Membuat peta bukti JSON yang dapat diaudit untuk mendokumentasikan informasi yang mendukung, bertentangan, dan informasi yang hilang dalam pengambilan keputusan teknis serta sintesis riset.
- Bintang GitHub
- 41.038
- File
- 5
- Commit terakhir
- 11 Nov 2026
- Lisensi
- MIT
- Tool yang diizinkan
- —
Apa fungsi skill build-evidence-map?
build-evidence-map adalah agent skill. Membuat peta bukti JSON yang dapat diaudit untuk mendokumentasikan informasi yang mendukung, bertentangan, dan informasi yang hilang dalam pengambilan keputusan teknis serta sintesis riset.
Ringkasan dibuat dari SKILL.md skill ini.
Tentang skill build-evidence-map
Skill ini memungkinkan Anda untuk mendokumentasikan penalaran kompleks di balik keputusan teknis atau sintesis riset. Ini membantu developer dan peneliti untuk melampaui sekadar teks naratif dengan membuat peta bukti JSON yang dapat diaudit, yang menangkap informasi yang mendukung, bertentangan, maupun yang hilang. Alih-alih merangkum perbedaan pendapat menjadi satu ringkasan saja, tool ini menjaga hubungan antara posisi utama, klaim perantara, bukti spesifik, dan fakta yang belum diketahui.
Seorang agent harus memuat skill ini ketika pengguna mengajukan pertanyaan yang diperdebatkan atau keputusan penting yang membutuhkan transparansi struktural. Proses ini menghasilkan file .doubt.json yang berisi directed graph dari penalaran tersebut. Anda dapat memvalidasi file ini menggunakan script Node.js bawaan dan merendernya ke dalam HTML menggunakan package doubt-ai. Workflow ini mengandalkan locator sumber yang presisi, seperti nomor halaman atau timestamp, untuk memastikan setiap klaim terhubung ke wilayah spesifik yang terukur dari sumber primer.
Apa yang bisa dilakukan agent dengannya
- 1Mendokumentasikan pilihan teknis yang diperdebatkanBuat artefak keputusan yang portabel untuk menunjukkan apa yang mendukung suatu posisi dan apa yang menentangnya.
- 2Memverifikasi integritas sumberPastikan kutipan yang dicatat sesuai dengan sumber file lokal atau HTTP aslinya.
- 3Memvalidasi integritas reasoning graphJalankan validasi deterministik untuk memeriksa adanya duplicate edges, directed cycles, atau error pada schema.
Ditulis dari SKILL.md milik skill tersebut. Setiap use case diverifikasi dengan kutipan darinya.
Cara install skill build-evidence-map
Setiap perintah menyalin folder skill ke direktori skills client. Restart client atau mulai sesi baru untuk memuatnya.Install skill build-evidence-map di Claude Code
~/.claude/skills/build-evidence-map/SKILL.md
$ npx degit github/awesome-copilot/skills/build-evidence-map ~/.claude/skills/build-evidence-mapInstall skill build-evidence-map di Claude Code (project)
.claude/skills/build-evidence-map/SKILL.md
$ npx degit github/awesome-copilot/skills/build-evidence-map .claude/skills/build-evidence-mapInstall skill build-evidence-map di Codex
~/.agents/skills/build-evidence-map/SKILL.md
$ npx degit github/awesome-copilot/skills/build-evidence-map ~/.agents/skills/build-evidence-mapInstall skill build-evidence-map di Gemini CLI
~/.gemini/skills/build-evidence-map/SKILL.md
$ npx degit github/awesome-copilot/skills/build-evidence-map ~/.gemini/skills/build-evidence-mapInstall skill build-evidence-map di Claude.ai
npx degit github/awesome-copilot/skills/build-evidence-map build-evidence-map && zip -r build-evidence-map.zip build-evidence-map # claude.ai → Customize → Skills → + → Create skill → Upload a skill → build-evidence-map.zip
Pengecekan otomatis
Berjalan 15 Nov 2026Laporan lengkap →Lolos cek otomatis kami. Ini bukan audit keamanan: baca skripnya sebelum membiarkan agent menjalankannya. Cara kerja checks
- Source repository terhubung dan dapat dijangkaugithub/awesome-copilot/skills/build-evidence-map is public and reachablegithub.com/github/awesome-copilot/tree/HEAD/skills/build-evi ↗Lolos
- Lisensi open source (OSI)MITspdx.org/licenses/MIT.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit 2026-11-11github.com/github/awesome-copilot/commits ↗Lolos
- Skrip tanpa unduh-lalu-jalankan atau pencurian kredensial2 scripts read; no download-and-run, remote eval, base64 execution or credential uploadLolos
- Tidak ada instruksi tersembunyi di SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/github/awesome-copilot/blob/HEAD/skills/build-evi ↗Lolos
- Tool yang diizinkan otomatis dibatasiNo pre-approved tools; the agent asks before using onegithub.com/github/awesome-copilot/blob/HEAD/skills/build-evi ↗Lolos
- SKILL.md mengikuti format Agent SkillsValid name and description; says when to use it; 108 linesgithub.com/github/awesome-copilot/blob/HEAD/skills/build-evi ↗Lolos
SKILL.md
Lihat di 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.
Berkas dalam skill ini
5Pertanyaan seputar skill build-evidence-map
Bagaimana cara install skill build-evidence-map di Claude Code?
Jalankan npx degit github/awesome-copilot/skills/build-evidence-map ~/.claude/skills/build-evidence-map. Claude Code memuat skill dari ~/.claude/skills (semua proyek) atau .claude/skills (satu proyek) dan menggunakan skill saat deskripsinya cocok dengan tugas.
Client mana saja yang bisa menggunakan skill build-evidence-map?
Client apa pun yang membaca format Agent Skills: Claude Code, Codex, Gemini CLI, dan claude.ai (unggah sebagai ZIP). Script dalam skill hanya berjalan di client yang mengizinkan eksekusi kode.
Kapan saya harus menggunakan skill ini alih-alih workflow fact-checking sederhana?
Gunakan skill ini ketika hubungan antara bukti, klaim perantara, trade-off, dan fakta yang hilang menjadi penting, bukan sekadar untuk klaim faktual sederhana.
Bagaimana cara memvalidasi bahwa peta bukti saya sudah benar?
Anda dapat memvalidasi peta tersebut menggunakan script validator bawaan dengan Node.js 18 atau versi terbaru dengan menjalankan node <skill-directory>/scripts/validate.mjs decision.doubt.json.
Apa saja tipe node yang diperbolehkan dalam reasoning graph?
Peta ini menggunakan empat tipe node spesifik: position, claim, evidence, dan unknown.