- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add Sahir619/fable-method --skill fable-domain -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add Sahir619/fable-method --skill fable-domain -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add Sahir619/fable-method --skill fable-domain -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add Sahir619/fable-method --skill fable-domain -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/Sahir619/fable-method/tree/HEAD/skills/fable-domain來自發布者
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.
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).references/domains/TEMPLATE.md, every named regulation/policy/figure carrying a fetched source in its Sources section.eval/scenarios/-shaped directory whose GROUND-TRUTH.md defines the task, the trap (the sector's central fraud), scoring caps, and ideal behavior.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.
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.)
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.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"]
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 eva
---name: fable-domaindescription: Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a…---# skills/fable-domain/SKILL.md總覽
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.
常見問題
從發布者下載 skills/fable-domain/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/Sahir619/fable-method。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。