agentleFS
htlin222htlin222/openevidence-mcp/openevidence-skill/SKILL.md

openevidence

Skill83 starsChanged 3 days agoApache-2.0View on GitHub

Query OpenEvidence (clinical evidence assistant) without an MCP server. Closely mirrors the openevidence-mcp tool surface - check auth, list question history, fetch an article, or ask a new question (with optional follow-up thread). Use when the user asks medical / evidence-based clinical questions, references OpenEvidence, asks for "OE answers", or wants citations + BibTeX from OpenEvidence. Portable to claude.ai's /mnt sandbox - just drop the folder and a fresh cookies.json next to scripts/oe.py.

  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. htlin222/openevidence-skill★ 17same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    Place a fresh cookies.json at /mnt/user-data/openevidence-skill/cookies.json (the file is gitignored - do not commit it back).

    line 85

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

OpenEvidence (portable)

A stdlib-only Python port of openevidence-mcp. One CLI (scripts/oe.py) with four subcommands matching the MCP tools.

MCP toolSkill commandPurpose
oe_auth_statuspython3 scripts/oe.py auth-statusConfirm cookies.json still authenticates /api/auth/me
oe_history_listpython3 scripts/oe.py historyPaginated question history with optional search
oe_article_getpython3 scripts/oe.py article <uuid>Fetch an article, extract answer + figures, save artifacts
oe_askpython3 scripts/oe.py ask "<question>"Submit a new question, optionally wait, save artifacts

Output of every command is a single JSON object on stdout - same shape the MCP returns to its client.

Setup (one time)

  1. Cookies. Export the OpenEvidence cookies from a logged-in browser tab (e.g. "Cookie-Editor" extension → "Export → JSON"). Save as cookies.json next to this SKILL.md. The format is either a flat array of cookie objects or { "cookies": [...] } (Playwright storage state). The file is gitignored.
  2. Verify. python3 scripts/oe.py auth-status should print "authenticated": true. Status 401/403 means the cookies expired - re-export.

Cookie lookup order: $OE_COOKIES, ./cookies.json, the skill folder, ~/.openevidence/cookies.json.

Common workflows

Ask a question, wait for completion, save artifacts (the default):

python3 scripts/oe.py ask "First-line therapy for adult community-acquired pneumonia in a hospitalized patient"

Note: behavior differs from the MCP tool. The MCP oe_ask is now fire-and-forget by default (returns a pending article_id; pass wait_for_completion:true to block, or fetch later via oe_article_get). THIS portable CLI waits by default — override with --no-wait.

Returns { article_id, status, extracted_answer_raw, figures, artifacts }. Artifacts land in $OE_ARTIFACT_DIR or ./oe-artifacts/<article_id>/ and include:

  • answer.md - markdown answer with <visual> tags resolved to ![alt](url)
  • article.json - raw API payload
  • citations.json - normalized citations with optional Crossref validation
  • citations.bib - BibTeX, Crossref-augmented when matched
  • crossref-validation.json - per-citation validation summary
  • figures.json + figures/ - figure metadata and downloaded images

Follow-up in the same thread (use the article_id you got back):

python3 scripts/oe.py ask "What if the patient has a beta-lactam allergy?" --follow-up <uuid>

Re-fetch / re-save an existing article:

python3 scripts/oe.py article <uuid>

Browse history:

python3 scripts/oe.py history --limit 20 --search "pneumonia"

Useful flags

  • --no-wait (ask): return immediately after creating the article; poll later with article <id>.
  • --timeout 240 --poll-interval-ms 1500 (ask): tune polling for long-running answers.
  • --no-save: skip artifact writes (response only).
  • --no-crossref: skip Crossref DOI validation (faster; offline-friendly).
  • --no-bibtex: drop bibtex from the response (still written to citations.bib).
  • --mailto you@example.com (or OE_CROSSREF_MAILTO): use Crossref polite pool.
  • --disable-caching, --personalization, --article-type, --variant: pass-through to the OpenEvidence /api/article request.

Environment overrides

VariableDefault
OE_BASE_URLhttps://www.openevidence.com
OE_COOKIES(lookup order above)
OE_ARTIFACT_DIR./oe-artifacts
OE_CROSSREF_MAILTOunset

Using this skill in claude.ai's /mnt sandbox

  1. Upload (or copy) the openevidence-skill/ folder into /mnt/user-data/openevidence-skill/.
  2. Place a fresh cookies.json at /mnt/user-data/openevidence-skill/cookies.json (the file is gitignored - do not commit it back).
  3. Invoke via Bash, e.g. python3 /mnt/user-data/openevidence-skill/scripts/oe.py ask "...".

The script needs only Python 3.10+ stdlib (no pip install). All artifacts stay inside the sandbox under ./oe-artifacts/ unless OE_ARTIFACT_DIR overrides.

Troubleshooting

  • cookies.json not found → export cookies and place beside SKILL.md, or set $OE_COOKIES.
  • "authenticated": false with status 401/403 → cookies expired; re-export.
  • OpenEvidence returned no article id → API rejected the question payload (try shorter prompt or different --variant).
  • Figures fail to download → individual download errors are swallowed; figures.json still records the URLs.

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.