Ihor Orlovskyi 3eeb5e7578 Fix scope-triage Snyk W007 wording (#24)
The skills.sh Snyk audit still returned W007 (high) on scope-triage 1.0.1: Step 0
and Route A asked the model to repeat the literal values, names, and numbers from
the request, and the secrets carve-out sat in a following paragraph, so the audit
read the instruction as forcing the model to echo user-supplied secrets verbatim.

Both places now ask for the request's domain values, the prohibition on
reproducing a secret, token, key, password, connection string, or personal datum
leads its own paragraph, and credentials are referenced by placeholder name in
the done criterion, in every command, and in the Security Model. No workflow
change; scope-triage 1.0.1 -> 1.0.2, release 1.9.1.
2026-08-09 03:03:53 +03:00
2026-07-05 21:21:01 +03:00

Agent Skills

A collection of agent skills for Claude Code and other AI coding agents.

Skills

Skill Skill Version Release Description
scope-triage 1.0.2 v1.9.1 Classify request scope before design work, then route to direct implementation, a light spec, or a full design cycle.
plan-crafting 1.1.1 v1.9.0 Turn an approved design or settled requirements into a bite-sized, TDD-oriented implementation plan.
vitest 1.2.0 v1.9.0 Configure, write, debug, run, migrate, and audit Vitest tests for JavaScript/TypeScript projects.
typescript 1.3.1 v1.9.0 Configure tsconfig, diagnose compiler behavior, and audit or migrate TypeScript projects.
web-debug 1.3.1 v1.9.0 Debug and verify local web apps via Playwright.
echarts 1.1.1 v1.9.0 Build, audit, style, debug, and optimize Apache ECharts visualizations in vanilla JS, React, or Vue.

Install

npx skills add sentimony/skills -s scope-triage -a codex claude-code -y
npx skills add sentimony/skills -s plan-crafting -a codex claude-code -y
npx skills add sentimony/skills -s vitest -a codex claude-code -y
npx skills add sentimony/skills -s typescript -a codex claude-code -y
npx skills add sentimony/skills -s web-debug -a codex claude-code -y
npx skills add sentimony/skills -s echarts -a codex claude-code -y

scope-triage and plan-crafting are the two halves of one workflow: scope triage writes an approved design to docs/specs/, then plan crafting turns it into a plan in docs/plans/.

scope-triage is a scope-gated fork of obra/superpowers brainstorming and is meant to replace it — install one or the other, not both. Installed on its own it activates on 10/10 design requests and stays out of 10/10 mechanical or read-only ones; installed alongside upstream brainstorming, the upstream skill's broader trigger wins most design requests and this skill fires on only 2 of 10. plan-crafting replaces upstream writing-plans the same way — install one planning skill, not both.

Have fun ;)

S
Description
echarts: You MUST use this when building, styling, debugging, or optimizing Apache ECharts charts in JavaScript, React, or Vue - setup, lifecycle, responsive resizing,…; web-debug: You MUST use this when interacting with or testing local web applications with Playwright - verifying frontend functionality, debugging UI behavior, capturing…; typescript: You MUST use this when configuring tsconfig, resolving compiler errors, debugging slow type-checking, fixing module resolution or ESM/CJS issues,…
Readme 1.1 MiB
Languages
Python 98.2%
Shell 0.6%
TypeScript 0.5%
HTML 0.4%
Vue 0.3%