Audit and fix citation formatting across brain pages. Ensures every fact has an inline [Source: ...] citation matching the standard format. Extended in v0.25.1: scans for broken tweet/post references that lack actual URLs and resolves them via the host's X / Twitter API integration.
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The canonical home for this skill is citation-fixer in garrytan/gbrain
Convention: see conventions/quality.md for the canonical citation format every fix should match.
Output rule: all links MUST be deterministic (built from API data, not composed by LLM). See _output-rules.md.
This skill guarantees:
https://x.com/<handle>/status/<id>
links.[Source: ...] citations.x.com URLsconventions/quality.md.For each broken tweet reference, follow this chain. The actual API call
goes through whatever X integration the host has configured (typical
shape: a recipe under recipes/x-api/ with handle / search-all
endpoints).
Scan the page for patterns that indicate tweet references without URLs:
tweeted, posted, said on X, RT, retweet,
X post[Source: ... X/Twitter ...] without an x.com URLFrom each broken reference, extract:
@<username>)Use the host's X API integration. Query patterns:
# Handle + quoted text:
from:<handle> "<exact quote fragment>"
# Quoted text only:
"<exact quote fragment>"
# Original of a retweet:
"<exact quote>" -is:retweetOnce a candidate is found:
https://x.com/<handle>/status/<tweet_id>.Replace the broken citation with a proper one:
Before:
"<quote fragment>" [Source: <some hand-wavy attribution>]After:
"<full verified quote>" — <N> likes, <N> RTs, <N> impressions
[Source: [X/<handle>, YYYY-MM-DD](https://x.com/<handle>/status/<tweet_id>)]When sweeping many pages:
# Pages mentioning tweets but with no x.com links
for f in $(find . -name "*.md" -not -path "./node_modules/*"); do
refs=$(grep -ci "tweet\|posted\|x post\|RT\|retweet\|said on X" "$f")
links=$(grep -c "x.com/.*/status/" "$f")
if [ "$refs" -gt 2 ] && [ "$links" -eq 0 ]; then
echo "$f"
fi
doneCitation Audit Report
=====================
Pages scanned: N
Citations found: N
Issues fixed: N
Tweet links resolved: N
Remaining gaps: N (pages with uncitable facts)Follow the agent operator protocol for any gbrain error code, exit code, [AGENT] block or notice block. Specific to this skill:
put_page returns revision_conflict mid-batch: re-read that page, re-apply only the citation fix, and continue; never overwrite with the copy you read earlier.get_page returns page_not_found for a cited source: mark the citation unresolvable in the report instead of rewriting it to a guessed slug.conventions/test-before-bulk.md).This skill can be called:
enrich or media-ingest can call citation-fixer
before commit to validate outputIf running as a recurring batch, track state in a small JSON file under
~/.gbrain/citation-fixer-state.json:
{
"last_run": "2026-04-15T...",
"pages_scanned": 0,
"citations_fixed": 0,
"tweet_links_resolved": 0,
"citations_unresolvable": 0,
"pages_remaining": 1424
}The skill's output shape is documented inline in the body sections above (see "Output", "Brain page format", or equivalent). The literal section header here exists for the conformance test (test/skills-conformance.test.ts).
garrytan/gbrain
f4d1866
Canonical home
since Jul 24, 2026
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.