- Home
- Skills
- Research & Analysis
- Research evidence and contradiction ledger
Research evidence and contradiction ledger
For research analysts: a claim-level evidence ledger and unresolved contradictions.
$12
Works with the AI Agents you already use
Research evidence and contradiction ledger
Example session with this skill installed
Use the skill to produce a claim-level evidence ledger and unresolved contradictions. Input S1: Source A: 2025 survey of 100 shops, 30 percent adoption. Source B: 2026 survey of 20 large chains, 70 percent adoption.
- Read your context and instructions
- Compiled the research evidence
Synthetic test example. Recorded AI smoke-test response. No real service changes were executed.
S1 does not establish comparable adoption growth.
Evidence ledger
- A: "2025 survey of 100 shops, 30 percent adoption." Supported as a reported survey result; shop population, definitions and sampling limitations are unknown.
- B: "2026 survey of 20 large chains, 70 percent adoption." Supported as a reported result for large chains; definitions and sampling are unknown.
The difference is 70 - 30 = 40 percentage points, but treating it as growth is unsupported because both year and population change. The two results can coexist; no direct contradiction is established. Averaging would hide incompatible units and populations.
Missing inputs: decision question, adoption definitions, survey methods, response rates and population overlap.
Next discriminating evidence: the same measure for a comparable shop or chain population in both years.
Acceptance check: retain year, sample size and population next to each figure; a trend conclusion needs comparable evidence first. No surveys were independently verified.
Connects securely to your tools. The creator never sees your data.
About this skill
Use this skill when you have a question and supplied source excerpts with dates and need a claim-level evidence ledger and unresolved contradictions.
The workflow:
- Define the decision and break it into answerable claims.
- Record source date, quoted support, population and limitations per claim.
- Keep conflicting measures side by side; do not average incompatible definitions.
- Write a conclusion only as strong as the evidence and list the next discriminating source.
You receive the work product with input-linked findings, visible unknowns and concrete verification checks. Work from pasted or redacted text. This skill does not execute changes, send messages or access service accounts.
Original AI-assisted content. A synthetic worked example is included. Use through your Agensi-connected agent. No extra paid API or runtime is required for this workflow. Delivery is through the Agensi agent connection. No sales, ranking or compliance outcome is promised.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 8 days ago
Permissions
No special permissions declared or detected