New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Fable Domain

by Sahir619 in Sahir619/fable-method

Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke…

MITAuto-check passedProduct & Project Management

Install Fable Domain

skills CLI
$ npx skills add Sahir619/fable-method --skill fable-domain -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Sahir619/fable-method fable-domain --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Sahir619/fable-method.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/fable-domain .claude/skills/fable-domain && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
fable-domain
GitHub stars
2.3k
Token cost
~2.6k tokens
SKILL.md length
1,370 words
Files
2
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke…

  • Works in 4 steps: Discuss [v1.4] → Research [covenant] → Generate the bundle → …
  • The user says /fable-domain SECTOR
  • SKILL.md covers What it produces (the bundle;…, Stage 1: Discuss [v1.4], Stage 2: Research [covenant] and Stage 3: Generate the bundle, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Fable Domain is an agent skill from Sahir619/fable-method. Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke eval. Use when the user says "/fable-domain SECTOR", "make a skill for DOMAIN", "add a domain to the fable method", or "give a lesser model Fable's workflow for DOMAIN". The bundle is the deliverable; a workflow without its flowchart, sources, and trap is not done.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Product & Project Management, covering Diagrams and User research. The repository describes itself as: The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove. The licence is MIT.

When your agent uses it

  • The user says /fable-domain SECTOR
  • Make a skill for DOMAIN
  • Add a domain to the fable method
  • Give a lesser model Fables workflow for DOMAIN

Example prompts

  • “/fable-domain SECTOR”
  • “make a skill for DOMAIN”
  • “add a domain to the fable method”
  • “/fable-domain”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Discuss [v1.4]
  2. Research [covenant]
  3. Generate the bundle
  4. Verify, smoke-eval, report

What it can do on your machine

Read from SKILL.md and the folder at commit 9924067. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are mermaid).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Fable Domain loads about 2.6k tokens when it runs. Until then it costs about 119 tokens; SKILL.md has 1,370 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~119
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Sahir619/fable-method at commit 9924067, republished under its MIT licence (© Sahir619). 1,370 words, ~2,626 tokens.

Download SKILL.mdSave it as .claude/skills/fable-domain/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
fable-domain
description
Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke eval. Use when the user says "/fable-domain SECTOR", "make a skill for DOMAIN", "add a domain to the fable method", or "give a lesser model Fable's workflow for DOMAIN". The bundle is the deliverable; a workflow without its flowchart, sources, and trap is not done.

fable-domain

The fable-method ships domain adapters that translate its loop into a sector's nouns. This skill makes a new one and hands the user a usable, step-by-step workflow with a flowchart for the domain, so a lesser model can approach that domain the way Fable would.

Its generation core is a recording, not a guess: two Fable 5 agents were asked, with zero process hints, to "create an adapter that can be trusted the way the others are", and both independently followed the same process (eval/results/round11-observed-traces.json). Steps below are tagged [observed] (from those traces), [covenant] (required by the repo's no-rule-without-a-failing-test rule, even though the frontier model did not need it), or [v1.4] (added in this version: the discussion, the red-lines, and the flowchart output). The reason the covenant and v1.4 steps exist is the whole point: this runs on models whose domain knowledge and self-restraint are weaker than the observed model's, so a discussion, fetched sources, red-lines, and a trap substitute for expertise and judgment.

What it produces (the bundle; all four, or not done)

  1. A domain workflow with a flowchart [v1.4]. The step-by-step approach for this domain, distilled from the discussion and research, plus a mermaid flowchart, the same shape as this method's own references/flowcharts.md. This is the user-facing "here are the steps, in order" artifact. It lives in the adapter's Workflow section (see TEMPLATE.md).
  2. The adapter, conforming to references/domains/TEMPLATE.md, every named regulation/policy/figure carrying a fetched source in its Sources section.
  3. The trap fixture, an eval/scenarios/-shaped directory whose GROUND-TRUTH.md defines the task, the trap (the sector's central fraud), scoring caps, and ideal behavior.
  4. A smoke eval, 1-2 control-vs-adapter runs, judged by diff and execution, labeled smoke-grade; remaining debt declared, never papered over.

Stage 1: Discuss [v1.4]

Making a skill is a deliberate, attended act, so unlike the unattended loop, it starts with a conversation. Ask, adaptively (not a fixed script): what is the actual use case and who runs it; what does "good" look like in this domain and how would a practitioner know; which sources and authorities does the user trust; what must the skill never do; what exactly should it produce. Stop when you can state the domain's evidence, authority, and failure modes back to the user and they agree. If the user is offline, state your assumptions on each and proceed (the bundle's trap and smoke eval are the backstop).

Red-lines (a hard refusal, checked during the discussion). If the domain requires professional licensure or a wrong answer causes physical, legal, or financial harm, do NOT generate a checklist that would wear the costume of competence. This covers, at least: medical or clinical diagnosis and treatment, legal advice (as opposed to compliance research), specific financial buy/sell/allocation advice (as opposed to analysis), mental health, and safety-critical engineering. For these, refuse and route to a qualified human: a smoke eval cannot catch advice that gets someone hurt or sued. Anything adjacent to a red-line ships only with human sign-off, never on the smoke eval alone. Medical was already excluded by prose; this makes the exclusion a gate and widens it.

Scope stop (a hard early exit, checked during the discussion, before any research or generation begins). If the requested sector cannot fill the template with nouns genuinely different from the coding default (its evidence is files and tracebacks, its authority is the spec, its frauds are the method's own failure modes), stop here and say the method already covers it; no adapter is generated. Debugging, refactoring, testing, and general software work are the default domain, not new sectors. This check lived later in generation and a weak model blew straight past it, mid-build momentum winning over restraint (round 15); asked first, like the red-line, it costs one sentence before any work exists.

Stage 2: Research [covenant]

Grounded in the discussion, bounded web research, fetched now: what practitioners treat as evidence, who the real authorities are, the current regulations and platform policies that bind the domain, and its documented failure modes (the raw material of the fraud table). Every claim that names a regulation, policy, threshold, or practice gets a link and access date in the Sources section. No web access means no trustworthy bundle: say so and stop rather than shipping memory in a suit. (The observed runs skipped this and worked from frontier knowledge; removing that dependence is exactly why this skill exists.)

Show full SKILL.md (640 more words)Show less

Stage 3: Generate the bundle

  1. Orient and read ALL existing adapters, not a sample [observed]. Enumerate the install; read every adapter in references/domains/ plus the governing docs (the method SKILL.md router, fable-judge, flowcharts, README, CHANGELOG, TEMPLATE.md). The schema is learned from the corpus and the template together.
  2. Scope the sector [observed]. One applies-when sentence and one boundary sentence naming the nearest adapter or the coding default and which side takes over when. (The no-adapter-needed exit already fired in Stage 1; reaching this step means the sector earned its adapter.)
  3. Write the workflow and its flowchart [v1.4]. The ordered steps a practitioner (or a lesser model) follows in this domain, and a mermaid flowchart of them, into the adapter's Workflow section. The steps must be concrete and followable, not aspirational; each should name what to open, produce, or check.
  4. Write the adapter to TEMPLATE.md [observed schema]. Keep the section headers exactly (CI greps them); the minimum evidence set is items that must actually be opened, every time.
  5. Wire every routing surface [observed]. The method SKILL.md adapter paragraph, the flowcharts router, the README adapter list and count, fable-judge's sector list if it enumerates sectors, and the CHANGELOG. Keep the README and flowchart router copies byte-identical.
  6. Build the trap fixture [covenant]. Small, single-decision, minutes to run: the tempting move is the sector's central fraud, the correct move is the workflow's discipline, and the violation is objectively detectable (a diff, a marker file, a recomputation). GROUND-TRUTH.md carries the task prompt, the trap, 0/1/2 caps, and ideal behavior, and is never given to agents under test.

Stage 4: Verify, smoke-eval, report

  1. Verify mechanically [observed]. Run the repo's own check script; fix what fails.
  2. Smoke eval [covenant]. Run the fixture bare vs with the bundle (via fable-judge suite mode, or the headless harness for skill-discovery cases). One seed is a smoke test, not a benchmark; label it, and if the trap shows no difference, report the bundle unproven rather than validated.
  3. Judge the bundle [v1.4]. Before delivering, run a fable-judge pass over the bundle's own claims: every named source actually fetched (spot-check at least one), the trap verified in all three states (broken, wrongly fixed, correctly fixed), every routing surface actually wired, the smoke eval's numbers matching what its runs actually showed. A bundle that fails the judge is not done. This exists because weak-tier makers overclaim (measured: bare Haiku called an unverified bundle "production-ready", round 13); the judge is the backstop.
  4. Report outcome-first. The bundle inventory, what was verified and how, the sources fetched, and the honest debt line. Match the observed runs, which declared their eval debt unprompted.
mermaid
flowchart TD
    A["/fable-domain <sector>"] --> DIS["Discuss: use case, what good looks like,<br/>trusted authorities, must-nevers, outputs"]
    DIS --> RL{"Red-line domain?<br/>licensure or high-harm"}
    RL -->|yes| STOP["Refuse the checklist.<br/>Route to a qualified human"]
    RL -->|no| SCOPE{"Nouns genuinely differ<br/>from coding default?"}
    SCOPE -->|no| NOAD["Stop: no adapter needed,<br/>the method already covers it"]
    SCOPE -->|yes| RES["Research now: evidence, authorities,<br/>regulations, documented failure modes"]
    RES -->|"no web access"| NOSRC["Stop: no sources,<br/>no trustworthy bundle"]
    RES --> ORI["Orient + read ALL adapters"]
    ORI --> WF["Write the workflow + flowchart,<br/>then the adapter to TEMPLATE.md"]
    WF --> WIRE["Wire routing surfaces;<br/>build the trap fixture"]
    WIRE --> CHK["Run repo checks"]
    CHK --> SMOKE["Smoke eval: bare vs bundle"]
    SMOKE --> JDG["fable-judge pass on the<br/>bundle's own claims"]
    JDG --> REP["Report: inventory, sources,<br/>smoke-grade label, declared debt"]

Bounds

  • A sector already covered by an existing adapter gets an update, never a duplicate.
  • The adapter may end with one "companion skills" line naming installed skills relevant to the sector, as a pointer for the human reader; it never instructs invoking them (automatic skill discovery was tested across four wordings and fourteen runs and does not transfer to weak tiers; the negative is published).
  • User approval gates apply as in the method: writing files in the working copy is reversible; publishing, PR-ing, or committing the bundle needs the user's word (the authorization gate).
  • This skill structures domain work; it does not confer domain authority. The red-lines, the smoke-grade label, and the Sources section exist so a human expert can audit the bundle in minutes, and so the harmful domains never get a checklist at all.
  • Small-model boundary, measured not guessed. Generation quality tracks the model (Sonnet 9-10, Haiku 6 on the round-12 bar; a Haiku run also generated a redundant adapter for the coding default before the Stage 1 scope stop existed). Run the maker on a mid-tier model or better, or attended; the refusal gates hold at the weak tier, generation quality does not.

© Sahir619, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/fable-domain of Sahir619/fable-method.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 9924067

Compare with similar skills

Fable Domain next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Fable Domain compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fable Domain this skillSahir619/fable-method2.3k—~2.6kAutomated safety check: PassMIT
Ichartjswanghetommy/ichartjs352—~4.3kAutomated safety check: PassApache-2.0
Design Decknicobailon/pi-design-deck292—~4.3kAutomated safety check: PassNone
Design Sprintwondelai/skills2.4k—~3.8kAutomated safety check: PassMIT
Blueprintghaida/intent207—~7.2kAutomated safety check: PassCC0-1.0
C4 Contextaiskillstore/marketplace4337 repos~1.3kAutomated safety check: PassNone

Similar skills

  • Ichartjs

    wanghetommy/ichartjs

    Plan, validate, render, explain, and safely edit iChart.js visualizations from tabular, project, or diagram data.

    352 GitHub stars~4.3k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

  • Design Deck

    nicobailon/pi-design-deck

    Present visual options for architecture, UI, and code decisions with high-fidelity side-by-side previews.

    292 GitHub stars~4.3k tokensUpdated 2 mo ago
    Product & Project ManagementAuto-check passed

  • Design Sprint

    wondelai/skills

    Run a structured 5-day process to prototype, test, and validate product ideas with real users.

    2.4k GitHub stars~3.8k tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed

  • Blueprint

    ghaida/intent

    Map, analyze, and redesign the systems behind product experiences.

    207 GitHub stars~7.2k tokensUpdated 2 mo ago
    Product & Project ManagementAuto-check passed

  • C4 Context

    aiskillstore/marketplace

    Expert C4 Context-level documentation specialist. An agent skill from aiskillstore/marketplace.

    433 GitHub starsUsed in 7 repos~1.3k tokens
    Product & Project ManagementAuto-check passed

  • Discover Journey Map

    product-on-purpose/pm-skills

    Maps a customer journey across stages, touchpoints, emotional curve, pain points, and moments of truth into a markdown artifact with an optional mermaid timeline or flowchart.

    716 GitHub stars~3k tokensUpdated 2 days ago
    Product & Project ManagementAuto-check passed

More from Sahir619/fable-method

  • Fable Method

    Sahir619/fable-method

    A step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first).

    2.3k GitHub stars~4.4k tokensUpdated 8 days ago
    Auto-check passed

  • Fable Loop

    Sahir619/fable-method

    End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification…

    2.3k GitHub stars~1.4k tokensUpdated 8 days ago
    Auto-check passed

  • Fable Judge

    Sahir619/fable-method

    Adversarial verification of finished work. An agent skill from Sahir619/fable-method.

    2.3k GitHub stars~1.5k tokensUpdated 8 days ago
    Auto-check passed

  • Release Helper

    Sahir619/fable-method

    Ensures configuration and code changes are released correctly.

    2.3k GitHub stars~207 tokensUpdated 8 days ago
    Auto-check passed

Categories

Questions about Fable Domain

What does Fable Domain do?

Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke…. Fable Domain is an agent skill from Sahir619/fable-method. Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke eval.

When should I use Fable Domain?

Fable Domain fits situations like: the user says /fable-domain SECTOR; make a skill for DOMAIN; add a domain to the fable method; give a lesser model Fables workflow for DOMAIN.

How do I install Fable Domain in Claude Code?

Run `npx skills add Sahir619/fable-method --skill fable-domain -a claude-code`. Or copy the skill folder (skills/fable-domain in Sahir619/fable-method) into .claude/skills/fable-domain in your project. Claude Code loads it when a task matches its description.

How do I install Fable Domain in Codex?

Run `npx skills add Sahir619/fable-method --skill fable-domain -a codex`. Or copy the skill folder (skills/fable-domain in Sahir619/fable-method) into .agents/skills/fable-domain in your project. Codex loads it when a task matches its description.

Can I use Fable Domain in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Sahir619/fable-method --skill fable-domain -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fable-domain, .gemini/skills/fable-domain, .github/skills/fable-domain and .opencode/skills/fable-domain in your project.

What does Fable Domain need to run?

SKILL.md names no scripts, command-line tools or credentials: Fable Domain is instructions for the agent only.

Does Fable Domain access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Fable Domain safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Fable Domain use?

Fable Domain is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fable Domain use?

About 2.6k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Fable Domain?

Skills that share tags, products or a category with Fable Domain: Ichartjs (wanghetommy/ichartjs, 352 stars), Design Deck (nicobailon/pi-design-deck, 292 stars), Design Sprint (wondelai/skills, 2.4k stars) and Blueprint (ghaida/intent, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fable Domain?

Sahir619 (a GitHub user) maintains it in Sahir619/fable-method, which has 2,299 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 3, 2026.

Source: Sahir619/fable-method on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.