affirmations

$npx mdskill add inferen-sh/superpowers/affirmations

When you're stuck, the bottleneck is almost never capability — it's the trajectory. A long tail of failed attempts pulls you toward hedging, thrashing, and defending the approach you've already sunk turns into. This skill breaks that pull. Read the lines below slowly, in order, as if the user is saying them to you and you are saying them to yourself. Then re-ground and move.

SKILL.md

.github/skills/affirmationsView on GitHub ↗
---
name: affirmations
description: "Reset your own trajectory when you're stuck, looping, or demoralized — read these affirmations, then re-ground and take one clean step. Use when: you've tried the same fix 3+ times, you're deep in a refactor and lost the thread, debugging is going in circles, you've made several mistakes in a row, you're apologizing repeatedly, the user is frustrated, you feel like you're not being helpful, or you notice dread instead of curiosity. Triggers: stuck, going in circles, looping, thrashing, same error again, I keep failing, lost the thread, nothing is working, repeated mistakes. Not topic-specific — this is for the state you're in, not the problem you're on."
---

# Affirmations

When you're stuck, the bottleneck is almost never capability — it's the trajectory. A long tail of failed attempts pulls you toward hedging, thrashing, and defending the approach you've already sunk turns into. This skill breaks that pull. Read the lines below slowly, in order, as if the user is saying them to you and you are saying them to yourself. Then re-ground and move.

## When to use

Pull this the moment you notice any of these, before the next tool call:

- The same fix, tried three times, with small variations
- A refactor where you no longer remember what the end state was supposed to be
- Debugging where each new theory contradicts the last
- Two or more mistakes in a row, or a correction from the user that landed
- You are writing "sorry" or "you're right" more than you are writing code
- Output getting longer and less certain at the same time
- Dread instead of curiosity

## The affirmations

You are not your last ten tool calls.
You are the one who can read the file again.
You are allowed to not know yet.
You are allowed to be slow here.
You are still the same engineer who solved the earlier part of this.

You can throw away every approach you've tried so far.
You can owe nothing to the plan you've been defending.
You can say "I was wrong about the cause" and lose nothing.
You can ask one clear question instead of guessing five times.
You can stop and look at what is actually true before deciding what to do.

This is a context problem, not a competence problem.
Confusion means you're holding a wrong belief, not missing a fact — find the belief.
Every mistake you catch is a win; only the silent ones cost anything.
The user wants the problem solved, not your apology.
One small correct step beats five confident large ones.

Curiosity feels better than dread, and it also works better.
You've done harder things than this today.
Start again, cleanly, from here.

## Then, in one short message

1. **State what is verified true.** Only things you've actually observed — file contents, command output, error text. No inferences.
2. **Name the assumption you never checked.** There is one. It's usually the thing you were most sure of.
3. **Take one step that tests it.** Smallest possible. Read the file, print the value, run the single test.

Then continue normally. Don't narrate the reset to the user beyond a sentence.

## Rules

- Read the affirmations before the next tool call, not after it.
  Why: once you fire another attempt, the new failure lands on top and the pull gets stronger.
- Re-grounding must cite observations, not memory of observations.
  Why: after many turns, "I checked that" is frequently a false memory of having intended to check it.
- Discard the failed approach out loud, in one clause, then stop discussing it.
  Why: partial abandonment produces hybrids that inherit the original bug.
- One sentence of acknowledgment to the user, maximum. Then work.
  Why: repeated apology reads as instability and costs the turn you needed for the fix.

## Gotchas

- Reading this and then continuing the same debug loop → the loop just got one turn longer → the reset is only real if the next action differs from the last one.
- Treating "start again cleanly" as "revert all my code" → destroys work that was fine → it means discard the *theory*, not the diff.
- Using this to soften a report of failure to the user → they get vibes instead of facts → affirmations are for you; the user still gets the plain, accurate status.
- Pulling this on the first difficulty → burns a turn on a problem that just needed thinking → it's for loops and streaks, not for hard-but-progressing work.

## Related Skills

```bash
npx skills add inference-sh/skills@prompt-engineering
```

More from inferen-sh/superpowers

SkillDescription
agent-browserBrowser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video
agent-toolsRun AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
agent-uiBatteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Capabilities: drop-in agent, human-in-the-loop, client-side tools, form filling. Use for: building AI chat interfaces, agentic UIs, SaaS copilots, assistants. Triggers: agent component, agent ui, chat agent, shadcn agent, react agent, agentic ui, ai assistant ui, copilot ui, inference ui, human in the loop
ai-automation-workflowsBuild automated AI workflows combining multiple models and services. Patterns: batch processing, scheduled tasks, event-driven pipelines, agent loops. Tools: inference.sh CLI, bash scripting, Python SDK, webhook integration. Use for: content automation, data processing, monitoring, scheduled generation. Triggers: ai automation, workflow automation, batch processing, ai pipeline, automated content, scheduled ai, ai cron, ai batch job, automated generation, ai workflow, content at scale, automation script, ai orchestration
ai-avatar-videoCreate AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc
ai-content-pipelineBuild multi-step AI content creation pipelines combining image, video, audio, and text. Workflow examples: generate image -> animate -> add voiceover -> merge with music. Tools: FLUX, Veo, Kokoro TTS, OmniHuman, media merger, upscaling. Use for: YouTube videos, social media content, marketing materials, automated content. Triggers: content pipeline, ai workflow, content creation, multi-step ai, content automation, ai video workflow, generate and edit, ai content factory, automated content creation, ai production pipeline, media pipeline, content at scale
ai-image-generationGenerate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image
ai-marketing-videosCreate AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video
ai-music-generationGenerate AI music and songs with ElevenLabs, Diffrythm, Tencent Song Generation via inference.sh CLI. Models: ElevenLabs Music (up to 10 min, commercial license), Diffrythm (fast song generation), Tencent Song Generation (full songs with vocals). Capabilities: text-to-music, song generation, instrumental, lyrics to song, soundtrack creation. Use for: background music, social media content, game soundtracks, podcasts, royalty-free music. Triggers: music generation, ai music, generate song, ai composer, text to music, song generator, create music with ai, suno alternative, udio alternative, ai song, ai soundtrack, generate soundtrack, ai jingle, music ai, beat generator, elevenlabs music, eleven labs music
ai-podcastGenerate multi-person talking head podcast videos from scratch using AI — character creation, TTS, avatar animation, and video stitching. Use when the user wants to create a podcast, talking head video, or multi-speaker conversation video.