Updated 1w ago
by bonginkan
fairy_tale
Fable/Mythos-informed workflow augmentation for agent skills and plugins
20 GitHub stars (20)
+2 in 23 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | +1 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
| Oct 17 | 0 |
| Oct 18 | 0 |
| Oct 19 | 0 |
| Oct 20 | 0 |
| Oct 21 | +1 |
| Oct 22 | 0 |
| Oct 23 | 0 |
- 4 skills (4 skills found in its SKILL.md files)
- 3 forks (3 forks)
- 1w ago last update (Last updated 1w ago)
Install
Skills CLI
npx skills add bonginkan/fairy_tale
Asks which skills and agents to install. Just one: npx skills add bonginkan/fairy_tale --skill fairy-tale-benchmark-feedback — add -g for every project.
Claude Code
git clone https://github.com/bonginkan/fairy_talecp -r "fairy_tale/skills/fairy-tale-benchmark-feedback" ~/.claude/skills/
Copies the fairy-tale-benchmark-feedback skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add bonginkan/fairy_tale
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
fairy-tale-benchmark-feedback
Apply measured benchmark feedback from SWE-Bench Pro, HLE-style closed-ended tasks, and defensive ExploitBench runs: classify misses, add narrow reusable rules, prune contradictions, and retry held-out samples without benchmark-specific hardcoding.
skills/fairy-tale-benchmark-feedback/SKILL.md on GitHub (opens in a new tab) -
fairy-tale-legal-feedback
Apply evaluated legal benchmark feedback, closure sweeps, and Fairy Fusion review to reduce one-miss and large-collapse failures in legal drafting, review, issue spotting, and form/calculation tasks.
skills/fairy-tale-legal-feedback/SKILL.md on GitHub (opens in a new tab) -
fairy-tale
Fable/Mythos harness for E3 minimum-sufficient execution, loop/spiral engineering, Helix blocker triage, double-helix learning loops, evolutionary spirals, job automation, agent handoffs, silent-loop resume, do-not-disturb windows, usage-aware load balancing, closure checks, negative-space discovery, excess/redundancy/legacy-surface review, finance completeness, e2e completion, GUI dogfood QA, cr…
skills/fairy-tale/SKILL.md on GitHub (opens in a new tab) -
japanese-wordplay-humor-detection
日本語の言葉遊び(縦読み・折句・ダジャレ・回文・アナグラム・もじり・替え歌)と日本的ユーモア(ボケ/ツッコミ・天丼・緊張と緩和・パロディ・自虐等)を体系的に検出・分類する。「縦読みして」「この文に仕掛けある?」「ダジャレ拾って」「ユーモアを分析して」等で発動。抽出した読みが実在し有意であることを必ず verbatim で確認してから報告する。
skills/japanese-wordplay-humor-detection/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.