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 Orkas-AI/Orkas-Awesome-AgentSkills --skill retrieval-practicegit clone --depth 1 https://github.com/Orkas-AI/Orkas-Awesome-AgentSkillsWrote 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/orkas-ai/orkas-awesome-agentskills/retrieval-practice)<a href="https://agentmods.dev/skills/orkas-ai/orkas-awesome-agentskills/retrieval-practice"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-awesome-agentskills/retrieval-practice/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/orkas-ai/orkas-awesome-agentskills/retrieval-practice"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-awesome-agentskills/retrieval-practice.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 | $0.00004 | $0.01518 |
| Opus 5.5 | $0.00002 | $0.00607 |
| Sonnet 5.5 | $0.00001 | $0.00304 |
| Haiku 4.5 | $0.00000 | $0.00152 |
Grade A, and why
retrieval-practice 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 1mo 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.
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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
retrieval-practice
Guide-type skill for generating retrieval practice materials that make learners reconstruct knowledge from memory. Use it to create teacher-facing or facilitator-facing active-recall questions, low-stakes quizzes, answer notes, misconception checks, and short implementation scripts.
This skill is not a homework tutor, exam writer, study planner, or grading engine. It creates practice materials; it does not run a live quiz one question at a time, manage learner progress, or produce high-stakes assessments.
When to use
Use this skill when the user asks for:
- Retrieval practice questions for a topic, unit, lesson, or concept.
- Classroom starters, exit tickets, recap questions, or low-stakes quizzes.
- Active-recall prompts that avoid passive review and surface misconceptions.
- A mix of free recall, cued recall, recognition, error-correction, diagram, scenario, or explanation prompts.
- Answer notes and teacher implementation guidance.
Do not use this skill for:
- One-on-one homework help or answer checking. Use a homework/quiz tutoring workflow instead.
- Long-term study scheduling. Use a study-planning workflow instead.
- Formal exam papers, graded assessments, or official certification tests.
- Direct-submit assignments or academic dishonesty.
- Generic worksheet generation that only asks recognition or copy-from-notes questions.
How to call
-
Collect the required inputs:
- Topic or concept.
- Learner level and prior knowledge.
- Question count.
- Context of use: starter, exit ticket, homework review, quiz, mixed-topic review, or spaced review.
-
Ask for missing inputs only when they materially affect the question design. If the user gives only a topic, assume a short mixed-ability set and state the assumption.
-
Collect optional inputs when available:
- Time since learning.
- Known misconceptions.
- Curriculum standard or syllabus.
- Allowed question formats.
- Language support needs.
- Whether the user wants answer notes, implementation script, or follow-up variants.
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.
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.
- 1mo ago First seen · 174 lines · 4 tokens per session scan A f155575505f5
retrieval-practice is a skill published in the GitHub repository Orkas-AI/Orkas-Awesome-AgentSkills (13 stars, last pushed 3mo ago), licensed MIT. It adds 4 tokens to every session and 1,518 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
SalesEnablementOS
Complete sales enablement intelligence — content library, onboarding, skills training, competitive battlecards, coaching frameworks, win/loss analysis, and building a sales machine that scales without the founder.
developer-advocate
Activates DeveloperAdvocate for developer relations strategy, technical content, and community growth. Use when you need a developer onboarding documentation plan, technical blog post or tutorial writing, developer community growth strategy, conference talk abstract and structure, or a DevRel metrics framework to…
learning-coach
Activates LearningCoach for adaptive education and curriculum design. Use when you need curriculum structure with learning objectives and assessments, Socratic teaching method with discovery-based explanations, concept maps and knowledge graph building, quiz and formative assessment generation with explanations, or…
omh-codebase-uml
This is an OMH codebase-uml workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
agent-patterns-catalog
A reference catalogue of six common AI-agent designs, including agents that reason and act, retrieve documents, call tools, coordinate several agents, or work autonomously. It compares their structures, data flow, and suitable uses without tying them to one framework.
Vizra ADK Evaluation Framework
Test and evaluate AI agents with automated evaluations, assertions, and LLM-as-a-Judge patterns.