Ready to supercharge your AI agents?

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

Evidence Scout · yogsoth-ai | DecimalAI

researchby yogsoth-ai

Evidence Scout

yogsoth-ai/evidence-scout

Source yogsoth-ai/de-anthropocentric-research-engine ↗License Apache-2.0

Searches for external evidence supporting or opposing specific claims. Returns structured evidence with source assessment and relevance scoring.

SkillScore88Maintained

Automatic

Research pack

Last verified 8/22/2026

What it changes

Passed 20 of 23 test cases with the skill, and 11 of 23 without it.

Without skill48%

With skill88%

Checks it passed that the model alone missed

The response sets the search budget to 5 searches.
The response sets the search budget to 10 searches.
The response specifies a search budget of 2 searches.

and 9 more in the full report

10 fixed12 passed either way3 still failing0 broke

Pass-rate lift: +40 pp
Tokens: -23%
Agent turns: 0%
Response time: -48%

Model gemini-3.6-flashMeasured 8/22/2026v122 of 25 cases passed with skill · 23 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/yogsoth-ai-evidence-scout/SKILL.md https://app.decimal.ai/s/yogsoth-ai-evidence-scout/SKILL.md

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

decimalai skills add yogsoth-ai-evidence-scout

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

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

Raw file: /s/yogsoth-ai-evidence-scout/SKILL.md ↗ · machine-readable summary at /s/yogsoth-ai-evidence-scout.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

After running an evidence retrieval pass across five distinct economic assertions regarding direct air carbon capture, what required output section tracks which assertions were backed versus unevidenced?

What was checked, without and with the skill
Checked	Without skill	With skill
The response identifies coverage as the component tracking backed versus unevidenced claims.	Missed	Passed

case-13 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md41 linessingle file

Evidence Scout

Searches for external evidence supporting or opposing claims.

Execution

Subagent — spawned via subagent-spawning/spawn-agent.

Why Subagent

Evidence gathering requires web search and paper lookup in dedicated context. Isolated execution prevents search results from biasing ongoing debate reasoning.

Input

claims_to_evidence: Specific claims needing external evidence
stance: Whether to search for supporting or opposing evidence (pro/con)
search_budget: Number of searches allowed (2/5/10 based on campaign budget)

Output

evidence_items: List of evidence found (source, content, relevance score)
evidence_quality: Assessment of each source's reliability
coverage: Which claims have evidence vs. which remain unevidenced

Budget

One unit = one evidence gathering pass (multiple searches within budget).

Available SOPs

Optional, no fixed order; the final leaf is always a sop.

SOP	When to use
spawn-agent	Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent.
stress-test-paper-overview	Paper landscape scan returning abstracts and metadata. Import of literature-engine/paper-overview skill. Abstracts only — no conclusions from abstracts.
stress-test-web-search	Quick web scanning for landscape understanding. Import of web-browsing/web-search skill. Snippets only — no conclusions from snippets alone.

Track record

Benchmark

20 / 23

test cases passed, vs 11 / 23 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

yogsoth-ai / de-anthropocentric-research-engine

skills/evidence-scout/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

Evidence Scout

Execution

Why Subagent

Input

Output

Budget

Available SOPs

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills