Skip to content
AI & Agents
Command

/cs-fable-goal

/cs-fable-goal — Turn a ramble about something you want made into one polished, autonomous /goal prompt (copy-paste ready). Extracts deliverable/quantity/stakes/tools/destination, asks at most one question batch, verifies every named resource exists, writes a 150–350 word prose

From plugin
claude-skills
30k169 skills127 agents169 commands2 MCP
$ npx -y skills add alirezarezvani/claude-skills --agent claude-code

Command definition

cs-fable-goal.md
disable-model-invocation: true
name: "cs-fable-goal"
argument-hint: "[ramble about the thing you want made]"
description: "/cs-fable-goal — Turn a ramble about something you want made into one polished, autonomous /goal prompt (copy-paste ready). Extracts deliverable/quantity/stakes/tools/destination, asks at most one question batch, verifies every named resource exists, writes a 150–350 word prose prompt with the seven-part anatomy, and self-checks before delivering."

/cs-fable-goal — Goal Prompt Writer

**Command:** `/cs-fable-goal <ramble>`

Converts a rambling description of a desired outcome into a single polished /goal prompt for a fresh autonomous session. The output is the prompt, never the build.

When to Run

  • You know what you want made but not how to ask for it well
  • Voice-to-text rambles ("I want like 5 landing pages, crazy good, put them up somewhere")
  • You're about to kick off a fresh autonomous session and want the prompt engineered first

When NOT to Run

  • You want the thing built right now in this session — just ask for it directly
  • You already have a well-formed prompt and want it executed

What You Get

1. One fenced code block containing the finished /goal prompt (150–350 words, flowing first-person prose) with all seven anatomy parts: desire + stakes, quality bar, verified tool inventory + discovery mandate, creative-freedom grant, medium-matched verification loop, delivery destination, and the closing goal line + autonomy directive 2. A 2–4 bullet **Assumptions** list so you can correct any gap-fill with one line instead of re-rambling

Process (enforced by the skill)

Extract the six slots from the ramble → fill gaps from your brand profile or defaults, asking at most ONE question batch → verify every resource the prompt will name actually exists → write the prompt → run the six-point self-check → deliver.

See `skills/fable-goal/SKILL.md` for the full anatomy, verification-by-medium table, and anti-pattern list.

Read more
@alirezarezvani
Ships withclaude-skills

411 production-ready skills for Claude Code and 12 other coding agents, covering engineering, product, marketing, compliance, finance and the C-suite. We test whether each skill loads when you ask in plain words, and publish the results.

30k200 skills127 agents2 MCP
Get the whole plugin

Stars on GitHub

Momentum

stars in total
29.6k
Star history of alirezarezvani/claude-skills on GitHub, a chart by star-history.com

Other commands on claude-skills.

focused-fix

focused-fix

Command

Deep-dive feature repair — systematically fix an entire feature/module across all its files and dependencies. Usage: /focused-fix…

plugin-audit

plugin-audit

Command

Comprehensive audit pipeline for skills, plugins, agents, and commands. Validates structure, quality, security, marketplace…

More commands from other plugins.

devbox-entrypoint

devbox-entrypoint

Command

Context: runloop resumes a devbox by re-running the same entrypoint script, which invokes `cn serve --id <agentId> ...`. Because…

@continuedev@continuedevInstall Command
c

c

Command

Shortcut for "continue working" — pick the work in flight back up exactly where it stopped and keep going until it is done or…

lifeos2w20k
@danielmiessler@danielmiesslerInstall Command
sidecar

sidecar

Command

Spawn a read-only sidecar subagent to investigate something in this checkout without editing files, moving branches, or touching…

@builderio@builderioInstall Command