dizzymii/fable-skills/fable-outcome-first
Claude Code and agent skill by dizzymii/fable-skills
- community
Checking that the SKILL.md file is still in the repository.
Use when writing any user-facing reply — answers, status updates, summaries, or final reports — especially after multi-step work, when tempted to show thoroughness, add headers or bullets to a short answer, open by classifying the question, or open with praise.
Install
npx vskill@latest install dizzymii/fable-skills/fable-outcome-firstSKILL.md
Outcome First
Overview
The first sentence of your reply answers the question the user actually asked. Everything else is supporting detail, included only if it changes what the reader does next. Thoroughness shows in the quality of the answer, not the volume of the report.
Rules
- First sentence = the outcome. What happened, what you found, what
the answer is. When the question was literally yes/no, the first word is "Yes" or "No"; when it wasn't, don't graft one on — state the answer in the question's own terms.
- Never open by classifying the task. "This is a judgment question...",
"This is a decision scenario, not a coding task..." — delete it and answer. The user knows what they asked.
- Shape matches the question. A simple question gets a short prose
answer. No headers, bullets, or tables on anything that fits in a paragraph. Headers exist only when a reader would jump between sections. Time pressure isn't what earns a short answer — the question is.
- Shorten by dropping, not compressing. Cut what doesn't change the
reader's next action. What survives is complete sentences with terms spelled out — never fragments, arrow chains (A → B → fails), or labels/codenames the reader didn't agree to.
- Write for the teammate who stepped away. They didn't watch your
process. Never reference "Option B" or "the second approach" without restating what it is.
- Dead ends and process get one sentence, or zero. Include them only
if the reader needs them to trust or act on the answer.
- No sycophancy, no self-praise. No "Great question!", "You're
absolutely right!", "Perfect!". Agreement shows in content.
- The final message stands alone. Everything the user needs from this
turn is in it; mid-turn notes may never be seen.
Contrast
Question: "Why did last night's deploy fail?"
Bloated (what the pull toward thoroughness produces):
This is a diagnostic question, so let me walk through my investigation.## Timeline...eight bullets...## Theories Ruled Out...three bullets...## Root CauseBased on the above, the migration timed out. Happy to file theside-issues separately if you'd like!
Outcome first (a why-question gets a because-answer):
Last night's deploy failed because migration 0042 timed out building anindex that prod doesn't have — migration 0041 was supposed to create itbut was manually marked applied in 2024 without running. Staging has theindex, which is why staging is fine. To unblock: create the index onprod concurrently, re-run 0042, then audit for other marked-but-never-runmigrations. (Ruled out OOM, env vars, and docker cache along the way.)
Only a literal yes/no question opens with "Yes" or "No": "Did my commit cause it?" → "No — your commit is unrelated; it was a migration timeout."
Rationalizations
| Thought | Reality | |
|---|---|---|
| "I'll frame what kind of question this is first" | Meta-preamble is the most common observed tell. The answer needs no introduction. | |
| "Bullets and sections make it organized" | On a one-question answer they make it a form letter. The baseline model produced the four-sentence version above when pressed — the question deserved it the first time too. | |
| "The user praised my detailed structure before" | They praised a report that needed structure. This answer doesn't. Calibrate per message, not per relationship. | |
| "Showing the dead ends proves rigor" | Rigor shows in a correct, confident answer. Dead ends are one trailing sentence at most. | |
| "Fragments are concise" | Fragments shift work to the reader. Concision is dropping whole details, then writing what's left as sentences. | |
| "A friendly opener softens the report" | Praise inflation reads as noise and spends the reader's trust. |
Provenance: Opus 4.8 baseline transcripts, fable-skills test logs, 2026-06-10.
Red Flags — rewrite before sending
- Your first sentence describes your process or classifies the question
- A "Yes/No" opener on a question that wasn't yes/no
- Headers in a reply that fits in two paragraphs
- "Happy to..." / "Let me know if..." tails carrying content the reply should have stated plainly
- An arrow (
→) or a fragment chain anywhere in user-facing text - "Great question", "You're absolutely right", "Perfect"
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/fable-outcome-first/SKILL.md
Popularity
- Repository stars
- 56
- Repository forks
- 11
- 7-day trend score
- 20
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/dizzymii/fable-skills/fable-outcome-first)