jovd83jovd83/playwright-skill/analysis/SKILL.md

playwright-analysis-requirements

Skill1 starsChanged 35 days agoMITView on GitHub

Requirements-analysis skill for Playwright planning and implementation. Use when the agent needs to extract testable behaviors, acceptance criteria, risks, dependencies, or open questions from tickets, specs, markdown docs, or other requirement sources before writing tests or coverage plans.

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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

Distinctive:
Use this skill to turn raw product or engineering artifacts into a trustworthy testing baseline.
line 19
Distinctive:
Use the best available sources in this order:
line 23
Distinctive:
Do not keep searching indefinitely once you have enough evidence to form a reliable baseline.
line 29
Distinctive:
When tabular output helps, use:
line 41
Distinctive:
Call out missing or contradictory evidence explicitly instead of hiding it inside the summary.
line 51
Distinctive:
If the user explicitly asked for a baseline only, stop after the analysis.
line 56
Distinctive:
If the requirements are clear enough and the user asked for downstream planning in the same request, continue while marking assumptions.
line 57
Very specific:
Use the output of this skill as the input to dispatcher intent plan_playwright_coverage when planning is needed.
line 61
Very specific:
If dispatcher routing is unavailable, use ../coverage_plan/generation/SKILL.md or move directly into implementation work when the scope is …
line 63

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Playwright Requirements Analysis

Use this skill to turn raw product or engineering artifacts into a trustworthy testing baseline.

Inputs

Use the best available sources in this order:

user-provided tickets, specs, or links,
repository-local docs such as docs/, markdown files, issue exports, or feature notes,
adjacent automation or product artifacts that clarify behavior.

Do not keep searching indefinitely once you have enough evidence to form a reliable baseline.

Output Contract

Produce a concise requirements baseline with these sections:

Confirmed behaviors
Inferred behaviors
Risks and edge cases
Open questions or missing evidence
Source evidence

When tabular output helps, use:

Requirement ID

Behavior

Evidence

Confidence

Notes

Rules

Separate confirmed facts from reasonable inference.
Normalize vague prose into testable behaviors.
Capture edge cases, authorization rules, data constraints, and failure modes when the source implies them.
Call out missing or contradictory evidence explicitly instead of hiding it inside the summary.

When to Pause

Pause for confirmation when the requirements are ambiguous enough to change the downstream plan materially.
If the user explicitly asked for a baseline only, stop after the analysis.
If the requirements are clear enough and the user asked for downstream planning in the same request, continue while marking assumptions.

Handoff

Use the output of this skill as the input to dispatcher intent plan_playwright_coverage when planning is needed.

If dispatcher routing is unavailable, use ../coverage_plan/generation/SKILL.md or move directly into implementation work when the scope is already narrow.

Download now (ZIP)

In this repository7 other files it gives its agents.
- playwright-ciSkill
- playwright-coreSkill
- playwright-migrationSkill
- playwright-orchestratorSkill
- playwright-cliSkill
- playwright-pomSkill
- playwright-skillSkill

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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