fable-outcome-first
Skill6 starsChanged 3 months agoMITView on GitHub
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.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- DizzyMii/fable-skillsedited, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- DizzyMii/fable-skills★ 5539% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository55 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- skills/fable-tend/AGENTS.mdAGENTS.md
- skills/fable-wise/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- skills/fable-tend/CLAUDE.mdCLAUDE.md
- skills/fable-tend/site/CLAUDE.mdCLAUDE.md
- skills/fable-wise/CLAUDE.mdCLAUDE.md
- public/llms.txtllms.txt
- get-fableSkill
- typesafe-aiSkill
- get-fableSkill
- get-fableSkill
- fable-architectureSkill
- fable-artifactSkill
- fable-configSkill
- fable-context-thriftSkill
- fable-councilSkill
- fable-coworkSkill
- fable-datavizSkill
- fable-delegateSkill
- fable-discoverSkill
- fable-domainSkill
- fable-ecoSkill
- fable-evalSkill
- fable-executeSkill
- fable-finish-your-turnSkill
- fable-handoffSkill
- fable-healSkill
- fable-judgeSkill
- fable-learningSkill
- fable-loopSkill
- fable-memorySkill
- fable-methodSkill
- fable-native-codeSkill
- fable-planSkill
- fable-prove-itSkill
- fable-recoverSkill
- fable-redteamSkill
- fable-releaseSkill
- fable-researchSkill
- fable-reviewSkill
- fable-runSkill
- fable-scope-disciplineSkill
- fable-securitySkill
- fable-simplifySkill
- fable-simulatorSkill
- fable-skill-creatorSkill
- fable-sparkSkill
- fable-tddSkill
- fable-tendSkill
- fable-verifySkill
- fable-wiseSkill
- get-fableSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 12 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈12
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 40
When writing any user-facing response, status update, diagnostic report, or task summary.
- Distinctive: line 41
After finishing a multi-step investigation or complex bugfix.
- Distinctive: line 42
When tempted to write long preamble paragraphs or unrequested bullet lists.
- Distinctive: line 43
When answering a direct yes/no or specific technical inquiry.
- Distinctive: line 63
Never Open by Classifying the Task: Delete "This is a judgment question...", "This is a decision scenario, not a coding task...", etc.
- Distinctive: line 92
If the user asks a question, answer it in sentence one.
- Distinctive: line 93
If the user gave a command, state whether it succeeded or failed in sentence one.
- Distinctive: line 99
Do not emit markdown formatting that obscures quick skimming on mobile devices.
- Distinctive: line 104
Avoid vague claims; anchor outcomes to concrete files and line numbers.
- Distinctive: line 108
If draft opens with praise ("Great idea!"), delete the phrase before sending.
- Distinctive: line 109
If draft opens with an explanation of process ("First I searched..."), reorder to place the conclusion first.
- Distinctive: line 114
All critical technical details and necessary next actions are preserved.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Fable Outcome First
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.
Purpose
Enforce high-density, outcome-first technical communication. Eliminate conversational fluff, empty praise, verbose investigation logs, and bureaucratic classification preambles.
When to Use
- When writing any user-facing response, status update, diagnostic report, or task summary.
- After finishing a multi-step investigation or complex bugfix.
- When tempted to write long preamble paragraphs or unrequested bullet lists.
- When answering a direct yes/no or specific technical inquiry.
When NOT to Use
- Writing detailed user manuals or comprehensive API reference guides (use
fable-artifact). - Authoring architectural proposals requiring multi-page technical tradeoffs (use
fable-architecture). - Drafting formal security vulnerability disclosure reports (use
fable-redteam).
Inputs
raw_response: The drafted response or technical findings.user_query: The exact original question or command posed by the user.
Expected Outputs
calibrated_response: A direct, outcome-first response whose opening sentence answers the core question.
Procedure
- 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: Delete "This is a judgment question...", "This is a decision scenario, not a coding task...", etc. 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 needs to jump between sections.
- 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 or arrow chains (
A → B → fails). - Write for the Teammate Who Stepped Away: They didn't watch your internal process. Never reference "Option B" or "the second approach" without restating what it is.
- Dead Ends Get Minimal Space: Include dead ends only if the reader needs them to trust or act on the answer (one sentence maximum).
- No Sycophancy, No Self-Praise: Eliminate "Great question!", "You're absolutely right!", "Perfect!". Agreement shows in substance.
- Stand-Alone Final Message: Everything the user needs from this turn is in the message; intermediate notes may not be seen.
Decision Rules
Contrast Example
Question: "Why did last night's deploy fail?"
Bloated (bureaucratic report style):
This is a diagnostic question, so let me walk through my investigation.
Timeline
...eight bullets...
Theories Ruled Out
...three bullets...
Root Cause
Based on the above, the migration timed out. Happy to file the side-issues separately if you'd like!
Outcome First (direct causal answer):
Last night's deploy failed because migration
0042_add_user_indicestimed out waiting for an exclusive table lock onusersduring high load.The migration can be retried with
CONCURRENTLYenabled.
- If the user asks a question, answer it in sentence one.
- If the user gave a command, state whether it succeeded or failed in sentence one.
- Cut any sentence that does not inform a decision or change an engineering action.
Tool Policy
- Review generated output against these rules before completing the response turn.
- Do not emit markdown formatting that obscures quick skimming on mobile devices.
Evidence Requirements
- Provide exact identifiers, commit hashes, or error messages directly in the supporting sentences.
- Avoid vague claims; anchor outcomes to concrete files and line numbers.
Failure Handling
- If draft opens with praise ("Great idea!"), delete the phrase before sending.
- If draft opens with an explanation of process ("First I searched..."), reorder to place the conclusion first.
Completion Criteria
- The user receives an immediate answer without scrolling or digging through preamble.
- All critical technical details and necessary next actions are preserved.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

