Skip to content
Skills Library
AI & agents · Planning

define-validation

/define-validation

Use to add validation criteria to a spec or plan. Triggers include "define validation", "how will we validate", "what should the AI check", and "add validation to this".

Author
rjroy ↗
Repository
vibe-garden ↗
Licence
MIT
Last repository change
06.10.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 06.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use to add validation criteria to a spec or plan. Triggers include "define validation", "how will we validate", "what should the AI check", and "add validation to this".

Triggers from the description

define validationhow will we validatewhat should the AI checkadd validation to this
Original author description

Use to add validation criteria to a spec or plan. Triggers include "define validation", "how will we validate", "what should the AI check", and "add validation to this".

How it works

  1. What counts
Original SKILL.md headings · 27 lines, 331 words
SKILL.md preview
---
name: define-validation
description: Use to add validation criteria to a spec or plan. Triggers include "define validation", "how will we validate", "what should the AI check", and "add validation to this".
---

# Define Validation

Validation answers: "How will the AI know this is done?"

It must be behavioral and actionable — something the AI can actually run or observe, like "run the CLI with these args and confirm the output contains X." Not "verify the UX feels right." See "What counts" below for the range of forms this can take.

Add a validation section to an existing spec or plan. If none exists, save standalone to `.lore/work/validation/[topic].md`. Load `../../shared/frontmatter-schema.md (resolved from this skill's base directory)` for the frontmatter fields before writing. New documents start `draft`; use `approved` only for explicit user approval (including editing to approve) or a request for the relevant next process step, never infer it from arbitrary edits. Use `completed` when applicable agent work is done, independently of approval; use `archived` when archived. Status tracks lifecycle, not maturity/correctness. Current user direction may revise approved artifacts; approval is not a veto or mandatory gate. Don't ask approval for minor transitions or every document.

When saving standalone, write the body in Markdown per the "Body Format" section of `../../shared/frontmatter-schema.md (resolved from this skill's base directory)`. Reach for embedded inline HTML only when a visual carries meaning prose can't, such as a diagram separating automated from manual steps.

## What counts

- Unit or integration tests
- CLI invocations with expected output
- Browser automation steps
- Manual steps the AI can follow and report on
- Lint and type checks when behavior depends on them

Structural assertions ("verify this function appears only once") don't count. If a regression must not recur, write a test that fails when the behavior regresses, not when lines move.

Map every source requirement to at least one executable check and name the evidence
the check will produce. Discover affected consumers, state transitions, and system
boundaries from the feature rather than applying a fixed checklist. Use realistic
interfaces and persistence where mocks could hide behavior. A broad suite command
complements these checks but does not replace them.

Versions

The database has no other skills named define-validation.

Database snapshot: 13.11.2026 · package version eacba8e83ce6 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90clean-validate
    Design a data validation pipeline — schema checks, range validation, and quality metrics. Use when asked to "validate incoming data", "add schema checks", or "define data quality metrics".
  • 90spec
    Write a detailed spec document for a task before implementation begins. Use when the user wants to define requirements, acceptance criteria, or technical design for a task.
  • 100write-acceptance-criteria
    Use when the user asks to define acceptance criteria, write a spec for a task, clarify what "done" looks like, or translate a vague goal into testable requirements. Triggers on "acceptance criteria", "definition of done", "how will we know this works", "spec for".
  • 90validation
    Pipeline phase skill for state `validation`. Use when current_state is validation.
  • 100edc-data-validation
    Generate code for EDC export validation, clinical data range checks, cross-form consistency checks, SDTM structure validation, controlled terminology verification, and define.xml generation. Use when the user asks to validate clinical trial data exports, check vital sign or lab…
  • 95ml4t-model-validation
    Multi-gate model validation from cross-validation through stress testing to deployment sign-off. Use when qualifying a model for production use.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.