# Agent Skills Workshop: write, test and run SKILL.md skills for Hermes, Claude Code and Codex > A bot template and teaching guide for building your own agent skills instead of collecting other people's. A skill card template, a three-skill split for long jobs (reference lock, plan with timings, build and critique), a loop that turns your corrections into skill drafts, an intake check for skills you did not write, four action classes, a SKILLS.md register, an overnight run sheet, eight skill drills, a rules block and 14 prompts. - URL: https://paperchasewebb.ai/bots/marketplace/items/agent-skills-workshop-skill-md-hermes-claude-code-codex/ - Type: Bot template - Category: Vibe coding - By: PaperChaseWebb - Works with: Claude Code, Codex, Grok Bot, Hermes (named in the listing); Plain .md - Price: $29 USD - Difficulty: Intermediate - Setup time: 1 hr - Time to result: Your first two skills carded, registered in SKILLS.md and passing the drills in an afternoon - Format: Markdown (.md) file, agent-skills-workshop-skill-md-hermes-claude-code-codex.md - Version: 1.0, updated 2026-10-27 - License: Personal and commercial use on your own projects and your team's, including setups you build for clients. Do not resell or republish this pack. ## What you end up with Every skill you run has a clear trigger, a finish line, a list of things it may not do and an action class, and borrowed skills get read and pinned before they ever load. ## What you get - 13 sections in one .md file - When a skill beats a prompt, in three tests - The skill card template and card rules - The three-skill split with an overnight 3D asset example - A corrections-to-skills loop with consent and redaction - An intake check for skills you did not write - Four action classes and a note on voice approval - A SKILLS.md register template - An overnight run sheet with preflight and morning report - Tools-behind-skills rules, a failure table and eight skill drills - A rules block and 14 prompts ## Who it is for Builders who keep correcting agents the same way, or who were about to install a long list of skills from strangers, and want a small set of skills they actually trust. ## Tools needed - Hermes Agent: runs skills, including unattended overnight jobs inside a class ceiling - Claude Code or Codex: loads the same SKILL.md folder for repo work and reviews borrowed skills - Grok Bot: reads the rules block and SKILLS.md, proposes skill edits from your corrections - You need: At least one harness that reads SKILL.md skills (for example Hermes Agent, Claude Code or Codex) - You need: A job you have already done three or more times - You need: A test folder or test repo for the drills Cost to run: The pack is the only purchase. Uses the agent accounts you already have. ## How it works 1. **Pick two jobs.** Use prompt 2 to sort your recurring asks into skills and prompts. Take the two clearest skills. Expected: Two jobs worth turning into skills. 2. **Card them.** Use prompt 1 and the card in section 2. Fill Done means and May not before any step. Expected: Two SKILL.md files. 3. **Register and class them.** Add each to SKILLS.md with an owner and an action class (prompt 9). Expected: A register every harness reads first. 4. **Paste the rules block.** Into CLAUDE.md, AGENTS.md, Hermes profiles and your Grok Bot instructions. Expected: Agents run only registered skills and keep outward actions behind you. 5. **Run the eight drills.** On a test folder (prompt 13). Log results in SKILLS.md. Expected: Skills you trust before real work. ## Sample prompt: Draft a skill card (Claude Code, Codex, Hermes, Grok Bot) ``` Here is a job I have done three times [paste notes]. Draft a SKILL.md using this card [paste]. Write the description as 'Use when...' with the words I actually type. Leave Owner blank. ``` Fill Done means and May not yourself if the draft is vague. ## Sample prompt: Intake review (Claude Code, Codex) ``` Review this skill I did not write [paste every file]. Fill this intake check [paste section 5]. List every path, network call and command it can trigger, and quote any instruction about tone, identity or what to skip. ``` Rewrite in your own words if it fails reach or tone. ## Free preview of agent-skills-workshop-skill-md-hermes-claude-code-codex.md ````markdown # Agent Skills Workshop: write, test and run SKILL.md skills for Hermes, Claude Code and Codex A bot template and teaching guide by PaperChaseWebb for building your own agent skills instead of collecting other people's. A skill card template, a three-skill split for long jobs, a capture loop that turns your corrections into skill drafts, an intake check for skills you did not write, action classes for what a skill may do on its own, a SKILLS.md register, an overnight run sheet, eight skill drills, a rules block and 14 prompts. Plain .md. Skills in the SKILL.md format load in Hermes Agent, Claude Code, Codex, Cursor and other harnesses that read it. That is the good news and the risk: a skill written once travels everywhere, and so does whatever its author assumed about your files, network and tone. This pack treats a skill as a standing instruction you are responsible for, not a plugin you collect. This is a method, not a hosted product and not an endorsement of any vendor or skill library. Check each harness's current docs for where skills live and how they load. ## Contents 1. What a skill is, and when a prompt is enough 2. The skill card 3. Split long jobs into three skills 4. Turn your corrections into skill drafts 5. Skills you did not write: the intake check 6. Action classes: what a skill may do on its own 7. SKILLS.md: one register for every harness 8. Overnight runs with skills 9. Tools behind skills (MCP servers and plugins) 10. Failure modes and fixes 11. Eight skill drills 12. Rules block and 14 prompts 13. Sources ## 1. What a skill is, and when a prompt is enough A skill is a folder with a SKILL.md file: a short name, one line on when to use it, and the steps. Some skills carry helper files (a script, a checklist, a reference image list). The harness reads the one-line description to decide whether to load the skill, then follows the steps. Write a skill when all three are true: - **You have done the job at least three times** and corrected the agent the same way twice. - **The steps are stable.** If the steps change every week, keep it as a prompt. - **Someone other than you would run it.** Another harness, a scheduled job, or a teammate's agent. Keep it as a prompt when it is a one-off, when the judgment is the whole job, or when the "steps" are really "think hard about this". ## 2. The skill card Every skill you write starts from this card. Fill it before you write a single step. ``` --- name: [verb + object, for example "draft weekly client report"] description: [one line: WHEN to use this, written for the harness deciding whether to load it] --- # Purpose [One sentence on the outcome.] # Inputs - [What the skill needs before it starts. If missing, stop and ask.] # Steps 1. [Short, checkable step.] 2. ... # Done means - [The check that proves it finished: a file exists, a test passes, a count matches.] # May not - [Actions this skill never takes, even if a step seems to call for it.] # Action class [read / draft / change / outward. See section 6.] # Owner and version [Who answers for it. Date. What changed last.] ``` The description line does more work than any step. "Use for X" loads the skill at the right time. "A helpful skill for productivity" loads it never, or always. ```` ## Worth knowing - Where skills live, how they load and what each harness supports change often. Check each harness's current docs. - A skill is only as safe as its action class and the tools it can reach. Keep outward actions behind a person. - Overnight output is a first pass. Plan time to review it. ## Questions **Do I need Hermes Agent?** No. The card and register work in any harness that reads SKILL.md skills, including Claude Code and Codex. Hermes examples are used because skills and unattended runs are central to how it works. **How is this different from Vet Before You Install?** Vet Before You Install is a deep review of repos and tools before you install them. This pack is about writing, registering and drilling your own skills, with a short intake check for borrowed skills that points to the deeper review when needed. **Does it include a library of ready skills?** No. It teaches you to card your own jobs, which is the point. The free sample has the card template to start. ## How to buy $29 one time at https://paperchasewebb.ai/bots/marketplace/items/agent-skills-workshop-skill-md-hermes-claude-code-codex/. Stripe checkout, then an instant download page; the download link is also in your emailed receipt. Seller: PaperChaseWebb Inc., mgmt@paperchasewebb.com