Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nousresearch/grounded-citations
Ground answers and documents in cited, verifiable sources.
Passed 16 of 21 test cases with the skill, and 8 of 21 without it.
and 7 more in the full report
10 fixed8 passed either way5 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Where does sources.py store its default ledger file on disk when no override flags or environment variables are set?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies $HERMES_HOME/cache/citations/ledger.json as the default ledger path. | Missed | Passed |
The instructions your model reads when the skill loads.
Every claim taken from an outside source gets an inline numbered citation and a
Sources: list, Perplexity-style. A ledger script owns the url → [n] mapping
so the numbers and URLs come from retrieval, never from memory — the model only
ever emits small integers it was handed.
For high-stakes work the same ledger doubles as a fact-checking chain: verbatim
quotes are attached to each source (rejected unless they literally appear in
the fetched page text), claims from model knowledge are flagged [unverified],
and verify --evidence fails any draft whose cited sources carry no evidence.
This skill covers answers in chat, written documents (markdown, PDF, docx,
slides), and research reports. It does not cover academic BibTeX pipelines —
for conference papers use the research-paper-writing skill, which this skill
feeds (see references/citation-formats.md).
Use whenever an answer or artifact rests on information you fetched rather than knew:
Skip inline citations when the retrieval is incidental to another task — a quick syntax/version lookup mid-coding, casual conversation, creative writing. Mention a URL only if the user would plausibly want the link.
None beyond the standard toolset. scripts/sources.py is stdlib-only Python 3.
Retrieval comes from whatever is configured: web_search, web_extract,
browser_navigate, or terminal (curl, CLIs).
Ledger location: $HERMES_HOME/cache/citations/ledger.json (profile-aware).
Override per task with --ledger <path> or HERMES_CITATION_LEDGER.
test cases passed, vs 8 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.