--- title: "Build Evidence Map: review, setup & limitations · Undominated.ai" canonical: https://undominated.ai/skills/github-build-evidence-map/ description: "Builds a structured map of claims, evidence and unresolved gaps, with a local validator for the map’s structure." --- # Build Evidence Map: review, setup & limitations · Undominated.ai > Builds a structured map of claims, evidence and unresolved gaps, with a local validator for the map’s structure. [← Explore all skills](/skills/) RESEARCH AND EVIDENCE / GitHub community # Build Evidence Map Builds a structured map of claims, evidence and unresolved gaps, with a local validator for the map’s structure. See setup guidance ↓Original source ↗ SOURCE REVIEW Reviewed 2026-09-22 Evidence 10 linked sources Publisher GitHub community Licence MIT ↗ Revision a19b3101cc79 Read what was—and wasn’t—checked ↓ “Build an auditable evidence map for a contested technical choice, research synthesis, proposal review, or consequential decision. Use when Copilot must preserve” GitHub community · upstream description ↗ Our analysis follows below. 01 / THE REASONING ## Why this made the selection. - Preserves supporting, contradicting, qualifying and missing evidence as separate relationships instead of flattening a contested choice into confident prose. - Requires identifiable source regions and gives the map a structural validator and reproducible receipt hashes. ### A good fit for - Comparing competing architectural or product proposals - Producing a reviewable research handoff with explicit counterevidence and unknowns ### Weigh up before choosing - The bundled validator checks structure and declared excerpts; it does not establish that a source is true or that the excerpt supports the claim. - Optional live-source verification uses a separate Doubt CLI and needs its own installation, review and network permission. It is not part of the verified local validator behavior. - Evidence maps can include private source excerpts. Select appropriate material before writing or sharing a receipt. - The prose quality gates are broader than the structural checks: a successful receipt does not establish that counterevidence was sought or that every judgment rule was satisfied. 02 / THE REVIEW RECORD ## What we actually inspected. Source review has boundaries. A clear record is more useful than a “safe” badge. ### Material inspected - skills/build-evidence-map/SKILL.md - README.md (installation and supported-host sections) - LICENSE - skills/build-evidence-map/references/evidence-ladder.md - skills/build-evidence-map/references/map-schema.md - skills/build-evidence-map/scripts/contract.mjs - skills/build-evidence-map/scripts/validate.mjs ### Our findings - The entire skill, schema/evidence references and both JavaScript helpers were read. - The validator checks dates, IDs, edge targets, graph reachability and cycles, then hashes canonicalized content; no helper was executed. ### Not established by this review - No upstream definition, helper, installer or generated workload was executed. - No end-to-end agent session or effectiveness benchmark was run. The review applies to the material and revision named here. A newer upstream release can change its behavior. 03 / PUT IT TO WORK ## Add a skill to your workflow. Upstream setup instructions ↗ DOCUMENTED COMMAND npx skills add https://github.com/github/awesome-copilot/tree/a19b3101cc797a35de8b1c1698c13d1344703522/skills/build-evidence-map --skill build-evidence-map Copy command ↗ Copying does not execute this command. It may retrieve a newer version than the reviewed source. - Install the complete skill directory, including its references and helpers; select your intended host and project scope. - Review the instructions before invoking them. The source revision is pinned; the installer was not executed or version-pinned by this review. ### Before you start - Node.js/npm and git for the documented Skills installer - An agent host that supports the skill format and the tools required by the workflow - Node.js for the bundled structural validator; optional Doubt CLI is a separate dependency ### Compatibility GitHub Copilot ### Repository instructions and host-provided tools - Read selected sources and record bounded excerpts - Write the map and receipt locally - Optional external verification fetches source URLs only when separately enabled ### Cost model MIT-licensed collection; agent usage and any separately chosen verification service or CLI terms are additional. 04 / FOLLOW THE EVIDENCE ## The source trail. Our notes are separate from the original resource. Check upstream before adopting a new version. - Definition at the reviewed revision ↗ Checked 2026-09-22 https://github.com/github/awesome-copilot/blob/a19b3101cc797a35de8b1c1698c13d1344703522/skills/build-evidence-map/SKILL.md Supports: summary, upstreamDescription, whySelected, bestFor, limitations, review, access - Publisher installation guidance ↗ Checked 2026-09-22 https://github.com/github/awesome-copilot/blob/a19b3101cc797a35de8b1c1698c13d1344703522/README.md Supports: install, compatibility - Licence at the reviewed revision ↗ Checked 2026-09-22 https://github.com/github/awesome-copilot/blob/a19b3101cc797a35de8b1c1698c13d1344703522/LICENSE Supports: license, access.cost - Reviewed companion: skills/build-evidence-map/references/evidence-ladder.md ↗ Checked 2026-09-22 https://github.com/github/awesome-copilot/blob/a19b3101cc797a35de8b1c1698c13d1344703522/skills/build-evidence-map/references/evidence-ladder.md Supports: review, limitations, install, access - Reviewed companion: skills/build-evidence-map/references/map-schema.md ↗ Checked 2026-09-22 https://github.com/github/awesome-copilot/blob/a19b3101cc797a35de8b1c1698c13d1344703522/skills/build-evidence-map/references/map-schema.md Supports: review, limitations, install, access - Reviewed companion: skills/build-evidence-map/scripts/contract.mjs ↗ Checked 2026-09-22 https://github.com/github/awesome-copilot/blob/a19b3101cc797a35de8b1c1698c13d1344703522/skills/build-evidence-map/scripts/contract.mjs Supports: review, limitations, install, access - Reviewed companion: skills/build-evidence-map/scripts/validate.mjs ↗ Checked 2026-09-22 https://github.com/github/awesome-copilot/blob/a19b3101cc797a35de8b1c1698c13d1344703522/skills/build-evidence-map/scripts/validate.mjs Supports: review, limitations, install, access - Skills installer: README.md ↗ Checked 2026-09-22 https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md Supports: install - Skills installer: src/git.ts ↗ Checked 2026-09-22 https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/src/git.ts Supports: install - Skills installer: src/source-parser.ts ↗ Checked 2026-09-22 https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/src/source-parser.ts Supports: install KEEP COMPARING ## Other approaches to consider. Related by category or shared topics. These are alternatives to inspect, not a measured quality order. [### Bug Receipt ↗ Creates an evidence-bearing defect or incident handoff that distinguishes verified, partial and blocked outcomes.](/skills/github-bug-receipt/)[### Superpowers Verification Before Completion ↗ Requires a fresh command result or direct check for each completion claim and distinguishes passing tests from fulfilling requirements.](/skills/obra-verification-before-completion/) [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)