Display Name
claude-fable-5-skills
Category
Agent Skills
Sub-Category
None
Primary Link
https://github.com/kpab/claude-fable-5-skills
Author Name
kpab
Author Link
https://github.com/kpab
License
MIT
Other License
No response
Description
A collection of 10 Agent Skills written specifically for Claude Fable 5, covering effort calibration, scope control, autonomous continuation, and subagent orchestration. Rewrites patterns that were over-prescriptive for older models into intent-and-boundary rules suited to Fable 5's behavior.
Validate Claims
Install the no-gold-plating skill and ask Claude Code to fix a small, well-defined bug in an existing file. The resulting diff should touch only the lines needed to fix the bug, with no added abstractions, error handling for impossible states, or unrelated refactors.
Specific Task(s)
Install the skills, then give Claude Code a multi-step but already-clear coding task. With act-when-ready active, it should begin executing once it has enough information rather than re-deriving already-established facts or presenting a menu of options it wouldn't pursue.
Specific Prompt(s)
Open skills/effort-calibrator/SKILL.md in this repo and tell me: at what effort level does it recommend running most coding and agentic work?
Additional Comments
Built this after reading Anthropic's Fable 5 prompting guide, which notes that skills written for older models can be too prescriptive for Fable 5 and degrade output quality. Each skill here states an outcome and a boundary rather than a step-by-step procedure.
Recommendation Checklist
Display Name
claude-fable-5-skills
Category
Agent Skills
Sub-Category
None
Primary Link
https://github.com/kpab/claude-fable-5-skills
Author Name
kpab
Author Link
https://github.com/kpab
License
MIT
Other License
No response
Description
A collection of 10 Agent Skills written specifically for Claude Fable 5, covering effort calibration, scope control, autonomous continuation, and subagent orchestration. Rewrites patterns that were over-prescriptive for older models into intent-and-boundary rules suited to Fable 5's behavior.
Validate Claims
Install the no-gold-plating skill and ask Claude Code to fix a small, well-defined bug in an existing file. The resulting diff should touch only the lines needed to fix the bug, with no added abstractions, error handling for impossible states, or unrelated refactors.
Specific Task(s)
Install the skills, then give Claude Code a multi-step but already-clear coding task. With act-when-ready active, it should begin executing once it has enough information rather than re-deriving already-established facts or presenting a menu of options it wouldn't pursue.
Specific Prompt(s)
Open skills/effort-calibrator/SKILL.md in this repo and tell me: at what effort level does it recommend running most coding and agentic work?
Additional Comments
Built this after reading Anthropic's Fable 5 prompting guide, which notes that skills written for older models can be too prescriptive for Fable 5 and degrade output quality. Each skill here states an outcome and a boundary rather than a step-by-step procedure.
Recommendation Checklist