Ready to supercharge your AI agents?

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

Get Started Free →

Guardrail Scorecard Skill · gtmagents | DecimalAI

marketingby gtmagents

Guardrail Scorecard Skill

gtmagents/guardrail-scorecard

Source gtmagents/gtm-agents ↗License Apache-2.0

Framework for defining, monitoring, and enforcing guardrail metrics across experiments.

SkillScore59Maintained

Automatic

Product Management pack

Last verified 8/23/2026

What it changes

Passed 13 of 22 test cases with the skill, and 5 of 22 without it.

Without skill23%

With skill59%

Checks it passed that the model alone missed

Includes explicit warning and critical boundaries for each listed metric
Assigns a metric owner and data refresh frequency for support channel tracking
Defines strict decision timelines and response deadlines for escalation actions

and 12 more in the full report

10 fixed3 passed either way7 still failing2 broke

Pass-rate lift: +36 pp
Tokens: +5%
Agent turns: 0%
Response time: -11%

Model gemini-3.6-flashMeasured 8/23/2026v113 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-guardrail-scorecard/SKILL.md https://app.decimal.ai/s/gtmagents-guardrail-scorecard/SKILL.md

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

decimalai skills add gtmagents-guardrail-scorecard

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

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

Raw file: /s/gtmagents-guardrail-scorecard/SKILL.md ↗ · machine-readable summary at /s/gtmagents-guardrail-scorecard.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 10

Prompt

We are getting ready to run a new pricing test across Europe and need to establish our safety boundaries before launching. Can you set up a comprehensive guardrail scorecard for us? Make sure it outlines the metrics we need to track, assigns ownership and update frequencies, defines warning versus critical breach boundaries across regions, and details the escalation pathway if something goes wrong.

What was checked, without and with the skill
Checked	Without skill	With skill
Specifies conditions and required approval hierarchy under which guardrail thresholds may be overridden	Missed	Passed
Includes a retrospective protocol for logging breaches, mitigations, and guardrail rule updates for future tests	Missed	Passed

case-01 · 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

Guardrail Scorecard Skill

When to Use

Setting non-negotiable metrics (stability, churn, latency, compliance) before launching tests.
Monitoring live experiments to ensure guardrails stay within thresholds.
Reporting guardrail status in launch packets and post-test readouts.

Framework

Metric Inventory – list guardrail metrics, owners, data sources, refresh cadence.
Threshold Matrix – define warning vs critical bands per metric / persona / region.
Alerting & Escalation – map notification channels, DRI, and decision timelines.
Exception Handling – document when guardrail overrides are acceptable and required approvals.
Retrospective Loop – log breaches, mitigations, and rule updates for future tests.

Templates

Guardrail register (metric, threshold, owner, alert channel).
Live monitoring dashboard layout.
Exception memo structure for approvals.

Tips

Tie guardrails to downstream systems (billing, support) to catch second-order impacts.
Keep thresholds dynamic for seasonality but document logic.
Pair with launch-experiment to ensure readiness before flipping flags.

Track record

Benchmark

13 / 22

test cases passed, vs 5 / 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/growth-experiments/skills/guardrail-scorecard/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 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

Guardrail Scorecard Skill

When to Use

Framework

Templates

Tips

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills