kpab/claude-fable-5-skills

1

claude-fable-5-skills 10 Agent Skills built specifically for Claude Fable 5 — intent, boundaries, and verification hooks instead of the ste…

kpab/claude-fable-5-skills

18

2

autonomous-continuation Keep Claude Fable 5 / 5.1 running to completion in unattended pipelines — no stopping on a statement of intent, no mi…

kpab/claude-fable-5-skills

4

3

grounded-progress Make Claude Fable 5 / 5.1 progress reports verifiable against actual tool results during long autonomous runs.

kpab/claude-fable-5-skills

4

4

no-gold-plating Keep Claude Fable 5 / 5.1 changes minimal — no unrequested refactors, abstractions, defensive code, feature creep, or…

kpab/claude-fable-5-skills

4

5

scope-guard Prevent Claude Fable 5 / 5.1 from taking unrequested actions — applying fixes when only asked to diagnose, sending or…

kpab/claude-fable-5-skills

4

6

subagent-orchestration Patterns for delegating work to parallel subagents with Claude Fable 5 / 5.1 — when to split tasks, async coordinatio…

kpab/claude-fable-5-skills

4

7

act-when-ready Stop Claude Fable 5 / 5.1 from over-planning, re-deriving settled facts, or surveying options it will never pursue.

kpab/claude-fable-5-skills

3

8

effort-calibrator Choose and tune the effort setting for Claude Fable 5 / 5.1 workloads.

kpab/claude-fable-5-skills

3

9

skill-refactorer Audit and rewrite existing agent skills, system prompts, and CLAUDE.md files for Claude Fable 5 / 5.1.

kpab/claude-fable-5-skills

3

10

markdown-memory A file-based lesson memory that Claude Fable 5 / 5.1 reads and maintains across sessions.

kpab/claude-fable-5-skills

2

11

regrounding-summary Make Claude Fable 5 / 5.1's final report readable to someone who saw none of the work. Use for long agentic sessions,…

kpab/claude-fable-5-skills

2