Skip to content
All tags

#skills

10 posts

Hooks, Skills, Plugins: The Three-Layer Extension System of Mature Coding Agents

Hooks govern control flow, skills inject knowledge, and plugins package both. looplane now has opt-in deny-only project hooks, a bounded SKILL.md loader, exact enabled_skills selection, plugin manifests/install/list, and external-runtime projection. Input rewriting, full lifecycle coverage, remote registries, and a mature marketplace remain open.

Looplane Skills, Blocking Hooks, and Plugin Packages

Looplane treats skills as bounded repository-local guidance, hooks as opt-in host commands that can only deny, and local plugin manifests as packages for skills and hooks; their authority is deliberately different.

ai deep-dive

How Agents Accumulate Team Judgment: Warp's Skill Feedback Loop

Warp's self-improving agent pattern is not about dumping every mistake into a prompt. A base skill does the work, humans leave feedback in GitHub or Slack, an improver skill turns repeated signals into a small diff, and humans review the PR before the next run inherits it.

Memory and Skills in Hermes Agent: A System That Rewrites Itself, and Where You Can Intervene

Hermes memory has hard caps: 2,200 characters for MEMORY.md and 1,375 for USER.md, and an over-limit write returns an error instead of auto-compacting, forcing the agent to make room itself. Skills are maintained by a curator that runs every 7 days after 2 hours of idle, marks skills stale at 30 days and archives at 90 — but never deletes. The switches actually worth flipping are `memory.write_approval` and `skills.write_approval`, which stage the background self-improvement writes for review.

ai deep-dive

Assembling LLM Agent Skills / Tools / Code Interpreter for Real: A Paper Reading Map

The hard part of LLM agents is not building function calling, skills, code interpreter, and document tools individually -- it is assembling them into a system that selects the right tool, writes code when needed, decomposes tasks, verifies results, and resists prompt injection. This post organizes the key papers into six engineering decisions: function calling reliability, tool/skill selection, code-as-action, multi-step planning, skill systems, and safety plus document generation.

tech guide

Where Should AI Agent Global Skills Live? The Division of Labor Between .claude, Codex Skills, and AGENTS.md

Skill paths are almost always runtime-specific. AGENTS.md is the reliable way to share rules across agents. Put personal reusable capabilities in each agent's supported global directory; put project workflows inside the repo.

tech guide

gstack — Garry Tan's 20 Skills That Turn Claude Code into a Virtual Engineering Team

gstack is Garry Tan's open-source Claude Code skills toolkit. Its 20 specialized skills transform a solo developer into an entire engineering team — automating everything from product planning and design review to code review, QA, and deployment.

OpenClaw Tools, Part 2: Six Layers of Skill Precedence, and Why Sub-Agents Get No Message Tool

Skills load from six sources with the highest precedence winning on name collisions, and a per-agent list replaces rather than merges. Sub-agents get no session or message tools by default — they return plain text to the parent, and the right to speak to a human stays with the parent agent.

Claude Code Plugins & Marketplaces: Packaging Skills, Hooks, and MCP into One Installable Unit

Plugins add distribution, not new capabilities: they collect skills, agents, hooks, and MCP settings scattered across .claude/ into one manifest-backed directory that marketplaces can install, update, and version-pin. This post covers plugin structure, the minimal build flow, publishing a marketplace, and dependency version constraints.

Claude Code Global Skills Not Found in New Sessions? Understanding Skill Discovery and How to Debug It

Global skills live in ~/.claude/skills/, but they go missing in new sessions or the Desktop App? The problem usually isn't a missing file — it's that the skill descriptions aren't being loaded into context. This post clarifies the CLI vs Desktop App differences, the role of settings.json, and the most reliable fix.