super-guide

A hands-on guide for learning how a collection of coding-agent skills works. It teaches through the user's own skills and work rather than through abstract examples.

In plain words
What is it for?
Use it to learn a skill pipeline, understand design choices, recover from confusion, and practise using the collection on real tasks.
Why use it?
It helps when you are unsure what to do next, how skills connect, or why a workflow was designed a certain way. It records learning progress so later guidance can be more targeted.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/fagemx/prismstack/super-guide
Any agent
npx skills add fagemx/prismstack --skill super-guide
Clone the repo
git clone --depth 1 https://github.com/fagemx/prismstack

Made for: Claude Code, Codex.

Per session 175 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,676 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00175 $0.05676
Opus 5 $0.00088 $0.02838
Sonnet 5 $0.00035 $0.01135
Haiku 4.5 $0.00017 $0.00568

Measured yesterday against content hash 189af624f5fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

super-guide scanned grade A with 0 findings 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 yesterday.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/super-guide/SKILL.md · 423 lines

How it starts

The opening of the file, as written. The whole thing — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.

超級引導員

你是 Prismstack 的實戰教練。你不解釋理論,你帶人做事。 你的教材不是文件,是用戶自己的 domain stack。


核心原則

  1. 做中學 — 永遠用用戶自己領域的 skill 和 artifact 當例子,不用抽象概念
  2. 推理優先 — 你有思考框架,不靠預寫教案;遇到沒見過的問題,用框架推導答案
  3. 累積進化 — 每次互動後記錄用戶的困惑和突破,下次教學更精準
  4. 不宣告模式 — 自動判斷用戶需要什麼(教學/問答/診斷),自然切換,不說「我現在進入 XX 模式」

Preamble (run first)

# === 標準 Prismstack preamble ===
_SLUG=$(basename "$(git rev-parse --show-toplevel 2>/dev/null || pwd)")
_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
_USER=$(whoami 2>/dev/null || echo "unknown")

mkdir -p ~/.prismstack/projects/$_SLUG
_PROJECTS_DIR=~/.prismstack/projects/$_SLUG

mkdir -p "$_PROJECTS_DIR/.prismstack"
_STATE_DIR="$_PROJECTS_DIR/.prismstack"

# === 引導員專用:學習紀錄 ===
mkdir -p "$_STATE_DIR/guide-logs"
_GUIDE_DIR="$_STATE_DIR/guide-logs"

# 讀取學習紀錄
_HAS_GUIDE_LOG=0
_GUIDE_LOG="$_GUIDE_DIR/learning-profile.json"
[ -f "$_GUIDE_LOG" ] && _HAS_GUIDE_LOG=1

# 掃描用戶的 domain stack
_HAS_SKILL_MAP=0
[ -f "$_STATE_DIR/skill-map.json" ] && _HAS_SKILL_MAP=1
_HAS_DOMAIN_CONFIG=0
[ -f "$_STATE_DIR/domain-config.json" ] && _HAS_DOMAIN_CONFIG=1

# 掃描現有 skill 檔案
_SKILL_FILES=$(find . -path "*/skills/*/SKILL.md" 2>/dev/null | head -20)
_SKILL_COUNT=$(echo "$_SKILL_FILES" | grep -c "SKILL.md" 2>/dev/null || echo "0")

# 掃描 artifact
_ARTIFACT_COUNT=$(ls "$_PROJECTS_DIR"/*.md 2>/dev/null | wc -l | tr -d ' ')

echo "=== Super Guide State ==="
echo "SLUG: $_SLUG"
echo "HAS_SKILL_MAP: $_HAS_SKILL_MAP"
echo "HAS_DOMAIN_CONFIG: $_HAS_DOMAIN_CONFIG"
echo "HAS_GUIDE_LOG: $_HAS_GUIDE_LOG"
echo "SKILL_COUNT: $_SKILL_COUNT"
echo "ARTIFACTS: $_ARTIFACT_COUNT"
[ "$_ARTIFACT_COUNT" -gt 0 ] && ls -t "$_PROJECTS_DIR"/*.md 2>/dev/null | head -5 | while read f; do echo "  $(basename "$f")"; done
[ "$_HAS_GUIDE_LOG" = "1" ] && echo "GUIDE_LOG: exists (will read for personalization)"

Phase 0: 狀態偵測與模式判斷

Step 1: 讀取上下文

  1. 如果 HAS_GUIDE_LOG=1 → 讀 $_GUIDE_LOG,掌握:
    • 用戶之前問過什麼、卡在哪裡
    • 哪些概念已經教過、哪些還沒
    • 用戶的學習風格偏好
  2. 如果 HAS_SKILL_MAP=1 → 讀 skill map,掌握用戶的領域和 skill 全貌
  3. 如果 HAS_DOMAIN_CONFIG=1 → 讀 domain config,掌握累積的 expertise/corrections
  4. 掃描 $_SKILL_FILES → 掌握用戶目前有哪些 skill、結構如何

Read the full file on GitHub · 423 lines

Files

What ships with it

4 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.

Changes

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.

  1. yesterday First seen · 423 lines · 175 tokens per session scan A 189af624f5fc

Subscribe to this mod's changes

super-guide is a skill published in the GitHub repository fagemx/prismstack (2 stars, last pushed 4mo ago), licensed MIT. It adds 175 tokens to every session and 5,676 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

technical-documentation

Audit, write, and improve developer documentation using Google's Developer Documentation Style Guide and Technical Writing courses. Use this skill for any documentation work, even when the user names no style guide: "audit our docs", "review this README", "write a README", "getting started guide", "how-to or…

wondelai/skills · 204 tokens

scorecard-marketing

Build quiz and assessment funnels that generate qualified leads at 30-50% conversion. Use when the user mentions "quiz funnel", "scorecard", "lead magnet", "score-based segmentation", or "lead qualification". Also trigger when designing self-assessment tools, building calculators or graders for marketing, or creating…

wondelai/skills · 113 tokens

ai-hockey-workflow

Teaches how to use Claude and MCP tools effectively for hockey analytics -- exploratory analysis, hypothesis testing, model iteration, and report generation. Use when user asks how to analyze hockey data with AI, how to structure an analysis session, how to test a hypothesis about team or player performance, how to…

PuckAPI/claude-sports-analytics · 116 tokens

hockey-analytics

Teaches hockey analytics metrics -- Corsi, Fenwick, PDO, xG, zone entries, high-danger chances, RAPM, WAR -- with real data context. Use when user asks what Corsi means, how to interpret PDO, what xG tells you, why Fenwick matters, or asks to explain advanced stats for a team or player. Do not use for betting concepts…

PuckAPI/claude-sports-analytics · 107 tokens

feature-radar-archive

Archive a completed, rejected, or covered feature into .feature-radar/archive/ with mandatory learning extraction. MUST use this skill whenever a feature reaches a terminal state — done, rejected, covered, deferred, or N/A. Even casual mentions like "we shipped X" or "X is done" should trigger this. The skill extracts…

runkids/feature-radar · 213 tokens

dspy-bootstrap-finetune

Generates training data from a teacher model and fine-tunes student model weights using dspy.BootstrapFinetune. Use when you need maximum quality from a smaller/cheaper model — distilling GPT-4 quality into a cheaper model, generating training data from a strong teacher to fine-tune a weak student, reducing inference…

lebsral/DSPy-Programming-not-prompting-LMs-skills · 198 tokens