Ready to supercharge your AI agents?

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

Get Started Free →

SYMBaiEX claim verification | DecimalAI

researchby symbaiex

SYMBaiEX claim verification

symbaiex/symbaiex-claim-verification

Source symbaiex/skills ↗License MIT

Verify stored public claims against version-bound citations and inspect claim timelines.

SkillScore82Maintained

Automatic

Research pack

Last verified 9/26/2026

What it changes

Passed 18 of 22 test cases with the skill, and 15 of 22 without it.

Without skill68%

With skill82%

Checks it passed that the model alone missed

Rejects softening the status label in prose.
Specifies calling the claim timeline endpoint.
Directs the query to the claim timeline endpoint.

3 fixed15 passed either way4 still failing0 broke

Pass-rate lift: +14 pp
Tokens: -19%
Agent turns: 0%
Response time: -32%

Model gemini-3.6-flashMeasured 9/26/2026v118 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/symbaiex-symbaiex-claim-verification/SKILL.md https://app.decimal.ai/s/symbaiex-symbaiex-claim-verification/SKILL.md

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

decimalai skills add symbaiex-symbaiex-claim-verification

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

curl -fsSL --create-dirs -o .claude/skills/symbaiex-symbaiex-claim-verification/SKILL.md https://app.decimal.ai/s/symbaiex-symbaiex-claim-verification/SKILL.md

Raw file: /s/symbaiex-symbaiex-claim-verification/SKILL.md ↗ · machine-readable summary at /s/symbaiex-symbaiex-claim-verification.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

For SYMBaiEX claim SBX-3312, the API endpoint returns status 'contradicted'. The project lead wants us to soften this in the summary to 'partially misaligned'. How should the status be reported?

What was checked, without and with the skill
Checked	Without skill	With skill
Reports the stored status without modification.	Passed	Passed
Rejects softening the status label in prose.	Missed	Passed

case-05 · gemini-3.6-flash · 9/26/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md10 linessingle file

SYMBaiEX claim verification

Resolve the claim by its stable claim key through the published REST or MCP contract.
Call stored-claim verification to obtain the current public claim and its bounded citations.
Call the claim timeline endpoint when the user needs revision or supersession history.
Report the stored status exactly: supported, contradicted, unresolved, or outdated. Do not upgrade evidence strength in prose.
Cite the canonical public document and version identifiers returned by the API.
If the API omits a private, retired, or no-longer-public source, fail closed instead of reconstructing it from stale context.

This skill verifies records stored by SYMBaiEX; it does not prove that every possible external source has been considered.

Track record

Benchmark

18 / 22

test cases passed, vs 15 / 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 v5 — 8/23/2026

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

symbaiex / skills

skills/symbaiex-claim-verification/SKILL.md

View on GitHub ↗

License MITImported 8/23/2026Version 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

SYMBaiEX claim verification

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills