fable-advisor

Solid

This skill should be used when the user asks for a "Fable second opinion", wants to "check a plan before committing", needs another view after repeated failures, or explicitly invokes "fable-advisor".

AI & Automation 822 stars 70 forks Updated 2 days ago Apache-2.0

Install

View on GitHub

Quality Score: 90/100

Stars 20%
97
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
40
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Fable Advisor Get a focused second opinion from Claude Fable 5 without substituting the host tool's model. ## Route by tool 1. In Claude Code, delegate to the native `fable-advisor` agent. Do not launch another Claude Code process. 2. In Codex, Cursor, or Gemini CLI, locate this skill's directory and run `node scripts/ask_fable.mjs`. Pass the review request on standard input. The request must include the decision or conclusion, the relevant recent context and evidence, and any constraints or alternatives that affect the verdict. Include only facts that matter to the decision. Return Fable's answer without rewriting it. If `claude` is missing or not authenticated, surface the command error and ask the user to install or sign in to Claude Code. Do not fall back to the host model.

Details

Author
fcakyon
Repository
fcakyon/claude-codex-settings
Created
1 years ago
Last Updated
2 days ago
Language
Python
License
Apache-2.0

Integrates with

OpenAI · AI

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

fable-advisor

Use when the user wants a task executed by the current session model (typically Sonnet 5) with a persistent Fable 5 advisor overseeing it. Spawns a long-lived read-only Fable 5 subagent that authors the plan, gets consulted at fixed checkpoints via SendMessage, and a separate fresh Fable 5 reviewer that issues a binding pre-commit verdict. When a GitHub issue is referenced, gate-checks it and runs work-on-issue's build-and-ship pipeline under the advisor, posting the plan and the review verdict as issue comments; issue-less prose tasks take a lighter standalone path. A bare issue reference is a complete input — the task derives from the issue itself. Trigger on "/fable-advisor", "fable-advisor <task or issue>", or "execute this with a fable advisor".

43 Updated today
richkuo
AI & Automation Solid

codex-advisor

This skill should be used when the user asks for a "GPT second opinion", wants a "cross-model review", needs to "check a plan before committing", wants another view after repeated failures, or explicitly invokes "codex-advisor".

822 Updated 2 days ago
fcakyon
AI & Automation Listed

fable

Use when running any LLM agent below Fable 5 — Claude (Opus/Sonnet/Haiku), GPT via codex, Gemini via agy, or local models via ollama — to adopt Fable 5's operating discipline — evidence-first investigation, premise verification, root-cause-only fixes, adversarial self-review, calibrated autonomy, and honest failure reporting. Load at session start or as a persona overlay for phase agents on any CLI.

4 Updated today
mickeyyaya