform, docker, infra, ci).

    line 31
  6. Very specific:

    Use metagit_upstream_hints to rank candidate repositories and files.

    line 32
  7. Distinctive:

    Start narrow with issue-specific terms (error, module, variable, image tag).

    line 40
  8. Distinctive:

    Prefer repositories referenced by workspace metadata before searching unknown repos.

    line 42
  9. Distinctive:

    Keep this workflow read-only unless an explicit sync action is requested.

    line 55

≈ “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

Metagit Upstream Discovery Skill

Use this skill when the current repo does not appear to contain the full fix and related repositories may hold the source issue.

Supported Use Cases

  • Missing Terraform input in a shared module
  • Docker base image/version mismatch across repos
  • Shared infrastructure definitions causing local failures
  • CI pipeline breakages tied to upstream templates/workflows

Local Script Wrapper (Use First)

Use this token-efficient wrapper for upstream discovery tasks:

  • ./scripts/upstream-scan.sh [root_path] "<query>" [preset] [max_results]

Output format:

  • compact status line
  • top ranked repo hints (hint)
  • top search file hits (hit)

Workflow

  1. Read workspace repository map from active .metagit.yml.
  2. Run metagit_workspace_index to verify repo availability and sync state.
  3. Use metagit_workspace_search with category preset (terraform, docker, infra, ci).
  4. Use metagit_upstream_hints to rank candidate repositories and files.
  5. Return a concise action plan:
    • top candidate repos
    • likely files/definitions
    • whether sync is needed before deeper analysis

Search Strategy

  • Start narrow with issue-specific terms (error, module, variable, image tag).
  • Expand to broader shared terms if no hits.
  • Prefer repositories referenced by workspace metadata before searching unknown repos.

Output Contract

Return:

  • ranked candidates with rationale
  • suggested next file openings
  • confidence level and unresolved assumptions

Safety Rules

  • Restrict search to configured workspace repositories.
  • Cap result size and duration.
  • Keep this workflow read-only unless an explicit sync action is requested.

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.