agentleFS
Sign inStart free
ThakurvaibhavThakurvaibhav/platform-agent-harness/skills/contract-validation/SKILL.md

contract-validation

Skill2 starsChanged 6 days agoApache-2.0View on GitHub

Validate a feature, workflow, or platform change against an explicit contract. Generic — does not require a dedicated validator agent. Any CLI agent executes the contract, collects evidence, and produces a structured report.

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:

    Use when a feature, rollout, or platform change needs to be validated against an explicit pass/fail contract.

    line 12
  2. Distinctive:

    Read the validation contract.

    line 27
  3. Very specific:

    Use templates/validation-report.template.json for machine-readable reports or the standard handoff contract for human review.

    line 57
  4. Very specific:

    When the same contract runs across N targets (clusters, services, dashboards), pair this skill with core/protocols/parallel-dispatch.md: …

    line 61

≈ “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

Contract Validation

Use when a feature, rollout, or platform change needs to be validated against an explicit pass/fail contract.

Inputs

  • Validation contract — a list of numbered assertions, each with a pass/fail criterion and required evidence.
  • Target — repo, service, cluster, dashboard.
  • Preconditions — what must be true before starting.
  • Test surface — docs, CLI, API, UI, Kubernetes, GitOps, observability.
  • Evidence requirements — what counts as proof.
  • Output format — JSON report, structured handoff, or both.

A contract is a runnable artifact, not a wish list. See templates/validation-contract.template.md.

Workflow

  1. Read the validation contract.
  2. Identify each assertion and its required evidence.
  3. Confirm prerequisites are satisfied.
  4. Execute each assertion through the real contract surface where possible (real command, real API, real query).
  5. Mark each assertion as pass, fail, blocked, or skipped.
  6. Capture evidence for every result (command output, query result, screenshot, exit code).
  7. Report blockers and any non-disruptive checks attempted.
  8. File follow-up bd tasks for failures or gaps.

Status meanings

  • pass: observed behavior matches the contract.
  • fail: observed behavior contradicts the contract.
  • blocked: prerequisite unavailable or unsafe to proceed.
  • skipped: explicitly out of scope or not applicable to this run.

Evidence by surface

SurfaceEvidence
CLIcommand, output summary, exit code
APIrequest, status code, response summary
UIscreenshot, console / network summary
Kubernetesread-only command output
GitOpsrendered manifests, diff, sync status
Observabilityquery, time window, result summary
LogsLogQL query, count, sample lines

Output

Use templates/validation-report.template.json for machine-readable reports or the standard handoff contract for human review.

Pairing with parallel dispatch

When the same contract runs across N targets (clusters, services, dashboards), pair this skill with core/protocols/parallel-dispatch.md: launch N workers, each executing the contract against one target, then aggregate.

A 12-check contract run across 3 clusters in parallel completes in ~5 minutes vs ~45 minutes sequential.

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