agent-skills

agent-skills copied to clipboard

fix(hooks): resolve security eval and session-start output schema

1

## Summary Fixes two issues surfaced in #106 and #110. ### Fix #106 — eval injection vector in simplify-ignore-test.sh (Critical) `eval "$(sed -n '/^filter_file()/,/^}/p' hooks/simplify-ignore.sh)"` extracted and eval'd a function...

googlarz

Fixes https://github.com/addyosmani/agent-skills/issues/112 ## Summary All 21 skills return `Unknown skill` when invoked via the Skill tool despite the plugin being enabled. ## Root cause `.claude-plugin/plugin.json` declares `"commands"` but omits `"skills"`...

creazyfrog

## Summary When `agent-skills@addy-agent-skills` plugin is enabled in Claude Code, the **Skill tool fails to invoke any of the 21 skills** in `skills/` (and 3 sub-agents in `agents/`). Calling `Skill:...

ariada-ai

SessionStart hook silently fails: invalid JSON format + Claude Code Bug #16538 — with fix and smart loading proposal

2

## Problem The `session-start.sh` hook produces **zero visible output** in Claude Code sessions, even though the script executes successfully. The meta-skill `using-agent-skills` is silently discarded on every session start. ##...

wasikarn

## Summary Adds Common Rationalizations tables and Verification checklists to the three agent definitions, mirroring the skill anatomy guardrails. Fixes #17. ## Changes - Add rationalizations + verification to code-reviewer,...

zerone0x

## Summary - Add `references/docker-compose-checklist.md` — a standalone checklist covering the most common Docker Compose deployment pitfalls: naming stability, image tag pinning, secret injection, named volumes, network isolation, health checks,...

kirisame-wang

ZuoFuhong

Hi — while running an automated NL-quality audit on this repository ([NLPM](https://github.com/xiaolai/nlpm-for-claude)), the security pre-scan flagged a few patterns in the hooks directory that seemed worth surfacing. Treating this as...

xiaolai

giuseppecrj

# Proposal: systems-engineering-traceability skill for agent-generated code ## Summary I would like to propose a focused new skill: `systems-engineering-traceability`. The skill would add a lightweight traceability workflow for agent-generated behavior....

jjziets