explore-product-structure
Skill1 starsChanged 3 months agoMITView on GitHub
Type: skill (grounded model exploration) · Used by: perf-author · Status: STUB (P0 scaffold — not yet implemented) - Input: an environment from live/ (read-only) plus a target product area. - Output: a page/endpoint map (pages, flows, request URLs) that feeds the script-author step, alongside the raw HAR capture. This is grounded exploration — observe the real UI, do not invent endpoints.
In this repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- k6-browser-testSkill
- k6-load-testSkill
- k6-playwright-converterSkill
- k6-smoke-testSkill
- k6-test-plannerSkill
- apply-ws2-conventionsSkill
- author-resilient-playwrightSkill
- build-status-viewsSkill
- choose-k6-execution-modeSkill
- compare-coreSkill
- compare-to-baselineSkill
- corroborate-2-sourcesSkill
- curate-baselinesSkill
- doc-consistency-checkSkill
- emit-otlp-and-prometheusSkill
- estimate-token-costSkill
- file-perf-regression-jiraSkill
- func-verdictSkill
- heal-playwright-suiteSkill
- k6-profile-benchmarkSkill
- k6-profile-loadSkill
- k6-profile-soakSkill
- k6-profile-spikeSkill
- k6-profile-stressSkill
- learn-via-k6-docsSkill
- link-grafana-panelSkill
- notify-responsible-teamSkill
- open-draft-prSkill
- parse-k6-json-summarySkill
- parse-playwright-summarySkill
- perf-run-logSkill
- run-k6-scriptSkill
- run-ledgerSkill
- run-playwright-suiteSkill
- scope-reviewSkill
- scrub-har-secretsSkill
- triage-func-verdictSkill
- triage-perf-verdictSkill
- verify-k6-scriptSkill
- verify-playwright-suiteSkill
The file
Files
explore-product-structure
Map product pages with Playwright and capture a HAR of representative traffic.
Type: skill (grounded model exploration) · Used by: perf-author · Status: STUB (P0 scaffold — not yet implemented)
Prompt
Drive the product UI with Playwright to enumerate the pages/flows a load test should cover and capture a HAR of representative traffic.
- Input: an environment from
live/(read-only) plus a target product area. - Output: a page/endpoint map (pages, flows, request URLs) that feeds the script-author step, alongside the raw HAR capture.
This is grounded exploration — observe the real UI, do not invent endpoints.
Tools
Playwright MCP
Data
- Reads:
live/(read-only — environment definitions / scripts) - Writes:
reports/(HAR capture + page/endpoint map)
Notes
Activation: P4. First half is grounded model exploration; its output feeds
verify-k6-script / the script-author step. Read-only against live/ — this
skill never mutates environment definitions. Any captured HAR MUST pass through
scrub-har-secrets before it is persisted or fed to a model.
Frozen skill registry: AGENTS.md in this repo
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
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.