fable-audit
From the author
Read-only gap check. Finds which of the 16 sections of Anthropic's Fable 5.1 prompting guide your CLAUDE.md, rules files, and agent system prompts are missing, which of your rules push against a section, and what the plugin already covers; the Opus 5 / Opus 5.5 / Sonnet 5.5 / Haiku 5.5 model notes are listed unscored. Changes nothing; it prints suggested wording to add and stops. For dated, stale or contradictory text to remove, use Claude Code's /doctor prompt-audit instead. Use /fable-setup to apply changes, /fable-status to see what is in effect. Triggers: "/fable-audit", "가이드 대조", "가이드에서 빠진 것", "check against the Fable guide", "which guide sections am I missing", "what does the prompting guide say that my rules lack".
Install
npx skills add Junhan2/oh-my-fable --skill fable-audit -a claude-code
Installs to .claude/skills/fable-audit/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
Want your agent to suggest skills while you type? See how to use skills from your IDE.
Safety checks on SKILL.md
No warnings.
Why 82
aiqbench computes the trust score from public signals. It is not a security audit, so read a skill before you install it.
Similar skills
Closest to this one by what they do and when they are used.
- agent-context-auditAI-Builder-Club/skillsAudit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude Code's system prompt with no eval loss). Finds overconstraint, conflicting instructions, redundancy, stale facts, and missing "unknown knowns"; produces a scored findings report with concrete rewrites, then applies approved fixes. Use when someone says "audit my CLAUDE.md", "context audit", "unhobble this repo", "review our agent docs/skills/tools", or after upgrading to Claude 5-generation models.Productivity★ 1.3K
- fableJunhan2/oh-my-fableRewrite a rough, terse, or under-specified request into a prompt that follows Anthropic's Claude prompting guides (Fable 5.1, Opus 5.5), then carry it out. Add "just the prompt" or "프롬프트만" to only see the rewrite.Planning★ 58
- pdf-helperrobonuggets/skill-creator-plusFree Claude skill that audits, builds and improves other skills against Anthropic's skill-writing rules, including what changed for Opus 5.5, Sonnet 5.5 and Fable 5.Documents★ 69
- prompt-masternaveedharri/benai-skillsThe one skill for prompting the Claude 5 models the way Anthropic says to. Starts by interviewing the user one question at a time, then writes a new prompt, rewrites an old one, or audits a whole CLAUDE.md, skill or project-instruction file, applying the rules from Anthropic's Opus 5 guide, Fable 5 guide, best practices page and context engineering post. Strips retired instructions, rebuilds the ask as a Full Job Brief (job, why, guardrails, done-means), swaps bare rules for reasons, caps scope, length and report-back, and adds Anthropic's audit line on long runs. Use when the user says "prompt master", "write me a prompt", "fix this prompt", "upgrade my prompt for Claude 5", "audit my CLAUDE.md", "rewrite my rules", "my skill feels too strict", "brief this for me", "help me brief this", "I don't know where to start", or pastes any prompt and asks why Claude over-does or under-does the task.Writing★ 74
- skill-creator-plusrobonuggets/skill-creator-plusAudits, creates and improves Agent Skills (folders with a SKILL.md) against Anthropic's skill authoring best practices, the Claude Code skills docs and the prompting guides for newer models such as Claude Fable 5 and Opus 5.5. Audit mode reports every rule as pass, fail or not applicable, with file and line evidence and a proposed fix, and changes nothing until the user approves. Use when the user asks to audit, review, check or score a skill or a folder of skills, to create a new skill or turn a repeated workflow into one, to improve, shorten, refactor or update an old skill for newer models, or to run the skill validator.Engineering★ 69
- fable-setupJunhan2/oh-my-fableOptional, recommended once. The plugin works with no setup (hook delivery, auto-detected mode, subagents covered). Use /fable-setup to move the base rules into a rules file (the recommended delivery, also the one for agent teams) or a CLAUDE.md section, pin interactive/unattended mode, see where effort comes from, or audit CLAUDE.md for conflicting rules. To see what is in effect, use /fable-status instead. Triggers: "/fable-setup", "fable 세팅", "환경 점검", "무인 모드로", "apply the Fable guide", "set up for Fable 5.1", "set up for Opus 5.5", "unattended mode", "rules file".Other★ 58
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in