paper-reading-method-commitment — Claude Code skill: what it does
The paper-reading-method-commitment skill guides a research method from a chosen or assembled starting point to a recorded status. Use it before experiment planning or research framing.
no license ★ 240 updated 2026-09-18
npx skills add franklee16/academic-research-skills --skill paper-reading-method-commitment -a claude-codeWhat paper-reading-method-commitment does
The workflow fixes one source method and one problem, reviews relevant local files, then maps the method’s parts and challenges risky assumptions with the user. When a decision changes the method’s structure, the skill records it and updates the reconstruction where needed.
It assigns one of four statuses: committed, provisionally-committed, needs-redesign, or reject-current-method. Only committed work is ready to pass downstream as a normal source. The skill does not search broadly for methods, select a winner automatically, or produce a complete experiment plan.
Working files go under method-commitments within the chosen workspace root, alongside a summary of the decision. If the initial brief lacks key details, the skill asks for them before reconstruction or critique. To install it in Claude Code, run npx skills add franklee16/academic-research-skills --skill 06-method-commitment -a claude-code; the skill file is at ~/.claude/skills/06-method-commitment/SKILL.md.
What it helps with
- converge on one method from several candidate approaches
- map a method’s inputs, outputs, and mechanism
- surface risky design assumptions before experiment planning
- record a method decision and its status in workspace files
Example prompts for the agent
- Help me settle on a status for this research method before I plan experiments.
- Combine these candidate approaches into one method and identify its weakest link.
- Review my rough method and ask for any missing details before assessing it.
How to install paper-reading-method-commitment
1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill paper-reading-method-commitment -a claude-code2Manually: put the files in place
~/.claude/skills/06-method-commitment/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/06-method-commitment/
1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill paper-reading-method-commitment -a codex2Manually: put the files in place
.agents/skills/06-method-commitment/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill paper-reading-method-commitment -a cursor2Manually: put the files in place
.cursor/skills/06-method-commitment/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/06-method-commitment2Manually: put the files in place
.github/skills/06-method-commitment/SKILL.md1Skills CLI (Vercel)
npx skills add franklee16/academic-research-skills --skill paper-reading-method-commitment -a gemini-cli2Platform CLI
gemini skills install https://github.com/franklee16/academic-research-skills --path lit-review/Paper-Reading-Skills-main/skills/06-method-commitmentManually: put the files in place
.devin/skills/06-method-commitment/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-method-commitment
How do I install paper-reading-method-commitment in Claude Code?
Run npx skills add franklee16/academic-research-skills --skill 06-method-commitment -a claude-code. The skill file is at ~/.claude/skills/06-method-commitment/SKILL.md.
What does paper-reading-method-commitment do?
It helps shape and assess one research method, then assigns a status that controls whether it can proceed to later workflows. Only committed methods are routed onward as normal sources.
What information should I have before using the workflow?
The workflow needs one method tied to one source problem. If the brief lacks essential details, it asks about the problem, failure addressed, inputs, outputs, mechanism, expected improvement, and boundaries before starting its assessment.