Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add alivirgo/Major-AI-Skills --skill give-ai-direct-feedbackgit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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/alivirgo/major-ai-skills/give-ai-direct-feedback)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/give-ai-direct-feedback"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/give-ai-direct-feedback/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/alivirgo/major-ai-skills/give-ai-direct-feedback"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/give-ai-direct-feedback.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 | $0.00023 | $0.01093 |
| Opus 5 | $0.00012 | $0.00547 |
| Sonnet 5 | $0.00005 | $0.00219 |
| Haiku 4.5 | $0.00002 | $0.00109 |
Grade A, and why
give-ai-direct-feedback 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 yesterday.
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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Give AI Direct Prescriptive Feedback (AI Skill)
Overview
When an AI response doesn't hit the mark, many users respond with vague frustration ("No, that's not good, try again" or "Make it more creative"). Because the model cannot read your mind, it randomly varies tokens, often worsening the output or abandoning the parts that were already working.
The Direct Prescriptive Feedback Protocol teaches users how to steer subsequent conversation turns using the 3-Part Feedback Formula: validate what worked, isolate the flaw, and provide an explicit structural fix.
Vague Complaint vs. Prescriptive Steering
┌─────────────────────────────────────────────────────────────┐
│ Feedback Loop Comparison │
│ │
│ Vague Complaint: │
│ "Make this sound better and less boring." │
│ ↳ Model guesses $\rightarrow$ throws in buzzwords and emojis │
│ │
│ Prescriptive Feedback (3-Part Formula): │
│ "Keep paragraphs 1 and 2. In paragraph 3, cut the passive │
│ voice, replace the bullet points with a 3-column table, │
│ and keep the entire response under 100 words." │
│ ↳ 100% Deterministic Correction on Next Turn │
└─────────────────────────────────────────────────────────────┘
The 3-Part Feedback Formula
┌───────────────────────────────────────────────────────────────────────────┐
│ 1. VALIDATE ANCHOR ──► "Keep Section 1 and the introductory hook..." │
│ 2. ISOLATE FLAW ──► "...but Section 2 is too formal and verbose..." │
│ 3. APPLY FIX ──► "...rewrite Section 2 in 2 short punchy sentences." │
└───────────────────────────────────────────────────────────────────────────┘
Master Direct Feedback Prompt Templates
Pattern 1: The Tone & Cadence Calibrator
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.
- yesterday Changed · -7 tokens per session 58f98ae1b81c
- 7d ago First seen · 109 lines · 30 tokens per session scan A 238cb33f0a88
give-ai-direct-feedback is a skill published in the GitHub repository alivirgo/Major-AI-Skills (1 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,093 once invoked, about $0.0001 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 2026-09-05.
Other skills, from other repositories
ai-engineering-toolkit
AI Engineering Toolkit workflow skill. Use this skill when the user needs 6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching and the operator…
few-shot-architect
Professional Few Shot Architect skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
llm-prompt-master
Professional LLM Prompt Master skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
responsible-ai
Professional Responsible Ai Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
cost-aware-llm-pipeline
A planning guide for choosing language models and managing the amount of conversation context used by an AI coding workflow. It groups tasks by complexity and gives rules for avoiding context overflow during long sessions.