> ## Documentation Index
> Fetch the complete documentation index at: https://labs.prompthon.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Practitioner Skills

<div className="not-prose my-4 rounded-md border border-gray-200 bg-gray-50 p-2 text-sm dark:border-gray-800 dark:bg-gray-900/40">
  <div className="mb-2 px-1 text-xs font-semibold uppercase tracking-wide text-gray-500 dark:text-gray-400">Need help?</div>

  <div className="flex flex-wrap gap-2">
    <a className="inline-flex items-center gap-2 rounded-md border border-gray-200 bg-white px-3 py-1.5 font-medium text-gray-700 no-underline shadow-sm hover:border-gray-300 hover:bg-gray-50 dark:border-gray-800 dark:bg-gray-950/60 dark:text-gray-200 dark:hover:bg-gray-900" href="https://discord.gg/sDE2HhGTg4" target="_blank" rel="noreferrer">
      <Icon icon="discord" iconType="brands" size={14} />

      <span>Ask in Discord</span>
    </a>

    <a className="inline-flex items-center gap-2 rounded-md border border-gray-200 bg-white px-3 py-1.5 font-medium text-gray-700 no-underline shadow-sm hover:border-gray-300 hover:bg-gray-50 dark:border-gray-800 dark:bg-gray-950/60 dark:text-gray-200 dark:hover:bg-gray-900" href="https://github.com/Prompthon-IO/agent-systems-handbook/issues/new/choose" target="_blank" rel="noreferrer">
      <Icon icon="github" iconType="brands" size={14} />

      <span>Open a GitHub issue</span>
    </a>

    <a className="inline-flex items-center gap-2 rounded-md border border-gray-200 bg-white px-3 py-1.5 font-medium text-gray-700 no-underline shadow-sm hover:border-gray-300 hover:bg-gray-50 dark:border-gray-800 dark:bg-gray-950/60 dark:text-gray-200 dark:hover:bg-gray-900" href="https://github.com/Prompthon-IO/agent-systems-handbook/blob/main/SUPPORT.md" target="_blank" rel="noreferrer">
      <Icon icon="life-ring" size={14} />

      <span>Support guide</span>
    </a>
  </div>
</div>

This directory collects Codex-compatible skills that are useful for everyday
workflows and personal operations. Each skill should be usable as an
installable package with a human-facing `README.md`, an agent-facing
`SKILL.md`, and only the supporting resources it needs.

## Specialization IDs

Specialization IDs use two letters followed by a two-digit sequence number. The first letter identifies the category: **G = General**, **P = Professional**. The second identifies the format: **W = Workshop-type** short course, **T = Internship** with real-project engagement.

| ID     | Specialization                                                       | Category and format                                 |
| ------ | -------------------------------------------------------------------- | --------------------------------------------------- |
| `GW01` | [Setup and Examples](/reading-paths/environment-setup)               | General · Workshop-type                             |
| `GW02` | [Professional AI Agent Course](/skills/professional-ai-agent-course) | General · Workshop-type                             |
| `PT01` | [AI-Native Internship](/specializations/ai-native-internship)        | Professional · Internship (real-project engagement) |

## GW02 · Professional AI Agent Course

The [Professional AI Agent Course](/skills/professional-ai-agent-course) composes twelve focused capabilities for Lessons 2–5. Each package link opens the complete skill codebase. Start with the [shared setup and classroom guide](https://github.com/Prompthon-IO/agent-systems-handbook/blob/develop/skills/course-support/README.md); production course persistence is a separately tracked backend dependency.

| Lesson | Skill package                                                                                                                                       | Course capability                              |
| ------ | --------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------- |
| 2      | [`local-document-organizer`](https://github.com/Prompthon-IO/agent-systems-handbook/tree/develop/skills/local-document-organizer)                   | Organize files                                 |
| 2      | [`personal-knowledge-capture`](https://github.com/Prompthon-IO/agent-systems-handbook/tree/develop/skills/personal-knowledge-capture)               | Understand sources                             |
| 2      | [`personal-workflow-automation`](https://github.com/Prompthon-IO/agent-systems-handbook/tree/develop/skills/personal-workflow-automation)           | Automate tool steps                            |
| 3      | [`web-builder`](https://github.com/Prompthon-IO/agent-systems-handbook/tree/develop/skills/web-builder)                                             | Build a local site                             |
| 3      | [`webapp-testing`](https://github.com/Prompthon-IO/agent-systems-handbook/tree/develop/skills/webapp-testing)                                       | Test behavior                                  |
| 3      | [`vercel-deploy`](https://github.com/Prompthon-IO/agent-systems-handbook/tree/develop/skills/vercel-deploy)                                         | Deploy a preview                               |
| 4      | [`business-data-structuring`](https://github.com/Prompthon-IO/agent-systems-handbook/tree/develop/skills/business-data-structuring)                 | Structure a dataset                            |
| 4      | [`crm-operations`](https://github.com/Prompthon-IO/agent-systems-handbook/tree/develop/skills/crm-operations)                                       | Operate CRM objects                            |
| 4      | [`business-data-analysis`](https://github.com/Prompthon-IO/agent-systems-handbook/tree/develop/skills/business-data-analysis)                       | Analyze evidence                               |
| 5      | [`content-strategy`](https://github.com/Prompthon-IO/agent-systems-handbook/tree/develop/skills/content-strategy)                                   | Plan content                                   |
| 5      | [`prompthon-social-campaign-manager`](https://github.com/Prompthon-IO/agent-systems-handbook/tree/develop/skills/prompthon-social-campaign-manager) | Distribute through canonical Social operations |
| 5      | [`ai-search-visibility`](https://github.com/Prompthon-IO/agent-systems-handbook/tree/develop/skills/ai-search-visibility)                           | Discover visibility gaps                       |

## PT01 · AI-Native Internship

The [PT01 · AI-Native Internship specialization](/specializations/ai-native-internship) is a separate three-phase pathway: 4–6 private two-hour coaching sessions based on the student's existing skill proficiency, a formal GitHub open-source contribution, and supervised real-project engagement subject to readiness and project matching. Coaching covers flexible content areas rather than a fixed session-by-session syllabus. Its curriculum and deliverables are documented separately from the GW02 skill packages.

## Additional Practitioner Skills

| Skill                          | Package path                                                                                                                                                          | What it demonstrates                                                                                                                                                        |
| ------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Agent Runtime Cache Benchmark  | [`skills/agent-runtime-cache-benchmark/README.md`](https://github.com/Prompthon-IO/agent-systems-handbook/blob/main/skills/agent-runtime-cache-benchmark/README.md)   | Local-first comparison of cold and warm agent runs, cache-break detection from structured run artifacts, and report-driven prompt-cache tuning                              |
| Daily News Watcher             | [`skills/daily-news-watcher/README.md`](https://github.com/Prompthon-IO/agent-systems-handbook/blob/main/skills/daily-news-watcher/README.md)                         | SQLite-backed persistent news monitoring, RSS/Atom + optional Playwright fetching, URL+hash deduplication, and per-run Markdown reports                                     |
| Garbage Collector              | [`skills/garbage-collector/README.md`](https://github.com/Prompthon-IO/agent-systems-handbook/blob/main/skills/garbage-collector/README.md)                           | Preview-first local cleanup, readable CSV rules, reversible duplicate cleanup, and explicit approval before destructive actions                                             |
| Presentation Template Designer | [`skills/presentation-template-designer/README.md`](https://github.com/Prompthon-IO/agent-systems-handbook/blob/main/skills/presentation-template-designer/README.md) | Brief-first layout planning, portable template manifests, deterministic validation, editable-backend selection, and explicit privacy boundaries before generation or upload |
| Prompt Cache Agent Harness     | [`skills/prompt-cache-agent-harness/README.md`](https://github.com/Prompthon-IO/agent-systems-handbook/blob/main/skills/prompt-cache-agent-harness/README.md)         | Claude prompt-cache layer planning, captured usage metadata review, cache-read/write reporting, and optional caller-supplied input-cost estimates                           |
| Safety Escalation Review       | [`skills/safety-escalation-review/README.md`](https://github.com/Prompthon-IO/agent-systems-handbook/blob/main/skills/safety-escalation-review/README.md)             | Local evidence review, redacted escalation memos, and human-owned safety handoff checklists without external reporting                                                      |

## Skill Package Shape

Each shared skill should keep the package itself small:

```text theme={null}
skills/<skill-name>/
  README.md
  SKILL.md
  agents/openai.yaml
  scripts/
  references/
```

Use `README.md` for the human-facing story: why the package exists, who it is
for, and the end-to-end workflow a student or operator should understand before
using it. Use `SKILL.md` for the Codex invocation contract. Use `scripts/` for
deterministic helpers, `references/` for rule files or supporting guidance, and
`agents/openai.yaml` for UI metadata.

## Contribution Type

Practitioner skill packages are code-plus-docs contributions. A package should
include a human-facing `README.md`, an agent-facing `SKILL.md`, agent metadata,
deterministic scripts, reference rules, and the minimum supporting
documentation needed to make the skill reviewable and runnable. Do not treat
these issues as documentation-only unless the requested change only edits
explanatory pages.

## Contribution Type

Practitioner skill packages are code-plus-docs contributions. A package can
include Markdown instructions, agent metadata, deterministic scripts, reference
rules, and the minimum supporting documentation needed to make the skill
reviewable and runnable. Do not treat these issues as documentation-only unless
the requested change only edits explanatory pages.

## Practitioner Boundary

Practitioner skills should show where Codex execution is stronger than a plain
chat answer: local files, persistent rules, repeatable workflows, browser or
system interaction, and explicit safety checks.