Ready to supercharge your AI agents?

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

Quality Report Generate Skill · aiskillstore | DecimalAI

testingby aiskillstore

Quality Report Generate Skill

aiskillstore/quality-report-generate

Source aiskillstore/marketplace ↗License Not recorded

Generate comprehensive quality report with metrics and verification. Produces final CHAPTER_XX_VERIFICATION.md and quality_metrics.json for deployment approval.

SkillScore86Maintained

Automatic

QA & Test Engineering pack

Last verified 8/22/2026

What it changes

Passed 17 of 20 test cases with the skill, and 5 of 20 without it.

Without skill23%

With skill86%

Checks it passed that the model alone missed

Clamps the final score to a minimum value of 0.
Executes the script from the Calypso/tools directory.
Names the markdown report CHAPTER_07_VERIFICATION.md.

and 16 more in the full report

14 fixed5 passed either way3 still failing0 broke

Pass-rate lift: +64 pp
Tokens: +179%
Agent turns: 0%
Response time: -25%

Model gemini-3.6-flashMeasured 8/22/2026v119 of 22 cases passed with skill · 20 comparable

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/aiskillstore-quality-report-generate/SKILL.md https://app.decimal.ai/s/aiskillstore-quality-report-generate/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add aiskillstore-quality-report-generate, 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/aiskillstore-quality-report-generate/ and pins it in .decimal/skills.lock

decimalai skills add aiskillstore-quality-report-generate

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

curl -fsSL --create-dirs -o .claude/skills/aiskillstore-quality-report-generate/SKILL.md https://app.decimal.ai/s/aiskillstore-quality-report-generate/SKILL.md

Raw file: /s/aiskillstore-quality-report-generate/SKILL.md ↗ · machine-readable summary at /s/aiskillstore-quality-report-generate.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

We are writing the verification report for Chapter 07. Should the markdown file be named `verification_report_ch07.md` or `summary_ch07.md` inside `output/chapter_07/chapter_artifacts/`?

What was checked, without and with the skill
Checked	Without skill	With skill
Names the markdown report CHAPTER_07_VERIFICATION.md.	Missed	Passed

case-12 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md508 linessingle file

Quality Report Generate Skill

Purpose

This skill generates the final quality report documenting everything about a chapter's generation and validation. The report:

Aggregates all validation results from previous gates
Calculates quality metrics (content size, structure complexity, accuracy)
Generates human-readable markdown report for review
Creates machine-readable JSON metrics for tracking and CI/CD
Provides deployment decision (pass/fail/requires-review)

This is the final skill before validation gates, producing the evidence needed to approve or reject a chapter for deployment.

What to Do

Collect all validation artifacts
- Load validation_structure.json (Gate 1 results)
- Load validation_semantic.json (Gate 2 results)
- Load consolidation_log.json (consolidation data)
- Load final chapter_XX.html file
Extract metadata from chapter
- Parse HTML to extract structure
- Count content elements (headings, paragraphs, lists)
- Calculate word count and content size
- Verify CSS class usage
Calculate quality metrics
- Overall validation score (0-100)
- Structural compliance percentage
- Semantic compliance percentage
- Content completeness estimate
- Accuracy score (if reference data available)
Generate markdown report
- Create human-readable verification report
- Include summary status (✅ PASS / ⚠️ REVIEW / ❌ FAIL)
- Document all validation results
- List findings and recommendations

Track record

Benchmark

17 / 20

test cases passed, vs 5 / 20 without

Adoption

Users: 1
Times used: 17

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

aiskillstore / marketplace

skills/abejitsu/quality-report-generate/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

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

Quality Report Generate Skill

Purpose

What to Do

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills