select-venue
Skill59 starsChanged 5 months agoApache-2.0View on GitHub
Builds a ranked venue shortlist for a research paper. Use when the user asks where to submit, which conference or journal to target, venue selection, track selection, or mentions CORE rank, h5-index, acceptance rate, CCF class, or submission deadlines. Maps the paper's topic and contribution type (method, system, dataset, demo, vision, industrial, survey) to venue-track pairs scored on topic fit, track fit, prestige signals, and deadline proximity computed from the machine-readable venues/ profiles — with mandatory re-verification of deadlines and page limits against each live CFP before the user relies on them.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- AfonsoZhang/auto-research-systemedited, first seen Nov 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- AfonsoZhang/auto-research-system★ 159% same
Wrote their own version · 0
None found.
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 repository43 other files it gives its agents.
- docs/llms-full.txtllms.txt
- docs/llms.txtllms.txt
- add-venue-profileSkill
- anonymize-paperSkill
- assess-paperSkill
- benchmark-paperSkill
- check-originalitySkill
- draft-related-workSkill
- draft-surveySkill
- fetch-paperSkill
- find-papersSkill
- fit-page-limitSkill
- literature-reviewSkill
- make-posterSkill
- make-slidesSkill
- match-styleSkill
- orchestrate-paperSkill
- paper-profileSkill
- parse-cfpSkill
- plan-submissionSkill
- polish-proseSkill
- polish-tables-figuresSkill
- preflight-checkSkill
- prepare-artifactsSkill
- prepare-camera-readySkill
- refactor-research-codeSkill
- refactor-structureSkill
- reflect-and-improveSkill
- reflect-paperSkill
- rehearse-qaSkill
- render-workspace-htmlSkill
- simulate-reviewersSkill
- study-exemplarsSkill
- tailor-to-venueSkill
- test-research-codeSkill
- triage-reviewsSkill
- verify-citationsSkill
- verify-claimsSkill
- verify-resultsSkill
- work-with-overleafSkill
- write-abstractSkill
- write-rebuttalSkill
- write-talk-scriptSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
Not for: parsing one specific CFP into a profile (parse-cfp), adapting a draft to an already-chosen venue (tailor-to-venue), or …
- Distinctive: line 44
Survey profiled venues: Run:
- Very specific: line 126
Never fabricate ranks, h5-indexes, acceptance rates, or citations.
- Distinctive: line 128
Never submit to, register with, or create accounts on any submission system on the user's behalf.
≈ “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.
Files
Select Venue
Turn "where should I submit this paper?" into a ranked shortlist of
venue-track pairs with scores, deadlines, page budgets, and an explicit
verification status — grounded in the repo's venues/ profiles, not vibes.
When to use
- The user asks where to submit a paper, for target-venue recommendations, or to compare candidate venues/tracks.
- The user asks "does my paper fit venue X?" or "research track or industry track?"
- The user mentions CORE rank, h5-index, CCF class, acceptance rates, or upcoming CS conference deadlines in a submission-planning context.
Not for: parsing one specific CFP into a profile (parse-cfp), adapting a
draft to an already-chosen venue (tailor-to-venue), or pre-submission
compliance checks (preflight-check).
Inputs
- Topic — one or two sentences on what the paper is about.
- Contribution type — classify using
references/track-fit.md; ask the user if ambiguous. - Constraints — earliest realistic submission date, prestige goals (and whether CCF class matters), page-budget reality of the current draft, blind-level conflicts (e.g. an already-public preprint), travel/registration constraints.
- Venue data —
venues/conferences/*.ymlprofiles (schema invenues/schema.yml), surfaced byscripts/list_venues.py.
Process
- Elicit the inputs. Confirm topic, contribution type, and constraints
in one round of questions. The contribution type changes the shortlist
more than the topic — pin it down first (
references/track-fit.md, "Contribution taxonomy"). Survey profiled venues. Run:
python3 scripts/list_venues.pyThis lists every profile with deadline proximity, blind level, submission system, and per-track page budgets, sorted by next upcoming submission deadline. Useful flags:
--upcoming-only,--family <name>,--track <name>,--json(full data incl. track notes),--today YYYY-MM-DD(reproducible runs). Never compute date arithmetic by hand. Caveat: some venues (e.g. SIGSPATIAL) have per-track deadlines that differ from the top-level ones — they live in each track'snotesfield; read them in the--jsonoutput.Build the candidate set. Combine (a) profiled venues that plausibly match the topic, and (b) venues you know fit the topic but have no profile yet. For unprofiled candidates, resolve identity via DBLP:
CONTACT_EMAIL=you@example.org python3 scripts/dblp_venue_lookup.py search "<venue name>"Optionally gauge venue size with
dblp_venue_lookup.py toc-count <dblp_key> <year>. Mark every unprofiled candidate clearly and suggestparse-cfpto profile it. Aim for 5-10 candidate venue-track pairs before scoring.- Gather prestige signals. For each candidate, look up CORE rank,
h5-index, CCF class (if the user cares), and acceptance rate following
references/ranking-sources.md. Hard rule: every number carries a source + edition/year, or is labeled "unverified — indicative" / "unknown". Never state a rank or acceptance rate from memory as fact, and never invent one. - Score and rank. Apply the 0-10 rubric in
references/track-fit.md(topic fit 0-3, track fit 0-3, prestige fit 0-2, deadline feasibility 0-2), then apply its tie-breakers and red-flag vetoes (embargoes, dual-submission bans, attendance mandates). - Re-verify the top picks against live CFPs — mandatory. For the top
3 venues, fetch each profile's
cfp_urland confirm the facts the user will act on: deadlines (and their timezone — AoE vs PT matters), page limits and what they exclude, blind level, submission system. Profiles are a starting point, never ground truth; a stale page limit causes a desk reject. Record what was verified and when in the output. If a CFP cannot be reached, mark that venue "NOT re-verified" — do not silently present profile data as confirmed. - Deliver the shortlist (format below) and offer next steps:
parse-cfpfor unprofiled picks,tailor-to-venueonce a target is chosen,plan-submissionfor the timeline.
Output
A ranked shortlist in chat (offer to save as venue-shortlist.md):
| # | Venue / track | Score | Deadline (tz) | Pages | Blind | Rank signals | Verified |
| 1 | SIGSPATIAL 2026 / Research | 9/10 | abstract 2026-05-29, paper 2026-06-05 (PT) | 10p excl refs +2p appendix | single | CORE2023 A (verify) | live CFP 2026-06-11 |
Below the table, per venue: 2-4 lines of rationale (the four rubric scores with one-line justifications), the red flags checked, and — for any venue whose deadline has passed — the next expected cycle. Close with the explicit disclaimer that the user must confirm all critical facts on the venue's own CFP page before planning around them.
Bundled resources
references/ranking-sources.md— CORE, h5-index, acceptance rates, CCF, deadline aggregators: where each lives, how to interpret, how to cite.references/track-fit.md— contribution taxonomy, track archetypes, the scoring rubric, tie-breakers, red flags.scripts/list_venues.py— stdlib-only profile lister + deadline math.scripts/dblp_venue_lookup.py— polite DBLP venue resolver (rate-limited ≤1 req/s, cached under.cache/, needsCONTACT_EMAIL).
Guardrails
- Profiles and this skill's tables are never ground truth — re-verify
deadlines, page limits, and policies against the live
cfp_url(step 6) and say so in the output. - Never fabricate ranks, h5-indexes, acceptance rates, or citations; route
any bibliographic citation through
verify-citations. - Never submit to, register with, or create accounts on any submission system on the user's behalf.
- Fetch venue/CFP pages on demand and process them transiently; do not copy paper abstracts or full text into the repo (metadata is fine).
- Prestige caps at 2 of 10 points by design — do not let "it's A*" override fit, and do not present prestige as publication advice ("aim lower/higher") unless the user asked for that judgment.
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
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.

