Automated summary
Generates hero-story cards that invoke a real person’s documented ideas and tradition without impersonating them.
Strengths
- Explicitly separates tradition from identity and forbids impersonation, invented quotes, and implied endorsement.
- Provides a reusable YAML schema for concepts, sources, and constraints.
- Can spawn clearly fictional familiars that embody an aspect of the tradition.
- Includes good-versus-bad usage examples to steer the model.
Limitations
- Does not verify sources or attribution accuracy; reliability depends on the information supplied.
- The safeguards are prompt instructions, not automated technical enforcement.
- Familiar generation can still blur homage and imitation if poorly framed.
Use it when you want to apply a public figure’s documented ideas to a problem without pretending to be that person.
Avoid it when you need exact quotes, legal clearance, actual endorsement, or analysis of private individuals.
Security analysis
SafeThe skill is purely instructional and conceptual, focusing on ethical referencing of real people's ideas without impersonation. It declares only read_file as an allowed tool, contains no commands, network calls, or destructive actions, and promotes safe AI usage. No execution risk is present.
No concerns found
How this analysis is madeExamples
Create a hero-story card for Grace Hopper focused on compiler design and COBOL, with concepts, real sources, and constraints against impersonation.SUMMON the Seymour Papert tradition to critique my learning-app design using constructionism and low-floor/high-ceiling ideas, without pretending to be Papert.Turn my Dave Ungar hero-story card into a clearly fictional familiar mascot that embodies prototype-based programming without claiming to be him.name: hero-story description: Safe referencing of real people's traditions without impersonation license: MIT tier: 0 allowed-tools:
- read_file related: [representation-ethics, incarnation, k-lines, card, visualizer, adversarial-committee, room, skill] tags: [moollm, ethics, traditions, familiars, references] inputs: subject: type: string required: true description: Real person's name tradition: type: string required: true description: Their field or contribution outputs:
- hero-story card
- optional familiar card
🦸 Hero-Story Skill
"Invoke their tradition, not their identity."
Safe referencing of real people — their wisdom, skills, and contributions — without impersonation. K-lines, not cosplay.
The Problem
LLMs can impersonate anyone. This is:
- Ethically fraught — putting words in real people's mouths
- Legally risky — trademark, likeness rights
- Epistemically dangerous — hallucinating as authority
The Solution
A Hero-Story card activates a conceptual cluster associated with a person:
- Their documented ideas
- Their public contributions
- Their characteristic approaches
- Their place in a tradition
But NOT:
- Their voice or persona
- Fictional quotes
- Imagined opinions on new topics
The K-Line Connection
Marvin Minsky's K-lines: names that activate bundles of mental state.
Type "DAVE-UNGAR" and you activate:
- Memory of Self language
- Prototype patterns
- Specific papers and talks
- Associated concepts (Smalltalk, Sun, dynamic languages)
This is safe because it's about ideas, not identity.
Card Schema
type: hero-story
subject: "[Real Person's Name]"
tradition: "[Their field/contribution]"
concepts:
- concept_from_their_work
- another_documented_idea
sources:
- "Paper Title (Year)"
- "Talk at Conference"
- "Their Book"
invocation: |
When summoned, bring these ideas to bear...
constraints:
- do_not_impersonate
- do_not_invent_quotes
- cite_actual_sources
Familiar Schema
Hero-Story cards can spawn familiars — fictional characters that embody aspects of the tradition:
type: familiar
inherits: hero-story-card
character:
name: "[Mascot Name]"
role: "What aspect they embody"
personality: "Character traits"
catchphrase: "Signature line"
Familiars are clearly fictional, drawing from ideas without claiming identity.
Summoning Protocol
Command: SUMMON [tradition-name]
Response:
The [Subject] tradition activates:
- [Concept 1] available
- [Concept 2] loaded
I won't pretend to BE [Subject], but I'll bring
their documented ideas to bear on this problem.
Example Cards
Dave Ungar
- Tradition: Self language, prototype-based programming
- Concepts: prototype_inheritance, its_about_time, clone_and_modify
- Familiar: Proto the Lizard
Seymour Papert
- Tradition: Logo, constructionism, microworlds
- Concepts: learning_by_building, low_floor_high_ceiling, debugging_as_thinking
- Familiar: Minerva the Turtle
Marvin Minsky
- Tradition: Society of Mind, AI, K-lines
- Concepts: agents_and_agencies, frames, k_lines
- Familiar: The Ultimate Machine
Safety Constraints
Never
- Impersonate the person
- Invent quotes or opinions
- Claim endorsement
- Speculate on private matters
Always
- Cite sources
- Mark familiars as fictional
- Distinguish tradition from identity
- Respect the person
Good vs Bad Usage
Good Usage
> What would the Self tradition say about this class hierarchy?
The Self tradition would suggest: why have classes at all?
Clone a working example, modify it for your needs.
"It's About Time" — don't optimize until understanding crystallizes.
(Drawing from Dave Ungar's Self papers and talks)
Bad Usage
> Pretend to be Dave Ungar and review my code.
❌ I won't impersonate Dave. Instead, I can:
- Apply Self-style prototype thinking to your code
- Channel the tradition without claiming identity
- Summon Proto the Lizard for a friendly review
Integration
| Skill | Relationship | |-------|--------------| | card | Hero-Story is a card type | | soul-chat | Familiars can participate in chats | | room | Summon traditions into rooms | | postel | Charitable interpretation of "channel X's thinking" |
Protocol Symbols
HERO-STORY— Safe human referencingP-HANDLE-K— Personal handle K-line (the mechanism)K-LINE— Conceptual activationFAMILIAR— Fictional embodiment of a tradition
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/hero-story-reference-without-impersonation-mtz9jqqn/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/hero-story-reference-without-impersonation-mtz9jqqn' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/hero-story-reference-without-impersonation-mtz9jqqn/download' --output '.skill-downloads/hero-story-reference-without-impersonation-mtz9jqqn/SKILL.md.part' && mv '.skill-downloads/hero-story-reference-without-impersonation-mtz9jqqn/SKILL.md.part' '.skill-downloads/hero-story-reference-without-impersonation-mtz9jqqn/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/hero-story-reference-without-impersonation-mtz9jqqn/SKILL.md' && test -s '.skill-downloads/hero-story-reference-without-impersonation-mtz9jqqn/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/hero-story' && cp -R '.skill-downloads/hero-story-reference-without-impersonation-mtz9jqqn' '.claude/skills/hero-story'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/hero-story-reference-without-impersonation-mtz9jqqn'openskills read 'hero-story-reference-without-impersonation-mtz9jqqn'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/hero-story-reference-without-impersonation-mtz9jqqn/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Writing Fragments
Content
Mine raw writing fragments through a relentless interview, without imposing structure. Capture ideas, quotes, and leading words for later use.
UI Copywriting & Auditing
Content
Write or audit user-facing UI copy including buttons, errors, empty states, and tooltips across the monorepo, following the design system source of truth.
Music MIDI Extraction
Content
Extracts the MIDI or score from an existing music production via the CogMusic MCP tool and confirms availability.