Borrowing it
Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/skills/prompt-optimize/SKILL.mdgit clone --depth 1 https://github.com/senda-labs/DQIII8Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/senda-labs/dqiii8/prompt-optimize)<a href="https://agentmods.dev/skills/senda-labs/dqiii8/prompt-optimize"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/prompt-optimize/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/prompt-optimize"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/prompt-optimize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00852 |
| Opus 5 | $0.00023 | $0.00426 |
| Sonnet 5 | $0.00009 | $0.00170 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
prompt-optimize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prompt-optimize — Optimize a Prompt for DQIII8/Pipeline
Analyze and optimize a prompt for maximum effectiveness in the DQIII8 ecosystem (LLM routing, scene director, TTS, Telegram bot, or agent instructions).
Usage
/prompt-optimize [the prompt text or file path]
Your Task
Given the prompt in $ARGUMENTS:
1. Classify the prompt type
- LLM routing prompt (sent to Ollama/Groq/Claude)
- Image generation prompt (sent to fal.ai flux-general)
- TTS prompt (narration text for ElevenLabs)
- Agent instruction (agent .md system prompt)
- Telegram bot message (user-facing output)
2. Evaluate on 5 dimensions (score 0-10 each)
| Dimension | What to check |
|---|---|
| Clarity | Unambiguous intent, no vague instructions |
| Specificity | Concrete examples, exact formats, numbers |
| Conciseness | No filler words, no redundant instructions |
| Output contract | Explicit format (JSON/markdown/text) stated |
| Edge cases | Handles empty input, failure, ambiguity |
3. Produce optimized version
Apply these DQIII8-specific improvements:
For LLM prompts:
- Add
Output ONLY JSON (no markdown):if structured output needed - Include exact field names in the output contract
- State the model tier this will run on (Haiku/Sonnet/Groq)
For image prompts (fal.ai):
- Lead with cinematographer style reference
- Include shot_type + camera_angle early in the prompt
- End with
no text no watermarks no logos - Keep under 200 tokens
For TTS narration:
- Present tense, max 8 words per sentence
- Include YOU/YOUR in at least 1 sentence
- Start with a specific name, date, or number
- Never start with "In [year]" / "During" / "Throughout"
For agent instructions:
- Add
## When NOT to usesection if missing - Verify trigger keywords match CLAUDE.md delegation table
- Confirm model assignment matches the canonical C/B/B+/B++/A/S tier table
(
.claude/rules/03_tiering_and_routing.md)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 110 lines · 46 tokens per session scan A 7910ff7e96bb
prompt-optimize is a skill published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 24d ago), licensed MIT. It adds 46 tokens to every session and 852 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skill-meta-prompt
Craft better prompts using proven optimization techniques — use when your prompt needs refinement.
chain-of-thought-prompts
Chain-of-thought and step-by-step reasoning prompts for complex problem solving.
few-shot-example-gen
Few-shot example generation and optimization for improved LLM performance.
llm-classifier
LLM-based zero-shot and few-shot classification for flexible intent detection.
prompt-craft
Translate natural language image descriptions into detailed, structured DALL-E prompts with subject, style, composition, lighting, and mood specifications.
gemini-api-dev
Use when build applications using Google Gemini API. Handle chat completions, multimodal inputs, function calling, streaming, and grounding with Google Search. Use when building applications using google gemini api. handle chat completions, multimodal.