agentleFS
Sign inStart free
dmzoneilldmzoneill/skills/appinterface-check/SKILL.md

appinterface-check

Skill2 starsChanged 19 days agoApache-2.0View on GitHub

Validate app-interface configuration and release readiness. Validates YAML, compares refs to live cluster, shows quotas, pending MRs. Use when user says "check app-interface", "app-interface validation".

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check $ref paths point to /services/ or /dependencies/

    line 34
  2. Distinctive:

    Check required fields: name, app, resourceTemplates

    line 35
  3. Very specific:

    No route to host → learn_tool_fix("kubectl_get_deployments", "no route to host", "VPN not connected", "Run vpn_connect()")

    line 75
  4. Very specific:

    No such host → learn_tool_fix("gitlab_mr_list", "no such host", "VPN not connected", "Run vpn_connect()")

    line 76

≈ “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

App-Interface Check

Inputs

InputTypeDefaultPurpose
saas_filestringtower-analyticsSaaS file name
namespace_stagestringtower-analytics-stageStage namespace
namespace_prodstringtower-analytics-prodProduction namespace
deploymentstringautomation-analytics-api-fastapi-v2Deployment to check for live SHA
stale_daysint7Alert if deployed SHA older than this
gitlab_projectstringautomation-analytics/automation-analytics-backendProject for pending MRs
app_namestringautomation-analyticsApplication name for search

Workflow

1. Bootstrap

  • persona_load("release") — appinterface tools
  • check_known_issues("appinterface", ""), check_known_issues("release", "")
  • knowledge_query(project="automation-analytics-backend", persona="release", section="gotchas")

2. Get SaaS File

  • appinterface_search(query="{app_name}")
  • appinterface_get_saas(service_name="{saas_file}")
  • Parse refs: stage_ref, prod_ref (40-char SHAs), $ref paths

3. Validation

  • Validate SHA format: 40-char hex or 'main'
  • Check $ref paths point to /services/ or /dependencies/
  • Check required fields: name, app, resourceTemplates

4. Live State (switch to devops)

  • persona_load("devops")
  • kubectl_get_deployments(namespace="{namespace_stage}", environment="stage") — extract deployed image SHA
  • kubectl_get_deployments(namespace="{namespace_prod}", environment="prod") — prod SHA

5. Compare State

  • stage_in_sync = app-interface stage_ref matches live cluster
  • prod_in_sync = app-interface prod_ref matches live cluster
  • stage_ahead_of_prod = stage has newer ref
  • ready_to_promote = stage_ahead and stage_in_sync

6. Diff & Resources

  • appinterface_diff() — uncommitted changes
  • appinterface_resources(namespace="{namespace_stage}")
  • kubectl_get(resource="resourcequota", namespace="{namespace_stage}", environment="stage")
  • kubectl_get(resource="limitrange", namespace="{namespace_stage}", environment="stage")

7. Pending MRs (switch to developer)

  • persona_load("developer")
  • gitlab_mr_list(project="{gitlab_project}", state="opened", per_page=10)

8. Release Readiness

  • ready = validation_ok and stage_ahead and no_pending_changes
  • blockers: validation issues, stage not ahead, uncommitted changes
  • warnings: open MRs, stage drift

9. Report

  • Validation status
  • Live state comparison (stage vs prod)
  • Pending changes
  • Resource quotas/limits
  • Pending MRs
  • Release readiness
  • Log: memory_session_log("Checked app-interface", "Ready: {ready}")

10. Failure Learning

  • Not found → learn_tool_fix("appinterface_get_saas", "not found", "SaaS file missing", "Check saas_file input")
  • Forbidden → learn_tool_fix("kubectl_get_deployments", "forbidden", "K8s auth expired", "Run kube_login('stage') and kube_login('prod')")
  • No route to host → learn_tool_fix("kubectl_get_deployments", "no route to host", "VPN not connected", "Run vpn_connect()")
  • No such host → learn_tool_fix("gitlab_mr_list", "no such host", "VPN not connected", "Run vpn_connect()")

Key MCP Tools

  • persona_load, appinterface_search, appinterface_get_saas, appinterface_diff, appinterface_resources
  • kubectl_get_deployments, kubectl_get
  • gitlab_mr_list
  • check_known_issues, learn_tool_fix, knowledge_query, memory_session_log

Key Namespaces

  • tower-analytics-stage — stage
  • tower-analytics-prod — production

If Ready to Release

skill_run("release_to_prod", '{"commit_sha": "{stage_ref}"}')

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