brycewang-stanford/lfg
SkillScore50MaintainedFull autonomous research workflow — brainstorm, plan, implement, review, and document
by brycewang-stanford
Links this skill to your agents and keeps it current with the author’s updates.
On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.
◆Coding pack
$decimalai skills pull brycewang-stanford-lfg
Get this skill — curl · raw file
$curl -fsSL https://app.decimal.ai/s/brycewang-stanford-lfg/SKILL.md
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 42h ago
—-21% tokens0% turns50% of whole cases pass with skill (11/22)
Showing 5 of 22 cases
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026
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
Importedbrycewang-stanford / Auto-Empirical-Research-Skills
skills/11-James-Traina-compound-science/skills/lfg/SKILL.md
License NOASSERTIONImported 8/2/2026Version v1
Run these 5 slash commands in order. Do not do anything else. Do not stop between steps — complete every step through to the end.
/workflows:brainstorm $ARGUMENTS/workflows:plan/workflows:work/workflows:review/workflows:compound
Hard gates:
- Step 2 must not start until step 1 has written a file to
docs/brainstorms/. If brainstorm produced no file, stop and report. - Step 3 must not start until step 2 has written a file to
docs/plans/. If plan produced no file, stop and report. - Steps 4 and 5 run on whatever step 3 produced. A failed review does not block compound.
Start with step 1 now.
Want to see if brycewang-stanford/lfg would activate on your phrasing? Try it before you install — no LLM call, no signup.