
Build Evidence Map
OfficialFreeCreate auditable maps for technical decisions and research.
Free · Opens the source repo
What Build Evidence Map does
The Build Evidence Map skill enables users to construct a structured and auditable artifact that details the evidence surrounding a contested technical decision. This skill is particularly useful for developers and researchers who need to synthesize complex information, presenting both supporting and contradicting evidence in a clear, traceable format. By focusing on the relationships between claims, evidence, and uncertainties, users can ensure that their decision-making process is transparent and well-documented.
To utilize this skill, users begin by framing a specific, falsifiable question and establishing a provisional position. They then gather bounded source regions, prioritizing primary sources and direct observations, which are essential for maintaining the integrity of the evidence map. The skill emphasizes the importance of preserving counterevidence and structuring uncertainty, ensuring that all relevant information is accounted for without oversimplifying the complexities of the situation.
The workflow includes creating nodes for positions, claims, evidence, and unknowns, and typing edges to illustrate the relationships between these nodes. This structured approach helps users visualize how different pieces of evidence interact and supports thorough analysis. The skill culminates in generating a validated JSON file that can be shared and reviewed, providing a comprehensive overview of the decision-making process.
Overall, Build Evidence Map is designed for professionals who require a rigorous approach to decision-making, particularly in environments where evidence quality and traceability are paramount. It is ideal for technical teams, researchers, and anyone involved in proposal reviews or research synthesis, where clarity and accountability are essential.
When to use it
Use this skill when you need to create a detailed, auditable map for a complex decision that involves multiple sources of evidence.
When not to use it
Avoid using this skill for simple fact-checking or straightforward claims that do not require extensive evidence mapping.
What you can build with it
Technical Proposal Review
Use the skill to map out evidence when reviewing a technical proposal, ensuring all claims are backed by reliable sources.
Research Synthesis
Create an evidence map to synthesize findings from multiple studies, highlighting areas of agreement and disagreement.
Contested Decision Analysis
When faced with a contested technical choice, this skill helps visualize the supporting and contradicting evidence clearly.
How to install Build Evidence Map
View source1. Install with the skills CLI
npx skills add github/awesome-copilot/build-evidence-map --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by githubBuild Evidence Map
Turn one contested question into a portable decision artifact that shows what supports the current position, what pushes against it, and what remains unknown. Do not use a graph to decorate an answer that has not been sourced.
For a simple factual claim or a general fact-checking request, use a verification
workflow such as doublecheck instead. Use this skill when the relationships
between evidence, intermediate claims, trade-offs, and missing facts matter.
Workflow
-
Frame one decision. Write one falsifiable question and one provisional position. Narrow the question until a reader can identify what action or belief the map is testing.
-
Collect bounded source regions. Prefer direct observations and primary sources. Record the URL or absolute local path, publisher, publication date, retrieval date, section/page/line/timestamp locator, and a short checkable excerpt. Read references/evidence-ladder.md when source quality is disputed.
-
Atomize the reasoning. Create only four node types:
position: the single current verdict;claim: an intermediate proposition;evidence: a faithful statement of one source region;unknown: a specific missing fact that could change the verdict.
-
Type every edge. Use
supports,contradicts,qualifies, ormissing. Add a plain-language note explaining why the source node bears on the target. Topical similarity is not support. Different scope, date, or population is not automatically a contradiction. -
Preserve counterevidence. Do not delete contrary evidence because the provisional verdict survives it. Represent scope differences with
qualifiesedges. -
Express uncertainty structurally. Do not invent confidence percentages. Add an
unknown, narrow the position, or qualify a claim. -
Write UTF-8 JSON with a
.doubt.jsonsuffix. Follow references/map-schema.md. Keep IDs short, stable, and semantic. -
Validate fail-closed. Resolve
scripts/validate.mjsrelative to thisSKILL.md, then run it with Node.js 18 or newer:node <skill-directory>/scripts/validate.mjs decision.doubt.jsonThe bundled validator uses only Node.js built-ins and does not require npm or network access. Fix every finding before reporting success. Only say the map is valid when the command exits
0and printsVALIDfollowed by a 64-character receipt. A file hash, node count, JSON parse, or manual schema review is not a Doubt receipt. If deterministic validation cannot run, report that block instead of inventing success.Render the validated map only when the user has already installed
doubt-ai@0.8.0; do not install or execute a remote package implicitly:doubt map decision.doubt.json --out decision.html -
Verify source snapshots only with explicit network permission. The following command retrieves each recorded HTTP(S) source and fails closed if an excerpt cannot be matched:
doubt verify decision.doubt.json \ --out decision.verified.doubt.jsonNever run this command implicitly. Local file verification does not use the network. Do not write a
verificationobject by hand or hide a mismatch. -
Inspect the deliverable. Confirm that the question, verdict, counterevidence, unknowns, edge notes, and exact source regions remain readable. Treat JSON as the canonical editable artifact; HTML is a shareable view.
Quality gates
A finished map must satisfy all of these:
- exactly one
positionhas incoming reasoning; - every evidence node names one source and participates in an edge;
- every source is used and has dates, a bounded locator, and a substantive excerpt;
- every non-position node has a directed path to the position;
- the reasoning graph has no duplicate edges or directed cycles;
- contrary or qualifying evidence is present when the source set contains it;
- each decision-changing gap is an explicit
unknownnode; - every edge note explains support, contradiction, qualification, or absence;
- the verdict is no broader than the evidence.
Deliver the result
Report:
- the current position in one sentence;
- the strongest counterevidence or qualification;
- the most important unresolved unknown;
- paths to the canonical JSON and any rendered HTML;
- whether deterministic validation and explicit source verification ran.
Never describe a structurally valid map as proven true. Validation establishes traceability and graph integrity; source quality and inference quality still require human review.
Frequently asked questions about Build Evidence Map
Similar skills
Systematic Literature Review
Automate your systematic literature reviews with ease.
Nature Reference Verifier
Cross-verify academic references efficiently.
Nature Paper Card
Create evidence-grounded research cards for scientific papers.
Nature Literature Pipeline
Automate daily literature discovery and delivery.
Paperclip CLI
Efficiently search and read biomedical literature and regulatory documents.
Paper Lookup
Efficiently search academic literature across multiple APIs.
