paper-source-trace
Skill81 starsChanged 7 days agoMITView on GitHub
Use when a user provides an academic paper PDF, extracted paper text, citation contexts, or references and asks for paper source tracing, claim-centered source tracing, citation intent extraction, entity/relation extraction, contribution mapping, citation graph JSON, SVG/HTML citation maps, or optional AMiner metadata/citation enrichment. Do NOT use this skill for simple paper lookup by title, scholar search, or lightweight academic queries — use aminer-free-academic or aminer-academic-search for those instead.
- Reads credentials
In this repository21 other files it gives its agents.
- aminer-academic-searchSkill
- aminer-daily-paperSkill
- aminer-deep-searchSkill
- aminer-experiment-to-paperSkill
- aminer-exp-extractionSkill
- aminer-free-academicSkill
- aminer-grant-applicationSkill
- aminer-paper-deep-readingSkill
- aminer-paper-writingSkill
- aminer-patent-tech-intelligenceSkill
- aminer-pdf-ocrSkill
- aminer-thesis-writingSkill
- aminer-topic-advisor-selectionSkill
- baseline-finderSkill
- citation-faithfulnessSkill
- deep-researchSkill
- pdf-citation-verifierSkill
- related-work-auditSkill
- scientific-taxonomySkill
- sota-finderSkill
- structured-reference-auditSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
27 rules. About 0 are common, 11 are distinctive, and 16 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
This author's own choices. Worth a look.
16
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 33
Use SKILL.zh.md when the user mainly writes in Chinese or explicitly requests Chinese output.
- Very specific: line 34
Use this SKILL.md for all other requests.
- Very specific: line 35
Keep json/graph/citation_graph.json keys, intent labels, relation types, source roles, and parameter names in English in both workflows.
- Very specific: line 73
Before reading the paper, extracting citations, checking AMINER_API_KEY, calling AMiner, or generating SVG, ask the user to confirm:
- Distinctive: line 78
If the user already supplied one or both values, restate them as provisional and still ask for final confirmation.
- Very specific: line 80
If interactive confirmation is genuinely impossible, use the recommended defaults: svg: both and aminer: on.
- Distinctive: line 84
Use only supplied paper text, citation contexts, reference entries, user notes, or explicitly requested AMiner results as evidence.
- Distinctive: line 85
Do not infer citation intent from domain memory alone.
- Very specific: line 89
Keep citation_sentence and context in the source language of the target paper.
- Very specific: line 90
Use the user's output language for evidence, summary, notes, Markdown report text, and visible SVG/HTML UI.
- Distinctive: line 91
If output files can be written, do not stop at a chat-only summary.
- Very specific: line 95
When confirmation is possible, treat AMiner as off unless the user confirms aminer: on or explicitly writes enhance with AMiner, use AMiner …
- Very specific: line 99
Check only whether AMINER_API_KEY exists.
- Distinctive: line 100
If missing, continue local analysis and record that enrichment was skipped.
- Very specific: line 101
Use the shortest viable chain: paper_search or paper_search_pro, paper_detail, paper_relation, and paper_info.
- Very specific: line 103
If estimated cost is ¥5 or more, ask for explicit confirmation before paid calls.
- Distinctive: line 108
Use only these labels unless the user explicitly extends the taxonomy:
- Distinctive: line 114
Ask the startup confirmation question and wait for the answer.
- Very specific: line 117
Read references/evidence_protocol.md before important classification or source tracing.
- Distinctive: line 122
If AMiner is enabled, enrich metadata without replacing local evidence.
- Very specific: line 123
Write json/graph/citation_graph.json before visual artifacts.
- Very specific: line 124
Write analysis.md; use references/analysis_template.md only for explicit template or fixed-format requests.
- Very specific: line 126
Do not hand-write ad hoc SVG or HTML.
- Very specific: line 140
Every citation has intent, evidence, confidence, and either reference_id or unmatched_reference: true.
- Distinctive: line 141
Every intent label is in the allowed list.
- Distinctive: line 144
Every entity is supported by at least one citation.
- Distinctive: line 145
Every source trace is grounded in at least one local citation context.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Paper Source Trace
Paper Source Trace turns one target paper into grounded, claim-centered source-tracing artifacts. It keeps one canonical skill name, paper-source-trace.
Invoke it through natural language or /paper-source-trace.
Language Routing
- Use
SKILL.zh.mdwhen the user mainly writes in Chinese or explicitly requests Chinese output. - Use this
SKILL.mdfor all other requests. - Keep
json/graph/citation_graph.jsonkeys, intent labels, relation types, source roles, and parameter names in English in both workflows.
English Workflow
Standard Artifacts
Produce these artifacts when evidence and filesystem access allow:
analysis.md: human-readable report.json/graph/citation_graph.json: canonical machine-readable graph followingreferences/schema.md.citation_map.svg: static citation map when SVG generation is possible.citation_map.html: single-file interactive graph when graph data is available.citation_map_chain.svg: chain-style source trace SVG only whensvg: both.citation_map_spec.md: only when SVG generation has caveats or fails.
Default output directory:
outputs/paper-source-trace/<safe-paper-stem>/Preferred layout:
analysis.md
citation_map.svg
citation_map.html
citation_map_chain.svg # only when svg is both
citation_map_spec.md # only when SVG generation has caveats or fails
json/graph/citation_graph.json
json/aminer/*.json # only when AMiner raw results are saved
json/extraction/*.json # only when structured intermediates are savedLegacy compatibility: if the user writes mode: current, treat it as svg: radial; mode: example as svg: chain; and mode: all as svg: both. If svg and mode are both supplied and conflict, ask the user to confirm the intended SVG output. hybrid, interactive graph, or expandable knowledge graph means the user wants the standard citation_map.html; it is not an SVG mode and does not change the SVG choice.
Startup Confirmation
Before reading the paper, extracting citations, checking AMINER_API_KEY, calling AMiner, or generating SVG, ask the user to confirm:
- SVG output:
radial,chain, orboth. - AMiner enrichment:
onoroff.
If the user already supplied one or both values, restate them as provisional and still ask for final confirmation. Stop until the user answers.
If interactive confirmation is genuinely impossible, use the recommended defaults: svg: both and aminer: on. Still follow the high-cost confirmation rule before any AMiner call estimated at ¥5 or more; if AMINER_API_KEY is missing, skip AMiner enrichment and continue local analysis.
Core Rules
- Use only supplied paper text, citation contexts, reference entries, user notes, or explicitly requested AMiner results as evidence.
- Do not infer citation intent from domain memory alone.
- AMiner enrichment is explicit opt-in only. Do not check
AMINER_API_KEYunless requested. - AMiner may enrich IDs, URLs, candidate reference matches, and external citation relationships, but it cannot replace local citation contexts or prove intent/source traces by itself.
- Preserve uncertainty; lower confidence when citation context, reference matching, or source role evidence is incomplete.
- Keep
citation_sentenceandcontextin the source language of the target paper. They are original evidence anchors, not localized explanations. - Use the user's output language for
evidence,summary,notes, Markdown report text, and visible SVG/HTML UI. - If output files can be written, do not stop at a chat-only summary.
AMiner Enrichment
When confirmation is possible, treat AMiner as off unless the user confirms aminer: on or explicitly writes enhance with AMiner, use AMiner metadata, complete paper_id, or trace AMiner citation relationships. When confirmation is genuinely impossible, the recommended fallback is aminer: on.
When enabled:
- Check only whether
AMINER_API_KEYexists; never print the token. - If missing, continue local analysis and record that enrichment was skipped.
- Use the shortest viable chain:
paper_searchorpaper_search_pro,paper_detail,paper_relation, andpaper_info. - Output a cost summary for all planned or completed AMiner calls.
- If estimated cost is
¥5or more, ask for explicit confirmation before paid calls. - Record enrichment metadata under
metadata.aminer_enrichmentinjson/graph/citation_graph.json.
Intent Labels
Use only these labels unless the user explicitly extends the taxonomy:
background, problem, core-method, supporting-method, dataset, metric, baseline, tool-resource, theory, result-evidence, limitation, future-work.
Execution Steps
- Ask the startup confirmation question and wait for the answer.
- Resolve input evidence and output directory.
- Extract reliable paper text, reference entries, and citation contexts.
- Read
references/evidence_protocol.mdbefore important classification or source tracing. - Classify citations with the allowed intent labels.
- Extract key target-paper claims or contributions when supported by text.
- Build
source_traces[]by linking claims to local citation contexts, cited-source roles, and evidence steps. - Extract entities and relations that explain the target paper.
- If AMiner is enabled, enrich metadata without replacing local evidence.
- Write
json/graph/citation_graph.jsonbefore visual artifacts. - Write
analysis.md; usereferences/analysis_template.mdonly for explicit template or fixed-format requests. - Generate
citation_map.htmland the confirmed SVG output with one renderer command:python3 scripts/render_html.py --graph <output>/json/graph/citation_graph.json --output <output>/citation_map.html --svg <radial|chain|both> --language auto. - Do not hand-write ad hoc SVG or HTML; both static SVG modes and the HTML
radial / chainviews must share the renderer layout, colors, language pack, text wrapping, node priority, and edge rules. - Validate artifacts before the final reply.
Reference Files
references/schema.md: canonical schema and JSON example.references/evidence_protocol.md: evidence and uncertainty rules.references/prompts.md: English and Chinese extraction/review prompts.references/visual.md: SVG and HTML graph rules.references/analysis_template.md: fixed report templates for explicit template mode.scripts/render_html.py: standard graph renderer. Use it forcitation_map.html,citation_map.svg, andcitation_map_chain.svg; do not hand-write ad hoc SVG or HTML.
Quality Checks
- Every citation has
intent,evidence,confidence, and eitherreference_idorunmatched_reference: true. - Every intent label is in the allowed list.
- Key citations trace back to a citation sentence or local context.
citation_sentenceandcontextpreserve the target paper's original language; only explanation fields are localized.- Every entity is supported by at least one citation.
- Every source trace is grounded in at least one local citation context; AMiner metadata cannot be the sole support.
- Generate
citation_map.htmland SVG maps withscripts/render_html.pyafterjson/graph/citation_graph.jsonis written. HTML and SVG must use one visible language, the same canonical group labels, the same node ranking, and the same reduced-edge layout strategy. - Static SVG should use only useful main edges, summarize dense groups with
+N, and avoid citation-to-citation cross-links or AMiner-only relation lines. json/graph/citation_graph.jsonremains complete even if Markdown, SVG, or HTML has caveats.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

