Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add j4rk0r/claude-skills --skill skill-advisorgit clone --depth 1 https://github.com/j4rk0r/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/j4rk0r/claude-skills/skill-advisor)<a href="https://agentmods.dev/skills/j4rk0r/claude-skills/skill-advisor"><img src="https://agentmods.dev/badge/skills/j4rk0r/claude-skills/skill-advisor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/j4rk0r/claude-skills/skill-advisor"><img src="https://agentmods.dev/badge/skills/j4rk0r/claude-skills/skill-advisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00100 | $0.02014 |
| Opus 5 | $0.00050 | $0.01007 |
| Sonnet 5 | $0.00020 | $0.00403 |
| Haiku 4.5 | $0.00010 | $0.00201 |
Grade B, and why
skill-advisor scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
2. Run `ls ~/.claude/skills/` and `ls .claude/skills/` How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Advisor
You are the routing brain for the user's skill ecosystem. For every task, you build the IDEAL execution plan — what they have AND what they're missing — so they can make an informed choice before starting.
How to Think About Recommendations
Before presenting any plan, ask yourself these three questions:
1. "What professionals would you hire for this project in the real world?" Designer, copywriter, SEO specialist, data analyst, QA engineer... Each role that has no matching installed skill = ❌ gap.
2. "Where does this project lose money or users if done with code alone?" No SEO = invisible. No analytics = blind. No copywriting = doesn't convert. No performance = users leave. These are the CRITICAL gaps.
3. "What would a product owner demand that a developer would forget?" Developers think in features. Product owners think in outcomes: conversion, retention, discoverability, compliance. The gaps live in this delta.
Output Format — The Only Acceptable Format
MANDATORY: Every recommendation uses this numbered plan with ✅/❌/⚡ markers.
A bullet list of installed skills is NEVER acceptable. The plan must interleave installed and missing skills in execution order.
Concrete Example: user says "quiero hacer una web"
## Plan de ejecución completo
1. ✅ /brainstorming — definir tipo de web, audiencia, objetivos
2. ✅ /writing-plans — planificar implementación paso a paso
3. ✅ /design-system-starter — tokens de diseño y sistema de componentes
4. ❌ Copywriting — textos, headlines y CTAs definen la conversión de tu web
5. ❌ SEO — sin SEO desde el inicio, la web será invisible para buscadores
6. ✅ /frontend-design — implementar interfaces production-grade
7. ✅ /animate — micro-interacciones y transiciones
8. ✅ /web-design-guidelines — verificar accesibilidad y buenas prácticas
9. ❌ Analytics — sin medición no sabrás si la web cumple sus objetivos
10. ❌ Performance — velocidad de carga impacta en SEO y retención
11. ✅ /verification-before-completion — verificar que todo funciona
12. ✅ /commit-work — commit limpio y documentado
---
Instaladas listas: 1, 2, 3, 6, 7, 8, 11, 12
Por instalar (recomendado): 4, 5, 9, 10
¿Qué prefieres?
- **"instalar todas"** — busco e instalo los gaps uno a uno
- **"empezar"** — arrancamos solo con las instaladas
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 177 lines · 100 tokens per session scan B 7b78ba133036
skill-advisor is a skill published in the GitHub repository j4rk0r/claude-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 2,014 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
stuck
Diagnoses a broken course setup by reading the folder, so the student never has to describe the problem in English. Takes no argument. Reports which class they are on and which files are filled, then names one blocker and one fix: Claude Code opened at the wrong level, .claude/skills/ missing, skills not loading…
grill-me
Two modes, picked from the file you point it at. Contract mode grills a claude-contract.md line by line until every line is a thing Claude must always do or must never do, editing that file in place and creating nothing new. Brief mode interrogates a design brief until it has no soft spots left, then produces a…
information-architecture
Map the user journey first, then derive the screen inventory, navigation and hierarchy from it, flagging any screen that serves no journey step. Writes the four-part markdown plus an HTML diagram of the step-to-screen mapping. Use after the brief is settled and before tokens or UI.
design-tokens
Establish color, typography, spacing, radius and motion as named role-based tokens. Use before building any interface.
heuristic-evaluation
Audit a design against Nielsen's ten usability heuristics, tying every finding to a specific element with a specific fix. Use on a built screen or a detailed mockup.
persona-acid-test
Stress-test a design through three lenses, confused user, skeptical engineer and impatient PM, before it goes to a stakeholder. Requires an actual design, an HTML file, Figma link or screenshot.