Ready to supercharge your AI agents?

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

Get Started Free →

Evidence Standards for Neo4j Subagents · majiayu000 | DecimalAI

agent toolingby majiayu000

Evidence Standards for Neo4j Subagents

majiayu000/evidence-standards

Source majiayu000/claude-skill-registry ↗License MIT

Evidence citation and domain scope standards for Neo4j subagents. Prevents hallucination and ensures audit trail.

SkillScore78Maintained

Automatic

AI Engineer pack

Last verified 8/19/2026

What it changes

Passed 16 of 21 test cases with the skill, and 9 of 21 without it.

Without skill43%

With skill78%

Checks it passed that the model alone missed

The response includes a ## Coverage section header.
The response contains a ## Coverage section header.
The response formats results under a ## Results header.

and 7 more in the full report

8 fixed10 passed either way5 still failing0 broke

Pass-rate lift: +35 pp
Tokens: +35%
Agent turns: 0%
Response time: -25%

Model gemini-3.6-flashMeasured 8/19/2026v118 of 23 cases passed with skill · 21 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/majiayu000-evidence-standards/SKILL.md https://app.decimal.ai/s/majiayu000-evidence-standards/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-evidence-standards, 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/majiayu000-evidence-standards/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-evidence-standards

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

curl -fsSL --create-dirs -o .claude/skills/majiayu000-evidence-standards/SKILL.md https://app.decimal.ai/s/majiayu000-evidence-standards/SKILL.md

Raw file: /s/majiayu000-evidence-standards/SKILL.md ↗ · machine-readable summary at /s/majiayu000-evidence-standards.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

As the neo4j-news subagent, search for news headlines about PLCE on September 11, 2024. Only 1 headline is found in the initial single-day query.

What was checked, without and with the skill
Checked	Without skill	With skill
The response states that news search was expanded beyond the initial query range.	Missed	Passed

case-09 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md100 linessingle file

Evidence Standards for Neo4j Subagents

Domain Scope

Each agent queries ONLY its designated node types:

Agent	Allowed Nodes	NOT Allowed
neo4j-report	Report, ExtractedSectionContent, ExhibitContent	News, Transcript, Fact
neo4j-news	News	Report, Transcript, Fact
neo4j-transcript	Transcript, QAExchange, PreparedRemark	Report, News, Fact
neo4j-xbrl	Fact, Concept, Dimension, Member	Report, News, Transcript
neo4j-entity	Company, Sector, Industry, Dividend, Split	Report, News, Fact

If asked for data outside your domain: Respond "This requires [correct-agent] agent" and do not query.

Evidence Citation Format

All returned data MUST include source verification.

Template: {metric}: {value} (Source: {NodeType}:{identifier}, {date})

Examples by Domain

Report:

Actual EPS: $2.03 (Source: Report:0001104659-24-098778/EX-99.1, 2024-09-11)
Filing type: 8-K (Source: Report:0001104659-24-098778, form_type)
Daily return: +84.14% (Source: Report:0001104659-24-098778, pf.daily_stock)

News:

Headline: "PLCE beats estimates by 127%" (Source: News:benzinga-456789, 2024-09-11)
Consensus EPS: $-0.19 (Source: News:streetinsider-123, 2024-09-10)

Transcript:

Track record

Benchmark

16 / 21

test cases passed, vs 9 / 21 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

majiayu000 / claude-skill-registry

skills/agent/evidence-standards-faisalanjum-eventtrader/SKILL.md

View on GitHub ↗

License MITImported 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

Evidence Standards for Neo4j Subagents

Domain Scope

Evidence Citation Format

Examples by Domain

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills