agentleFS
Sign inStart free
memgraftermemgrafter/skills-flatagents/openai-deep-research-citation-fixer/SKILL.md

openai-deep-research-citation-fixer

Skill3 starsChanged 8 months agoApache-2.0View on GitHub

Deterministically fixes broken OpenAI Deep Research markdown citations without using an LLM: creates a .bkp backup, rewrites citation markers, rebuilds references, and runs strict regex validation.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this when a Deep Research markdown export contains broken markers like citeturn... or entity... and you want a one-command cleanup.

    line 9
  2. Distinctive:

    No LLM needed (fully deterministic Python transform)

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Use this when a Deep Research markdown export contains broken markers like citeturn... or entity... and you want a one-command cleanup.

By default it warns/stops if Citations/References are not pasted at the bottom of the document.

Why use it

  • No LLM needed (fully deterministic Python transform)
  • Safe by default (<file>.bkp created before write)
  • Rebuilds clean ## References with anchor IDs
  • Warns if citations are not at the bottom (safer for paste workflows)
  • Runs direct-match validation and returns JSON pass/fail report

When to use

  • OpenAI Deep Research markdown files with broken citations
  • Reports that have Citations · N blocks with duplicated URL lines
  • Batch cleanup workflows where repeatability matters

When NOT to use

  • Non-markdown files
  • Cases where you need semantic remapping from turn... IDs to exact per-claim URLs (not available in exported markdown)

Usage

~/code/skills-flatagents/openai-deep-research-citation-fixer/run.sh ~/Downloads/deep-research-report.md

Dry-run (transform + validate, no write):

~/code/skills-flatagents/openai-deep-research-citation-fixer/run.sh ~/Downloads/deep-research-report.md --no-overwrite

Skip bottom-placement warning (advanced/use with intent):

~/code/skills-flatagents/openai-deep-research-citation-fixer/run.sh ~/Downloads/deep-research-report.md --skip-bottom-warning

Auto-accept warning prompts (automation friendly; implies skip):

~/code/skills-flatagents/openai-deep-research-citation-fixer/run.sh ~/Downloads/deep-research-report.md --yes

Output

JSON report with:

  • file path
  • backup path
  • replacement stats
  • validation checks
  • final ok: true/false

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free