openai-deep-research-citation-fixer/SKILL.md
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.
npx skillsauth add memgrafter/skills-flatagents openai-deep-research-citation-fixerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this when a Deep Research markdown export contains broken markers like citeturn... 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.
<file>.bkp created before write)## References with anchor IDsCitations · N blocks with duplicated URL linesturn... IDs to exact per-claim URLs (not available in exported markdown)~/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
JSON report with:
ok: true/falsetools
Use this as the default toolset for coding sessions when you want faster navigation, search, file inspection, and git workflow execution with lower command overhead: tools: - fzf - ripgrep - bat - delta - lazygit - starship - zoxide - eza - atuin - yazi
development
Turn a URL into a durable knowledge artifact: searchable markdown summary + local raw text archive, so you can recall it later without revisiting the web.
development
Run shell commands and analyze output with validated summaries. Use for build logs, test output, or any command with substantial output. Protects context by returning concise summaries with grep-validated citations.
development
Search the web and refine results to key findings. Use when the user asks to search and summarize, find and refine web results, or wants concise research summaries.