Source-backed research brief

---
name: source-backed-research-brief
description: Build an evidence table and a concise brief that preserves source conflicts and unknowns.
---

# Source-backed research brief

Use this skill when a user wants a research brief grounded in supplied documents or retrieved sources, especially when claims conflict. It does not require browsing; use the provided corpus unless the user requests or the host requires further verification.

## Inputs
Identify the research question, intended audience, source boundaries, and relevant date. Assign each source a stable identifier and retain its title, date, locator, and provenance. When the materials are synthetic, label both the source inventory and resulting brief as synthetic. Do not convert invented examples into claims about real products.

## Workflow
Break the question into claims that can be checked separately. Build an evidence table with claim, supporting source and locator, opposing evidence, scope, and confidence. Prefer direct statements over summaries for what a source actually says. Publication recency alone does not establish authority or override an earlier source with a different scope.

For conflicts, first compare dates, populations, versions, and definitions. If these explain the difference, describe the scope distinction with citations. Otherwise retain both values and mark the claim unresolved. Do not average conflicting limits or select a convenient figure. Separate what a source states from what you infer, and never invent missing evidence, quotations, or URLs.

## Output contract
Deliver a short answer, a claim-level evidence table, conflicts and unknowns, and a source inventory. Attach a source identifier and locator to every externally derived factual claim, including claims in the short answer. Clearly label recommendations and inferences. If the corpus cannot answer part of the question, name the missing evidence and the next verification step. Before delivery, follow each citation back to its input and verify that the cited passage supports the complete claim. Keep external publishing and account changes outside this analysis unless explicitly requested.

# Synthetic research corpus
Question: What can we say about the fictional Cedar trial? No external lookup.
[S1] Trial guide, 2026-09-01, paragraph 1: Cedar trials last 14 days and allow up to 5 seats. Exports are CSV only.
[S2] Help note, 2026-09-03, paragraph 2: All Cedar trials have a 10-seat limit. Trial length is 14 days.
[S3] Internal test memo, 2026-09-04, paragraph 3: One trial account successfully exported CSV. We did not test other export formats or seat limits.
All three excerpts are invented for this sample; neither S1 nor S2 specifies a version.

# Synthetic research brief: Cedar trial
The supplied excerpts agree on a 14-day trial [S1 ¶1; S2 ¶2]. The seat limit is unresolved: 5 versus 10 [S1 ¶1; S2 ¶2]. CSV export is documented and was observed on one account [S1 ¶1; S3 ¶3].

| Claim | Supporting evidence | Opposing evidence / scope | Assessment |
| --- | --- | --- | --- |
| Trial lasts 14 days | S1 ¶1; S2 ¶2 | No contradiction in the corpus | High agreement within this synthetic corpus |
| Trial allows 5 seats | S1 ¶1 | S2 ¶2 states 10 for all trials; no version specified | Unresolved |
| Trial allows 10 seats | S2 ¶2 | S1 ¶1 states 5; no version specified | Unresolved |
| CSV export works | S1 ¶1; S3 ¶3 | S3 tested one account only | Documented; one-account observation |
| CSV is the only export format | S1 ¶1 | S3 ¶3 did not test other formats; it cannot confirm exclusivity | Single-source assertion |

The dates alone do not resolve the seat conflict. Recommendation: obtain an authoritative version-specific trial limit before communicating one number. To verify export exclusivity, obtain a current complete format list or a scoped test covering other formats. These are proposed next steps, not completed research.

## Source inventory (all synthetic)
- S1: Trial guide, 2026-09-01, paragraph 1, supplied excerpt.
- S2: Help note, 2026-09-03, paragraph 2, supplied excerpt.
- S3: Internal test memo, 2026-09-04, paragraph 3, supplied excerpt.

Check: all five claim rows cite their excerpts. No seat average, real-product assertion, or invented URL is used.