Skip to content

gpsaggese/helpers / .claude/skills/research_idea.add_from_file

research_idea.add_from_file

Verified

Split a raw idea dump file into titled ideas and create idea files

Goal

  • Given a file <FILE> of very early, unstructured research ideas (loose fragments, one-liners, mixed bullets), add a ## <Title> header above each distinct idea
  • Once the user approves, create one template-formatted research idea file per idea

Workflow

Read the Inputs

  • Read <FILE>
  • Read the template .claude/templates/research_idea.template.md
  • Read .claude/skills/research_idea.rules.md for file naming and directory conventions
  • Read the file names under research/ideas/*.md to know which ideas exist

Title and Group the Fragments

  • Split <FILE> into distinct ideas
    • Merge fragments that describe the same idea into one group. Reordering or combining related fragments is fine
    • Keep fragments that are already distinct ideas separate, even if short
  • Add a ## <Title> header directly above each idea's raw content
    • <Title> is a short noun phrase (3-8 words) naming the idea, in the style of existing file names, e.g. Hierarchical Training, Compression as Proxy for Understanding
    • If a fragment already has a ## header, keep or refine that title instead of adding a duplicate
  • Do not summarize, expand, or fabricate content. Only add headers and move fragments next to the other fragments of the same idea
  • Flag (do not silently drop) any fragment whose idea already exists as a file under research/ideas/*.md, so the user can decide whether to skip it
  • Write the titled, grouped result back into <FILE>

Wait for the User

  • Show the user the proposed titles and which fragments are grouped under each
  • Wait for the user to approve <FILE> before creating any new idea file
  • If the user requests different titles or groupings, apply them and present the file again

Create One Idea File per Approved Idea

  • For each approved ## <Title> section, create research/ideas/draft.<Idea_Name>.md, per .claude/skills/research_idea.rules.md ## Status Prefixes
    • <Idea_Name> is <Title> in Title_Case_With_Underscores, matching existing file names (e.g. Hierarchical Training -> Hierarchical_Training)
  • Seed the new file with the section's raw content as the seed for Core Idea
  • Say in the idea file how it was generated, with this line right after the title:
    - Generated by `.claude/skills/research_idea.add_from_file/SKILL.md`
    
  • Skip creating a file for any idea the user chose to skip in Step 3

Clean Up the Source File

  • Ask the user whether to remove, from <FILE>, the sections that were split out into new idea files (or delete <FILE> if every section was split out)
  • Only remove a section once its new idea file exists and the user confirms its content was fully captured

Conventions

  • Follow .claude/skills/research_idea.rules.md

Constraints

  • Do not create any new idea file before the user approves the titled, grouped <FILE>
  • Do not fabricate content when titling or grouping fragments. Only add headers and reorganize the existing raw text
  • Do not remove content from <FILE> without user confirmation, per the Clean Up the Source File step

Examples

  • research/ideas/new_ideas.md: a raw idea dump file, the typical <FILE> input for this skill
  • See .claude/skills/research_idea.rules.md # Examples for a fully formatted research idea

Verification

  • Every fragment in <FILE> is grouped under a ## <Title> header
  • The user approved the titled, grouped <FILE> before any new idea file was created
  • Each new idea file follows .claude/templates/research_idea.template.md
  • Each new idea file is named research/ideas/draft.<Idea_Name>.md per .claude/skills/research_idea.rules.md ## Status Prefixes
  • No content from <FILE> was fabricated or lost while splitting
  • The idea file says that it was generated by .claude/skills/research_idea.add_from_file/SKILL.md
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall