Ready to supercharge your AI agents?

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

Get Started Free →

Validation Rulebook Skill · gtmagents | DecimalAI

databy gtmagents

Validation Rulebook Skill

gtmagents/validation-rulebook

Source gtmagents/gtm-agents ↗License Apache-2.0

Use to define validation, freshness, and compliance checks for enriched data.

SkillScore86Maintained

Automatic

Sales & GTM pack

Last verified 8/23/2026

What it changes

Passed 19 of 22 test cases with the skill, and 12 of 22 without it.

Without skill55%

With skill86%

Checks it passed that the model alone missed

The response includes data residency tagging for incoming records.
The response includes approval logging mechanisms for auditability.
The response includes pre-sync and post-sync verification checkpoints.

and 10 more in the full report

8 fixed11 passed either way2 still failing1 broke

Pass-rate lift: +32 pp
Tokens: +4%
Agent turns: 0%
Response time: +0%

Model gemini-3.6-flashMeasured 8/23/2026v119 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/gtmagents-validation-rulebook/SKILL.md https://app.decimal.ai/s/gtmagents-validation-rulebook/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add gtmagents-validation-rulebook, 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/gtmagents-validation-rulebook/ and pins it in .decimal/skills.lock

decimalai skills add gtmagents-validation-rulebook

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

curl -fsSL --create-dirs -o .claude/skills/gtmagents-validation-rulebook/SKILL.md https://app.decimal.ai/s/gtmagents-validation-rulebook/SKILL.md

Raw file: /s/gtmagents-validation-rulebook/SKILL.md ↗ · machine-readable summary at /s/gtmagents-validation-rulebook.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

Our third-party intent data vendor just updated their API schema, and we need to audit the incoming dataset before unblocking the sync. Draft a structured QA runbook detailing pre-sync and post-sync verification steps, exception handling processes for failed records, and a compliance review packet.

What was checked, without and with the skill
Checked	Without skill	With skill
The response defines confidence scoring criteria that weight provider source, validation method, and history.	Missed	Passed
The response specifies freshness SLA thresholds categorized by signal type.	Missed	Passed
The response provides a field-level rule catalog detailing required fields, regex patterns, allowed values, and dependencies.	Missed	Passed

case-02 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md25 linessingle file

Validation Rulebook Skill

When to Use

Running QA before syncing enrichment outputs to GTM systems.
Auditing providers after schema changes or outages.
Documenting compliance-ready validation procedures.

Framework

Rule Catalog – list required fields, regex patterns, allowed values, and dependencies.
Freshness Thresholds – define time-based SLAs per signal type.
Confidence Scoring – set weighting for provider, validation method, and history.
Exception Handling – create workflows for quarantining, reprocessing, or escalation.
Compliance Hooks – log approvals, data residency tags, and retention policies.

Templates

Rule table (field, check, threshold, severity, owner).
QA runbook with pre/post sync steps.
Compliance audit packet ready for legal/infosec reviews.

Tips

Automate as many rules as possible but keep manual sampling for high-impact signals.
Version rules alongside taxonomy updates.
Pair with data-quality-steward outputs for sign-off history.

Track record

Benchmark

19 / 22

test cases passed, vs 12 / 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 — 8/3/2026

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

gtmagents / gtm-agents

plugins/data-signal-enrichment/skills/validation-rulebook/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

Other skills for the same job

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

gtmagents/signal-taxonomyUse to define schemas, topic tags, and lineage metadata for enriched signals.Close match+14 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

Validation Rulebook Skill

When to Use

Framework

Templates

Tips

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills