Measures benchmark performance and output reports in JSON and markdown formats.

Install

mkdir -p .claude/skills/gtkb-benchmarks && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13810" && unzip -o skill.zip -d .claude/skills/gtkb-benchmarks && rm skill.zip

Installs to .claude/skills/gtkb-benchmarks

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Run GT-KB read-only measurement benchmarks. Outputs JSON plus markdown summary.
79 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Execute one or all GT-KB read-only measurement benchmarks
  • Print a summary of a previously emitted benchmark run
  • Compare two benchmark runs by idempotency_key and benchmark value
  • Generate structured observations with headline scalars and per-dimension breakdowns
  • Produce both JSON and markdown summary artifacts for each run

How it works

The skill executes specified read-only benchmarks, computes structured observations, and then writes the results to JSON and markdown files. It can also retrieve or compare these results.

Inputs & outputs

You give it
A command to run, report, or compare benchmarks, optionally with benchmark IDs or run IDs
You get back
run.json with full structured payload and summary.md with a human-readable table

When to use gtkb-benchmarks

  • Running performance benchmarks
  • Comparing benchmark runs
  • Reporting assertion quality

About this skill

<!-- GTKB-ANTIGRAVITY-SKILL-ADAPTER Generated: true Generated by: scripts/generate_antigravity_skill_adapters.py Canonical source: .claude/skills/gtkb-benchmarks/SKILL.md Canonical source sha256: 95940f9fecb54eee364558ad2c15b6f34395a1e2a0d8d6e760b90e80c62926be Generated at: 2026-06-11T18:34:14Z Do not edit this adapter directly. Edit the canonical source and regenerate. GTKB-ANTIGRAVITY-SKILL-ADAPTER -->

GT-KB Benchmark Suite

Read-only measurement benchmarks for the GT-KB platform. Each benchmark computes a structured observation with a headline scalar plus per-dimension breakdown, and emits both JSON and markdown summary artifacts.

Operationalizes SPEC-1662 (GOV-18 Assertion Quality Standard) and GOV-ARTIFACT-ORIENTED-GOVERNANCE-001 per Self-Diagnostic Leak Closure Slice 2.

Benchmarks

IDQuestion Answered
linkage_heatmapWhat fraction of cross-artifact references survive across SPEC, WI, ADR or DCL or GOV, DELIB, BRIDGE pairs?
recall_coverageWhat fraction of recent mutations cite prior-state evidence in change_reason?
tool_identificationWhat fraction of recent insertions carry a structured attribution marker?
deliberation_recallWhat is the recall at 3 of the semantic index over recent owner-decision deliberations?
advisory_latencyWhat is the median wall-clock latency from advisory filing to first Prime acknowledgement?
assertion_signal_noiseWhat fraction of categorized assertions land outside chronic_noise (signal-bearing)?

Subcommands

run

Execute one or all benchmarks. Defaults to a one-year window ending now.

python -m scripts.benchmarks.cli run --all
python -m scripts.benchmarks.cli run --benchmark assertion_signal_noise

report

Print a previously emitted run summary.

python -m scripts.benchmarks.cli report --run-id 20260514-040000

compare

Diff two runs by idempotency_key and benchmark value.

python -m scripts.benchmarks.cli compare --baseline RUN_A --candidate RUN_B

Output Contract

Each run writes two files under the runs directory:

  • run.json -- full structured payload (run_id, idempotency_key, results).
  • summary.md -- human-readable markdown summary table.

The idempotency_key is a SHA-256 hash of the window bounds, benchmark IDs, and source commit. Identical inputs over identical commits produce identical keys.

Governing Artifacts

  • SPEC-1662 (GOV-18 Assertion Quality Standard)
  • GOV-ARTIFACT-ORIENTED-GOVERNANCE-001
  • GOV-STANDING-BACKLOG-001
  • ADR-DA-READ-SURFACE-PLACEMENT-001
  • DELIB-S312-DETERMINISTIC-SERVICES-PRINCIPLE

When not to use it

  • When needing to modify GT-KB data, as this skill is for read-only measurements
  • When requiring benchmarks beyond the defined set of six GT-KB measurements

Limitations

  • Only performs read-only measurement benchmarks
  • Limited to the predefined set of benchmarks (e.g., linkage_heatmap, recall_coverage)
  • Defaults to a one-year window ending now for benchmark execution

How it compares

This skill automates the execution, reporting, and comparison of specific GT-KB benchmarks, unlike manually inspecting individual data points or writing custom scripts for each analysis.

Compared to similar skills

gtkb-benchmarks side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
gtkb-benchmarks (this skill)02moNo flagsIntermediate
model-usage52moReviewBeginner
analytics-tracking76moNo flagsIntermediate
splunk-analysis55moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

model-usage

openclaw

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

548

analytics-tracking

davila7

When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," or "tracking plan." For A/B test measurement, see ab-test-setup.

736

splunk-analysis

incidentfox

Splunk log analysis using SPL (Search Processing Language). Use when investigating issues via Splunk logs, saved searches, or alerts.

536

tracking-crypto-derivatives

jeremylongshore

Track cryptocurrency futures, options, and perpetual swaps with funding rates, open interest, liquidations, and comprehensive derivatives market analysis. Use when monitoring derivatives markets, analyzing funding rates, tracking open interest, finding liquidation levels, or researching options flow. Trigger with phrases like "funding rate", "open interest", "perpetual swap", "futures basis", "liquidation levels", "options flow", "put call ratio", "derivatives analysis", or "BTC perps".

437

weights-and-biases

davila7

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

325

perf-analyzer

ComposioHQ

Use when synthesizing perf findings into evidence-backed recommendations and decisions.

324

Search skills

Search the agent skills registry