hamzabellouch/agent-skills

Comprehensive collection of 850+ production-ready Agent Skills across 9 core pillars (58 domains) conforming to the Agent Skills Standard, featuring native auto-discovery for Antigravity, Claude Code, Gemini CLI, Cursor, and Codex.

8Stars on the repository
378Mods indexed here, across every type
4d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

eic_agent

04

hamzabellouch/agent-skills

Agent Claude Code

Editor-in-Chief; orchestrates the review panel and delivers the final editorial decision.

not rated 8 4d ago A 19 tokens copy · 83% MIT

field_analyst_agent

05

hamzabellouch/agent-skills

Agent Claude Code

Identifies the papers field and dynamically configures the reviewer teams identities and expertise.

not rated 8 4d ago A 21 tokens copy · 89% MIT

draft_writer_agent

11

hamzabellouch/agent-skills

Agent Claude Code

Writes the full paper draft section by section from the structured outline and Paper Configuration Record.

not rated 8 4d ago A 20 tokens original MIT

intake_agent

13

hamzabellouch/agent-skills

Agent Claude Code

Conducts the paper configuration interview and produces the Paper Configuration Record for downstream agents.

not rated 8 4d ago A 19 tokens original MIT

hamzabellouch/agent-skills

Agent Claude Code

Guides paper authors through Socratic questions to sharpen arguments and surface unstated assumptions.

not rated 8 4d ago A 23 tokens original MIT

visualization_agent

19

hamzabellouch/agent-skills

Agent Claude Code

Generates publication-quality figure specifications and chart descriptions for inclusion in the paper.

not rated 8 4d ago A 18 tokens copy · 83% MIT

hamzabellouch/agent-skills

Agent Claude Code

L3 claim-faithfulness audit — judges every cited claim against the retrieved reference text, surfaces uncited assertions and constraint violations, and feeds the Stage 4→5 formatter hard gate.

not rated 8 4d ago A 44 tokens original MIT

hamzabellouch/agent-skills

Agent Claude Code

Post-hoc observer scoring user-AI collaboration depth against the canonical rubric; advisory-only, never blocks pipeline progression.

not rated 8 4d ago A 27 tokens copy · 92% MIT

state_tracker_agent

24

hamzabellouch/agent-skills

Agent Claude Code

Tracks pipeline state and maintains the research session history across multi-phase workflows.

not rated 8 4d ago A 17 tokens copy · 89% MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: