agentleFS
chellehonikerchellehoniker/claude-code-storytelleros/skills/pen-names/SKILL.md

pen-names

Skill1 starsChanged 13 days agoMITView on GitHub

Use when the user mentions a specific pen name, has multiple pen names, or asks to switch between author identities. Triggers on phrases like "draft under my [pen name]", "switch to [pen name]", "log time for [pen name]", "my other pen name", "list my pen names".

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call stos_pen_names_list once.

    line 22
  2. Distinctive:

    Forgetting the selector mid-sequence: If the user has been working under a non-primary pen name for the last several tool calls, keep using …

    line 59
  3. Very specific:

    Call stos_pen_names_list — find "Indie Annie", get id

    line 69
  4. Very specific:

    Call stos_titles_list({ penNameId }) — find the active cozy and title id

    line 70
  5. Very specific:

    Call stos_chapters_list({ penNameId, bookId: titleId }) — find chapter 3 (or the next slot)

    line 71
  6. Very specific:

    Call stos_characters_list({ penNameId }) and stos_locations_list({ penNameId }) — load story-bible context

    line 72
  7. Distinctive:

    If the selector is omitted on any of those calls, it'd go to the primary pen name — wrong identity, wrong story bible, wrong voice.

    line 76

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Switching Between Pen Names

Why this matters

Authors who write under multiple pen names rely on StorytellerOS' pen-name separation: each pen name has its own books library, characters, locations, lore, calendar, finance ledger, tasks, and brand voice guides. The web app has a top-right dropdown to switch between them.

In the plugin, every profile-scoped tool (stos_titles_list, stos_characters_list, stos_tasks_create, stos_time_tracking_start, etc.) accepts an optional penNameId argument. Without one, calls go to the user's active / primary pen name. Just pass the argument.

When to use this skill

The user mentions a pen name by name, OR the user has multiple pen names, OR you suspect you're addressing the wrong identity (e.g., stos_titles_list returns an empty list and the user said they have books drafted).

Flow

1. Discover their pen names

Call stos_pen_names_list once. It returns:

{
  "penNames": [
    { "id": "pn_abc123...", "name": "chelle", "isPrimary": true },
    { "id": "pn_def456...", "name": "Indie Annie", "isPrimary": false }
  ]
}

isPrimary: true is the user's default profile (the one used when no selector is passed).

2. Match the user's intent to a pen name

If the user said "draft a chapter for Indie Annie" and you see a pen name "Indie Annie," that's the match. If the match is ambiguous, ask the user to confirm: "I see two pen names: chelle and Indie Annie. Which one should this go under?"

3. Pass the pen-name selector on every subsequent profile-scoped call

// Before pen-name switch
stos_titles_list({})  // → primary pen name's books

// After
stos_titles_list({ penNameId: "pn_def456..." })  // → Indie Annie's books
stos_characters_list({ penNameId: "pn_def456..." })
stos_tasks_create({ penNameId: "pn_def456...", fields: { task_name: "..." } })

The selector doesn't carry across calls automatically. If the user is working in a single pen name for a multi-step flow (drafting several chapters, planning a series), include it on EVERY tool call in the sequence.

4. Brand voice and story bible change per pen name

Story bible reads (stos_characters_list, stos_locations_list, stos_lore_list) return different data per pen name. ALWAYS scope them to the matching pen name before drafting prose — a cozy-mystery pen name's voice and world is different from a thriller pen name's.

Common mistakes to avoid

  • Forgetting the selector mid-sequence. If the user has been working under a non-primary pen name for the last several tool calls, keep using its id. Don't silently revert to primary.
  • Calling stos_pen_names_list multiple times. It's the same data each time — call it once at the start of the conversation when needed and remember the IDs.
  • Treating an empty stos_titles_list as "user has nothing." First check: did you scope to the right pen name? Their books might live under a different pen name.
  • Mixing pen names in a single record. A character belongs to one pen name. A book belongs to one pen name. Don't try to attach a character from pen name A to a book under pen name B.

Sample exchange

User: "Draft chapter 3 of my Indie Annie cozy. The previous chapter ended with the cat knocking the urn over."

You:

  1. Call stos_pen_names_list — find "Indie Annie", get id
  2. Call stos_titles_list({ penNameId }) — find the active cozy and title id
  3. Call stos_chapters_list({ penNameId, bookId: titleId }) — find chapter 3 (or the next slot)
  4. Call stos_characters_list({ penNameId }) and stos_locations_list({ penNameId }) — load story-bible context
  5. Draft the chapter in the cozy voice, given the urn cliffhanger
  6. Show the draft to the user, then on approval save the prose with stos_scenes_set_content and check the save result (see the chapter-drafting skill)

If the selector is omitted on any of those calls, it'd go to the primary pen name — wrong identity, wrong story bible, wrong voice.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.