fable-domain

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.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, well-sequenced workflow with genuine validation feedback loops and a flowchart, and its guidance is specific and actionable. Its weaknesses are token efficiency - dense meta-commentary on provenance and round citations inflates it - and a monolithic structure with no progressive disclosure into skill-local reference files.

Suggestions

Move the [observed]/[covenant]/[v1.4] tagging rationale and round-number provenance into a short note or a reference file, keeping the steps themselves lean; the tags can stay on each step without the multi-paragraph justification.

Trim 'the reason this step exists is...' justifications - the covenant/v1.4 rationale is stated once up front and need not be re-argued at each step.

Split the detailed TEMPLATE.md conformance and routing-surface wiring specifics into a reference file (e.g. references/bundle-template.md) so SKILL.md reads as an overview pointing to deeper material, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The actionable steps are sound but sit inside heavy provenance/rationale prose - the [observed]/[covenant]/[v1.4] tagging system, round-number citations ('round 15', 'round 13', 'round 12 bar'), and repeated 'the reason this step exists is...' justifications pad the file with context Claude does not strictly need to execute it.	2 / 3
Actionability	Guidance is concrete and specific for an instruction-only skill: it names exact paths and artifacts (references/domains/, TEMPLATE.md, GROUND-TRUTH.md, eval/scenarios/) and exact tools (fable-judge suite mode, headless harness, repo check script), with a worked mermaid example; absence of code is not penalized per the instruction-only carve-out.	3 / 3
Workflow Clarity	A clearly sequenced four-stage process with numbered steps and explicit validation gates - 'Run the repo's own check script; fix what fails', the smoke eval, and the fable-judge pass where 'a bundle that fails the judge is not done' - plus a flowchart with decision branches and early-exit gates, matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	Well sectioned and the external repo references are signaled with backticked paths, but the SKILL.md is monolithic - the full detailed workflow and the provenance/tagging rationale are all inline, and no skill-local reference files exist (references/, scripts/, assets/ are empty), so content that could be split out is not.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: it states concrete deliverables, gives an explicit 'Use when' trigger clause with multiple verbatim user phrasings, occupies a distinct niche, and uses third-person/imperative voice throughout. It answers both 'what' and 'when' with no fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions - 'Discuss a domain... research it from real sources... generate a trusted skill bundle - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke eval' - matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (generate a trusted skill bundle with four named parts) and when ('Use when the user says...'), satisfying the explicit-trigger requirement that would otherwise cap this at 2.	3 / 3
Trigger Term Quality	Quotes natural user phrasings verbatim as triggers - '/fable-domain <sector>', 'make a skill for <domain>', 'add a domain to the fable method', 'give a lesser model Fable's workflow for <domain>' - giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	A narrow, clearly delimited niche (producing fable-method domain bundles) with distinct, proprietary trigger phrases, making accidental firing for unrelated skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 3 missing, 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: Sahir619/fable-method
Path: skills/fable-domain/SKILL.md
Commit: 88b5cf3

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.