How do I install the Tosca Analyzing Execution History skill?

Run npx skillmds@latest add tricentis/tosca-analyzing-execution-history-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Tosca Analyzing Execution History safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Tosca Analyzing Execution History?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Tosca Analyzing Execution History free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under Apache-2.

Who published Tosca Analyzing Execution History?

Tricentis (@tricentis) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Tosca Analyzing Execution History by tricentis

Name: Tosca Analyzing Execution History
Author: Tricentis

Tosca Analyzing Execution History

Analyzes Tosca Cloud execution trends over multiple playlist runs — flakiness, recurring failures, and pass-rate changes. Use when the user asks about trends, flaky tests, historical failures, or whether a failure is new or recurring across runs. Read-only. Does NOT cover single-run diagnosis (use tosca-analyzing-execution-results).

Tricentis Updated Sep 21, 2026

File contents

Analyze Tosca Cloud execution history

Compare multiple runs of a playlist to detect flakiness, regressions, and recurring error signatures. Read-only.

Prerequisite: tosca-cloud-basics. Wire names: tosca_{domain}_{action}.

Session checklist

Analyze Cloud execution history:
- [ ] Resolve playlist
- [ ] getRecentRuns (limit 20+)
- [ ] Classify Passed/Failed trend
- [ ] getFailedTestSteps for failed runs only
- [ ] Compare signatures across runs (flaky vs recurring)
- [ ] Report with confidence; hand off if fix needed

Fast path

Resolve playlist — tosca_playlist_searchByName.
Fetch run history — tosca_playlist_getRecentRuns(playlistId, limit: 20) (or more if needed).
Classify runs — count Passed/Failed over window; note state transitions.
Deep dive failures — tosca_playlist_getFailedTestSteps for failed runs only; compare signatures across runs.
Optional comparison — tosca_execution_getRecentRunLogs for log-level diff.
Report — trend summary, flaky tests, new vs recurring failures with confidence.

Flakiness signals

Same test passes on run N, fails on N+1 with same environment
Failure signature changes but same test case ID
Failures correlate with run time / load (timing category)

See references/trend-and-anomaly.md.

Hand off

Single latest run diagnosis → tosca-analyzing-execution-results
Apply fix → tosca-remediating-from-results

Frequently asked questions