aiagents skills

57 tagged aiagents, measured the same way as everything else here.

Browse within: agents 35function-calling 20agentic-ai 16bun 16conversational-ai 16deno 16Reasoning 13agentic-workflow 13astro 13claude-code-plugin 13codeintelligence 13decision-making 13devtools 13multi-agent-systems 13

composio

01

ComposioHQ/composio

Skill Claude CodeCodex

Route and complete Composio work across Composio For You and Composio Platform. Use when the user mentions Composio; wants an agent to use apps such as Gmail, Slack, GitHub, Notion, Calendar, or Linear; needs first-time setup, an SDK or MCP integration, CLI operation, migration guidance, current documentation, or help…

not rated 31k +80 yesterday A Socket: passSnyk: warnSkillSpector: pass 84 tokens original MIT

pdf-processing

02

MervinPraison/PraisonAI

Skill Claude CodeCodex

Process and extract information from PDF documents. Use this skill when the user asks to read, analyze, or extract data from PDF files.

not rated 9.2k +33 yesterday A SkillSpector: pass 30 tokens original MIT

skill-creator

03

luongnv89/asm

Skill Claude Code

Create a skill or bring an existing one up to the same standard (validate + asm eval fix loop); run evals, tune triggering. Use when authoring, fixing, or retrofitting a skill. Don't use for invoking skills, writing prose, or Python scaffolds.

not rated 956 +2 changed 9d ago A SkillSpector: warn 60 tokens original MIT

ahmadvh/octochains

Skill Claude CodeCodex

Analyzes authentication and authorization events for failed-login clustering, privilege-escalation chains, credential-stuffing patterns, and MFA-bypass indicators.

not rated 377 +2 1mo ago A 35 tokens

EpicStaff/EpicStaff

Skill Claude CodeCodex

Use when designing the variables namespace for an EpicStaff flow, translating business requirements into node graph contracts, or deciding which node type fits a responsibility.

not rated 359 changed 1mo ago A 37 tokens

flywheel

06

veryfront/veryfront-code

Skill Claude CodeCodex

Development flywheel - autonomous cycle of run, observe, fix, verify. Use for continuous development with browser automation.

not rated 19 yesterday A SkillSpector: pass 26 tokens original Apache-2.0

vidursharma202-del/threadline-mcp

Skill Claude CodeCodex

Your AI agents start from zero every session — users repeat themselves endlessly. Threadline fixes this in 2 lines. inject() before your LLM call, update() after. Persistent context across every session, model, and product. Structured extraction across 7 scopes. OAuth-style grant system so agents only see permitted…

not rated 0 4mo ago A 137 tokens

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: