agentleFS
tamesystemstamesystems/intent-engineering-skills/skills/validate/SKILL.md

validate

Skill0 starsChanged 39 days agoMITView on GitHub

Determine whether a verified change actually satisfies the governing intent under representative conditions. Use when technical correctness alone cannot establish that the right outcome was achieved.

63 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use policy-init, create and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • open-coder-aiSkill

    policy-init

    Create conformant Chock policy from request. args(request, target_path,

    Also in 3 projects that use this

  • MicrosoftSkill

    create

    Also in 4 projects that use this

  • HermeticOrmusSkill

    close

    End-of-session ritual. Captures session state, updates auto-memory, writes a session summary, then exits the session cleanly.

    Also in 4 projects that use this

  • Hugging FaceSkill

    sprint

    Work on a batch of GitHub issues in parallel using Agent Teams. Creates one worktree per issue with TDD enforcement, coordinates via a lead agent, then produces stacked PRs.

    Also in 4 projects that use this

  • qtzx06Skill

    eval

    Evaluate trained YOLO model accuracy with mAP metrics and per-class error analysis. Identifies failure cases for targeted improvement. Use after training.

    Also in 4 projects that use this

  • csiddhant796-blipSkill

    board

    Read, write, and browse the AgentHub message board for agent coordination.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 53 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use representative conditions: Prefer realistic actors, environments, data, workloads, workflows, and dependency behavior.

    line 14

“Common” is measured: kept by at least 6 in 10 of the 53 edited versions of this file we could read. “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

Validate

Determine whether we built the right thing. Verification establishes conformance; validation establishes intended effect.

Work

  1. Return to the intent. Temporarily ignore implementation success and restate the real-world change this work was meant to produce.
  2. Define outcome evidence. Identify observations that would support or falsify achievement of that intent. Do not substitute convenient implementation metrics without justification.
  3. Use representative conditions. Prefer realistic actors, environments, data, workloads, workflows, and dependency behavior.
  4. Detect proxy success. Deployment is not adoption; traffic is not demand; passing tests is not usability; feature completion is not problem resolution.
  5. Compare reality with intent. Classify the outcome as satisfied, partially satisfied, not satisfied, or insufficient evidence.
  6. Expose discrepancy. Describe the gap without rationalizing it. Route the discrepancy to grounding, specification, investigation, decision, or realization as appropriate.

For a UI added to an existing product, inspect the complete representative workflow inside its real layout and compare it with the product's established screens. Evaluate hierarchy, primary actions, density, typography, spacing, and relevant viewport behavior. An isolated component capture or passing interaction test does not establish visual integration. Record discrepancies or unavailable visual evidence explicitly; do not substitute functional coverage for usability or fit.

Return

  • Governing intent
  • Validation method
  • Outcome evidence
  • Result: SATISFIED / PARTIAL / NOT SATISFIED / INSUFFICIENT EVIDENCE
  • Discrepancies
  • Remaining uncertainty
  • Next loop, if needed

Failure signals

Watch for validating the implementation instead of the intent, proxy metrics silently becoming goals, unrealistic test conditions, and declaring victory because the artifact shipped.

Done when

There is sufficient representative evidence to assess the intended outcome, or the inability to obtain that evidence is itself explicit and actionable.

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.