Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Test Report Generator · jeremylongshore | DecimalAI

testingby jeremylongshore

Test Report Generator

jeremylongshore/generating-test-reports

Source jeremylongshore/claude-code-plugins-plus-skills ↗License MIT

Generate comprehensive test reports with metrics, coverage, and visualizations.

SkillScore73Maintained

Automatic

QA & Test Engineering packtestingtest-reports

Last verified 8/30/2026

What it changes

Passed 16 of 22 test cases with the skill, and 8 of 22 without it.

Without skill36%

With skill73%

Checks it passed that the model alone missed

Includes coverage heatmaps
Recommends re-running the failed test suite
Names the Markdown summary file test-report.md

and 9 more in the full report

8 fixed8 passed either way6 still failing0 broke

Pass-rate lift: +36 pp
Tokens: +28%
Agent turns: 0%
Response time: -11%

Model gemini-3.6-flashMeasured 8/30/2026v116 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/jeremylongshore-generating-test-reports/SKILL.md https://app.decimal.ai/s/jeremylongshore-generating-test-reports/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add jeremylongshore-generating-test-reports, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/jeremylongshore-generating-test-reports/ and pins it in .decimal/skills.lock

decimalai skills add jeremylongshore-generating-test-reports

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/jeremylongshore-generating-test-reports/SKILL.md https://app.decimal.ai/s/jeremylongshore-generating-test-reports/SKILL.md

Raw file: /s/jeremylongshore-generating-test-reports/SKILL.md ↗ · machine-readable summary at /s/jeremylongshore-generating-test-reports.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

We want our test report summary rendered natively on the GitHub Actions workflow run page. What bash shell command attaches the generated Markdown summary to GitHub Actions?

What was checked, without and with the skill
Checked	Without skill	With skill
Uses cat test-report.md >> $GITHUB_STEP_SUMMARY to publish the report	Missed	Passed

case-13 · gemini-3.6-flash · 8/30/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md91 lines9 filesincludes scripts

Test Report Generator

Overview

Generate structured, human-readable test reports from raw test runner output including JUnit XML, Jest JSON, pytest results, and coverage data. Produces Markdown summaries, HTML dashboards, and CI-compatible annotations.

Prerequisites

Test results in a parseable format (JUnit XML, Jest --json, pytest --junitxml, or TAP)
Coverage data files (Istanbul coverage-summary.json, lcov.info, or coverage.xml)
Node.js or Python available for report generation scripts
Git history accessible for trend analysis across commits

Instructions

Locate all test result files using Glob patterns (**/junit.xml, **/test-results.json, **/coverage/lcov.info).
Parse each result file and extract:
- Total test count, passed, failed, skipped, and error counts.
- Execution duration per test suite and per individual test.
- Failure messages, stack traces, and assertion details.
Parse coverage data and extract:
- Line, branch, function, and statement coverage percentages.
- Per-file coverage breakdown identifying files below threshold.
- Uncovered line ranges for targeted improvement.
Compute aggregate metrics:
- Overall pass rate as a percentage.
- Total execution time and average test duration.
- Top 10 slowest tests with file paths and durations.
- Coverage delta compared to the previous commit (if git history is available).
Generate a Markdown report with sections for summary, failures, coverage, and performance.
Optionally generate an HTML report with sortable tables and coverage heatmaps.
Write CI-compatible output (GitHub Actions job summary, GitLab report artifacts, or Slack webhook payload).

Output

test-report.md -- Markdown summary with pass/fail table, coverage stats, and failure details
test-report.html -- Self-contained HTML report (optional)
Coverage summary table with per-file breakdown and delta from baseline
Slowest tests list ranked by execution time
CI annotation comments on failed test lines (GitHub Actions ::error format)

Track record

Benchmark

16 / 22

test cases passed, vs 8 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

jeremylongshore / claude-code-plugins-plus-skills

skills/.curated/generating-test-reports/SKILL.md

View on GitHub ↗

License MITImported 8/25/2026Version v1Bundled 8 files · scripts

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

foryourhealth111-pixel/generating-test-reportsGenerate structured test reports with pass/fail rollups, coverage summaries, and test artifacts. Use when the user is asking for test-result packaging or delivery, not for root-cause debugging or feature implementation.Close match-100 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Test Report Generator

Overview

Prerequisites

Instructions

Output

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills