Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

aminer-rec5 — measured AI agent skill | DecimalAI

tlysanhuo/aminer-rec5

NewSkillScoreMaintained

OpenClaw personalized paper recommendation skill. When the user invokes /aminer-rec5 or /skill aminer-rec5 in Feishu, immediately run the local pipeline under {baseDir}/scripts/, accept aminer_user_id, scholar hints, seed paper titles, papers_file, or free-form topic text, build a unified ResearchProfile, retrieve papers, enrich with AMiner, dispatch Feishu cards, and return NO_REPLY.

researchby tlysanhuo

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/tlysanhuo-aminer-rec5/SKILL.md

decimalai skills pull tlysanhuo-aminer-rec5 --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/tlysanhuo-aminer-rec5/SKILL.md https://app.decimal.ai/s/tlysanhuo-aminer-rec5/SKILL.md

Raw file: /s/tlysanhuo-aminer-rec5/SKILL.md ↗ · machine-readable summary at /s/tlysanhuo-aminer-rec5.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 4h ago

—+0% tokens0% turns77% of whole cases pass with skill (17/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-13	✗→✓	▲ Improved	5%	0%
case-04	✗→✓	▲ Improved	84%	0%
case-08	✗→✓	▲ Improved	-28%	0%
case-09	✗→✓	▲ Improved	32%	0%
case-10	✗→✓	▲ Improved	19%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

tlysanhuo / aminer-daily-paper

SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 22 files · scripts

Skill contents

scripts/

SKILL.md

aminer-rec5

Use this skill only for explicit /aminer-rec5 or /skill aminer-rec5 requests.

Contract

Every explicit invocation is a new run.
Do not answer with status-only text.
Do not search, install, or repair skills.
After running handle_trigger.py, check final_response in the JSON output:
NO_REPLY → Feishu cards were dispatched successfully. Return exactly NO_REPLY.
TEXT → No Feishu target available. Present the reply_text value directly to the user.
Any error → Report the reply_text or error detail to the user.

Inputs

aminer_user_id
scholar / name
org
papers
papers_file
topics
language_sort: zh or en — filter results by paper language
start_year: minimum publication year (e.g. 2023)
end_year: maximum publication year (e.g. 2026)
free-form natural-language interest description

Execution

bash
python3 "{baseDir}/scripts/handle_trigger.py" \
  --base-dir "{baseDir}" \
  --text "<original Feishu message>"

handle_trigger.py is the only supported entrypoint.

Examples

/aminer-rec5 topics: multimodal agents, tool use
/aminer-rec5 topics: LLM reasoning language_sort: en start_year: 2024
/aminer-rec5 scholar: Jie Tang org: Tsinghua University papers: OAG-Bench
/aminer-rec5 aminer_user_id: 696259801cb939bc391d3a37 topics: multimodal

Want to see if tlysanhuo/aminer-rec5 would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.