build-evidence-map
Helps your agent create an evidence record for important decisions. It keeps information that supports, contradicts, or qualifies a technical choice.
What it does
Creates a detailed map organizing information about a technical decision or research. It shows what supports an idea, what contradicts it, and what is still unknown, with links to exact sources.
When to use it
- ✓When making an important technical decision.
- ✓When reviewing complex research.
- ✓When analyzing proposals with conflicting viewpoints.
Example of what to ask your AI
“Create an evidence map for the decision to use Python or Java for our new backend project, focusing on scalability and cost.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
The AI organizes information gathered from reliable sources. It separates what supports the decision (position), what goes against it (contradiction), and what is missing (unknown), linking everything back to the original sources.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add github/awesome-copilot --skill build-evidence-mapOr download just the file:
curl -L https://raw.githubusercontent.com/github/awesome-copilot/main/skills/build-evidence-map/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Build 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.htmlVerify 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;
…
FAQ
What's the difference between this tool and a simple web search?
This tool organizes and structures evidence to clearly show points of agreement, disagreement, and information gaps, with exact sources, rather than just presenting a block of text.
What are 'bounded source regions'?
These are specific parts of a document or website (like a page, paragraph, or timestamped excerpt) containing the information used, with details like URL, date, and author, so the origin can be verified.
What does 'fail-closed' mean?
It means the tool only reports success if all checks are completed successfully and without errors. If something fails, it does not proceed and indicates the problem.
Details
Original description by the author
Build an auditable evidence map for a contested technical choice, research synthesis, proposal review, or consequential decision. Use when Copilot must preserve supporting, contradicting, qualifying, and missing evidence with exact source regions instead of collapsing disagreement into prose.
repo: github/awesome-copilot
Popularity
- GitHub stars
- 40k
- Ranking position
- #5047
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
acquire-codebase-knowledge
Helps your agent understand and document an existing code project. It's useful for onboarding new people or getting an overview of the architecture.
github/awesome-copilot
acreadiness-assess
Enables your agent to assess a project's readiness for AI and generate a report. It's useful for understanding how well a project is prepared to use AI tools.
github/awesome-copilot
acreadiness-generate-instructions
Helps your agent create instructions for AI tools based on an assessment. It's useful for improving how AI interacts with code and closing identified gaps.
github/awesome-copilot
acreadiness-policy
Enables your agent to help define or apply policies for AI project assessment. It's useful for standardizing how projects are evaluated and ensuring compliance.
github/awesome-copilot
Similar skills
intent-driven-development
Helps your agent turn ideas into clear, testable plans. Defines criteria to ensure changes are made correctly and safely.
affaan-m/ECC
product-capability
Guides your agent in turning product ideas into clear plans. It defines what needs to be done, the limits, and decisions before development.
affaan-m/ECC
article-writing
Writes long-form content like articles, guides, and blog posts with a unique style. It's useful when you need well-written texts with a consistent voice and credibility.
affaan-m/ECC