paper-reading-problem-reality-check — Claude Code skill: problem check
paper-reading-problem-reality-check puts a single Research Question Card under pressure: is the problem real, is evidence behind it, and would the motivation survive a skeptical reviewer?
no license ★ 240 updated 2026-09-18
npx skills add franklee16/academic-research-skills --skill paper-reading-problem-reality-check -a claude-codeWhat paper-reading-problem-reality-check does
The skill takes one Research Question Card and tests the motivation behind it: whether the problem exists, whether evidence sits under it, whether earlier work already covers the gap, and whether the wording holds up when someone pushes back. It ends with a fixed verdict written to problem_reality_check.md.
Artifacts land under {workspace-root}/research-question-checks/{field-slug}/, with workspace as the default root. The run writes source_card.md, follows the card's evidence links into the field map and supporting files, then builds interrogation_transcript.md one challenge question at a time. It waits for your answer before moving on, and each answer gets a dimension verdict. Six dimensions are covered: Problem Existence, Real-World Grounding, Evidence Support, Saturation / Prior-Solution Risk, Motivation Claim Safety, Scope and Stakeholder Fit.
Method critique, experiment design and fresh literature search stay out of scope, so nothing from outside your local workspace is pulled in. A card with no evidence links can still be checked; expect needs-evidence or motivation-fragile as the likely outcome. One card per run, so bring several and it asks you to pick.
What it helps with
- stress-test a problem statement before it reaches the motivation section
- spot motivation claims that rest on an unchecked assumption
- check whether earlier work already covers the same gap
- produce a verdict report to show an advisor
- list the evidence a research question still needs
Example prompts for the agent
- Run a Problem Reality Check on the card at
research-questions/nlp/cards/gap-1.md. - Stress-test whether this problem is real before I write the motivation.
- Interrogate the evidence behind this Research Question Card, one question at a time.
How to install paper-reading-problem-reality-check
1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill paper-reading-problem-reality-check -a claude-code2Manually: put the files in place
~/.claude/skills/03-problem-reality-check/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/03-problem-reality-check/
1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill paper-reading-problem-reality-check -a codex2Manually: put the files in place
.agents/skills/03-problem-reality-check/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill paper-reading-problem-reality-check -a cursor2Manually: put the files in place
.cursor/skills/03-problem-reality-check/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install franklee16/academic-research-skills lit-review/Paper-Reading-Skills-main/skills/03-problem-reality-check2Manually: put the files in place
.github/skills/03-problem-reality-check/SKILL.md1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill paper-reading-problem-reality-check -a gemini-cli2Platform CLI
gemini skills install https://github.com/franklee16/academic-research-skills --path lit-review/Paper-Reading-Skills-main/skills/03-problem-reality-checkManually: put the files in place
.devin/skills/03-problem-reality-check/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about paper-reading-problem-reality-check
How to install paper-reading-problem-reality-check in Claude Code?
Run npx skills add franklee16/academic-research-skills --skill 03-problem-reality-check -a claude-code. The skill file then sits at ~/.claude/skills/03-problem-reality-check/SKILL.md.
What does paper-reading-problem-reality-check do?
It checks the motivation of one Research Question Card across six dimensions and writes a report with a verdict. It leaves the method and the experiments alone.
What do I need before running it?
One selected Research Question Card inside the workspace; the default root is the workspace folder. Without evidence links the verdict leans to needs-evidence or motivation-fragile.