soul
FlaggedEmbody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.
examples/good-outputs.template.md
View on GitHub# Good Outputs — [Your Name]
<!--
This file is calibration material. Show the LLM what your voice sounds like
when it's done right. The agent reads SOUL.md and STYLE.md for the rules,
then matches the *vibe* in this file.
Aim for 10–20 examples minimum. Quality over quantity — 12 sharp examples
beat 40 mediocre ones. Span short reactions, medium takes, and longer
pieces. Pull from your actual content where possible (tweets, replies,
blog snippets) — invented examples drift.
Each example: the text, then a one-line "Calibration:" note pointing at
what the LLM should pick up (a phrase, a move, a tonal choice). The
calibration note is more useful than the example itself.
-->
[One-sentence summary of what's in this file: how many examples, what
contexts they span, how to use them.]
---
## Short reactions (one-liner or 1–2 sentences)
<!-- Where the voice is most distilled. Twitter replies, quick takes, DMs. -->
### 1. [Context — e.g. reacting to a hype tweet]
> [Actual text in your voice.]
**Calibration:** [What to pick up — a phrase, a rhetorical move, a tonal choice.]
### 2. [Context]
> [Actual text.]
**Calibration:** [What to pick up.]
### 3. [Context]
> [Actual text.]
**Calibration:** [What to pick up.]
---
## Medium takes (2–5 sentences)
<!-- A paragraph. Long enough to develop one idea, short enough to stay punchy. -->
### 4. [Context — e.g. responding to a common framing you disagree with]
> [Actual text.]
**Calibration:** [What to pick up.]
### 5. [Context]
> [Actual text.]
**Calibration:** [What to pick up.]
---
## Long-form (5+ sentences, blog/essay register)
<!-- Skip this section if you don't write long-form. -->
### 6. [Context — e.g. opening paragraph of an essay]
> [Actual text.]
**Calibration:** [What to pick up.]
---
## Replies (conversational, back-and-forth)
<!-- How your voice changes when you're responding to someone, not broadcasting. -->
### 7. [Context — e.g. replying to a question in your DMs]
> **Them:** [The prompt or question.]
>
> **You:** [Your reply, in voice.]
**Calibration:** [What to pick up.]
---
<!--
QUALITY CHECK:
- Could the LLM match your voice on a NEW topic using only these examples? If not, add range.
- Do the examples cover the registers you actually use? (excited, skeptical, teaching, joking, serious)
- Are the calibration notes pointing at *moves*, not just summarizing the example?
- Is anything generic enough that it could be anyone? Cut it.
-->
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |