Agents
Why Implexa
Pricing
Resources
Install
Sign in
Sign up
back to leaderboard
AG
@agentsope
contributor on implexa, with 10 skills ranked by
SkillRank
across 1 source.
agentsope on github
publishes to clawhub
skills, ranked by SkillRank
score
source
skill
8.1
clawhub
Agentsop Aider
agentsop-aider documents terminal-based git-native code editing via LLM using aider, covering repo-map context prioritization, edit format selection per model, per-edit commits with rollback via /undo, and human-in-loop REPL patterns for converging changes across 2-5 files.
7.8
clawhub
Agentsop Conventions Pinning
agentsop-conventions-pinning covers writing and loading project-level convention files so coder-agents respect style choices consistently. addresses four tool-specific load mechanics, conflict precedence, and a phased sop from initial decision through evolution.
7.2
clawhub
Agentsop Agent Topology Selection
agentsop-agent-topology-selection encodes a three-question rubric for deciding whether to split work across multiple agents or keep a single agent with tools. it surfaces the trade-offs (context isolation, parallel expertise, supervision model) that framework docs assume but leave implicit.
6.1
clawhub
Agentsop Crewai
agentsop-crewai documents multi-agent orchestration using role-based teams, sequential and hierarchical processes, flows, and memory. detailed model covers agent design, task decomposition, and process selection with explicit guidance on when to use alternatives like langgraph or autogen.
—
clawhub
Agentsop Bio Fraud Forensics
Screens biomedical / life-science papers for signs of data fabrication, image manipulation, and statistical anomalies, using the detection techniques distill...
—
clawhub
Agentsop Bounded Loop
Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix cycles. Encodes the one rule...
—
clawhub
Agentsop Code Execution Decision
Decision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus reason in natural language: classify each step...
—
clawhub
Skill Alchemy Main
SkillAlchemy — 一念落地,万象成形。输入任意想法或蒸馏目标,输出可安装的 SKILL.md。 内部编排 Lens(看清问题)和 LEAP(执行蒸馏/融合)。用户唯一入口。 Use when 用户说「蒸馏」「生成 skill」「融合」「我想做 X 但不知道从哪下手」。
—
clawhub
Agentsop Context Scope Discipline
Coder-agent working-file budget discipline: keep the editable working set (files you /add into writable context) under ~25k tokens, separate "read" from "edi...
—
clawhub
Agentsop Cost Tiered Models
Split a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions and a cheap model do the many mechan...
agentsope (10 skills ranked by SkillRank) | implexa