Catalog
github/build-evidence-map

github

build-evidence-map

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.

v1.0Latest
New~1.3kUpdated Aug 6, 2026

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

  1. 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.

  2. 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.

  3. 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.
  4. Type every edge. Use supports, contradicts, qualifies, or missing. 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.

  5. Preserve counterevidence. Do not delete contrary evidence because the provisional verdict survives it. Represent scope differences with qualifies edges.

  6. Express uncertainty structurally. Do not invent confidence percentages. Add an unknown, narrow the position, or qualify a claim.

  7. Write UTF-8 JSON with a .doubt.json suffix. Follow references/map-schema.md. Keep IDs short, stable, and semantic.

  8. Validate fail-closed. Resolve scripts/validate.mjs relative to this SKILL.md, then run it with Node.js 18 or newer:

    node <skill-directory>/scripts/validate.mjs decision.doubt.json
    

    The 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 0 and prints VALID followed 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
    
  9. 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.json
    

    Never run this command implicitly. Local file verification does not use the network. Do not write a verification object by hand or hide a mismatch.

  10. 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 position has 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 unknown node;
  • 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.

Files5
5 files · 26.6 KB

Select a file to preview

Overall Score

88/100

Grade

A

Excellent

Safety

90

Quality

88

Clarity

87

Completeness

85

Summary

This skill guides agents to construct auditable evidence maps for contested technical decisions and research synthesis. It provides a structured JSON-based format for organizing evidence, claims, counterarguments, and knowledge gaps with precise source locators and edge relationships. The skill emphasizes preservation of disagreement and treats the JSON artifact as the canonical editable form.

Detected Capabilities

file read (evidence-ladder, map-schema references)file write (JSON artifact creation)local file validation (Node.js script execution)optional network request (explicit source verification via doubt CLI)code generation (JSON structure generation)

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

evidence synthesiscontested decisionresearch proposal reviewdecision artifactsource attributioncounterargument mapping

Risk Signals

INFO

Network request via 'doubt verify' command

Step 9, command block
INFO

External CLI tool invocation ('doubt-ai@0.8.0')

Steps 8–9, code blocks
INFO

Optional explicit source verification

Step 9

Referenced Domains

External domains referenced in skill content, detected by static analysis.

example.com

Use Cases

  • Review contested architectural decisions with balanced evidence
  • Synthesize research findings with explicit source attribution
  • Document proposal trade-offs and missing information
  • Build decision records that preserve counterarguments
  • Audit consensus claims by surfacing contradicting evidence
  • Track unresolved questions that could change verdicts

Quality Notes

  • Comprehensive workflow with clear step-by-step instructions (10 steps, each actionable)
  • Strong quality gates section defines all structural requirements for a valid map
  • Evidence ladder provides explicit guidance on source ranking and counterfeits
  • Schema reference is complete with JSON example and invariant rules
  • Clear distinction between validation (local, deterministic) and verification (network, optional, explicit)
  • Validation fail-closed pattern ensures agent reports actual outcomes, not invented successes
  • All reference files present and appropriately scoped
  • Edge-relation semantics (supports/contradicts/qualifies/missing) are well-differentiated
  • Guideline on not inventing confidence percentages promotes structural rigor over false precision
Model: claude-haiku-4-5-20251001Analyzed: Aug 6, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Use github/build-evidence-map in your dev environment

Command Palette

Search for a command to run...