productivity by ellmos-ai
Hackathon-Operator ellmos-ai/hackathon-operator
Führt einen Hackathon end-to-end als Operator: von der Ausschreibung über Analyse, Ideenfindung, Bau, Beweisführung, Medienproduktion bis zur Einreichung — mit Zwischenstandsspeicher (STATE.md), aus dem jede Phase wieder aufgenommen werden kann. Der Nutzer ist human-in-the-loop: Richtungsvorgaben, Abnahmen und alle unumkehrbaren Aktionen (Public, Upload, Submit) bleiben beim Menschen.
Install linked skill Links this skill to your agents and keeps it current with the author's updates.
Fork editable copy Install locally · CLI or SKILL.md 1 · One-time — install the CLI (
docs ↗ )
$ pip install decimalaiCopy
2 · Get the skill — writes .claude/skills/ellmos-ai-hackathon-operator/SKILL.md
$ decimalai skills pull ellmos-ai-hackathon-operator --out .claude/skills/Copy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/ellmos-ai-hackathon-operator/SKILL.md https://app.decimal.ai/s/ellmos-ai-hackathon-operator/SKILL.mdCopy
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
Benchmark snapshot Same tasks, with and without this skill.
View full report → Model gemini-3.6-flashMeasured 8/6/2026 v1
Pass-rate lift +41 pp percentage-point change
Pass rate with skill 68% 27% without skill
Tokens +86% vs. without skill
Agent turns 0% vs. without skill Usage All-time distinct users and times used, across every version.
View activity → Read the skill SKILL.md · instructions and conventions
Open contents → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported License MITImported 8/2/2026Version v1