agentic-search SKILL.md skillA
agentic-search from alibaba-damo-academy/scholarseed is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add alibaba-damo-academy/scholarseed/agentic-search@v1.1.8Pins v1.1.8 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- alibaba-damo-academy/scholarseed
- Path
skills/community/agentic-search/SKILL.md- Versions recorded
- 2
- Latest version
- v1.1.8, committed Nov 3, 2026
- First version recorded
- Sep 22, 2026
- Size
- 11,799 bytes
- Repository stars
- 37
- License
- Apache-2.0
Tiered academic paper discovery for quick search-bar lookup, balanced interactive research, or maximum-quality multi-round retrieval. Infer hidden entities, search PaperHub with keyword/title/citation paths, optionally use public web evidence, and return a precision-first tiered metadata set. Use for natural-language research needs that ask to find relevant papers, including requests with a time budget or speed/quality preference.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Agentic Literature Search
Return relevant papers in `metadata.json`. Do not generate a narrative report
unless the user explicitly asks for one.
For a standalone conversation search, after producing real non-empty `metadata.json`, publish the result with
`scholarseed-bridge literature result --json '{"run":"RESULT_DIR","checkpoint":"metadata","skill":"agentic-search"}'`,
replacing RESULT_DIR with the session-relative result directory. This displays the host's
conversation component and the host's full-result actions; it does not authorize full-text access.
The dedicated search-bar invocation owns its result tab and does not need this conversation call.
When invoked by another research Skill, leave publication to that parent's checkpoint
(for example research-idea-partner's candidates or literature-review's retrieval); do not publish twice.
Never invent papers to obtain a card; report an empty or blocked search as such.
## Select one mode
An explicit user mode wins. Otherwise infer from `time_budget_minutes`; with
neither, use Quality.
| Mode | Product target | Time target | Papers | Execution graph |
|---|---|---:|---:|---|
…Read the whole file at its exact version.
How to install
mdr add alibaba-damo-academy/scholarseed/agentic-search@sha256:beee7bb4149eb4c4The line at the top of this page pins the label v1.1.8, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_4cquej5ei7vwcc7c)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 22, 2026 and Nov 3, 2026, about one every 42 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.8 latest | 2026-11-03 | d1437c6 | 11,799 B | A | view · diff |
| v1.1.0 | 2026-09-22 | 483c35d | 10,781 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11799 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
alibaba-damo-academy/scholarseed · 37 stars · license Apache-2.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_4cquej5ei7vwcc7c GET https://markdownregistry.com/api/v1/resolve?ref=alibaba-damo-academy/scholarseed/agentic-search GET https://markdownregistry.com/api/v1/blob/beee7bb4149eb4c497de739e4e7e95bdb37c11598f43a6a336ba4785692c9684
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.