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 deciqAI/knowledge-skills --skill deliberate-practicegit clone --depth 1 https://github.com/deciqAI/knowledge-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/deciqai/knowledge-skills/deliberate-practice)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/deliberate-practice"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/deliberate-practice.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.01833 |
| Opus 5 | $0.00049 | $0.00916 |
| Sonnet 5 | $0.00020 | $0.00367 |
| Haiku 4.5 | $0.00010 | $0.00183 |
Grade A, and why
deliberate-practice 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 7d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deliberate Practice
Overview
Most people confuse repetition with learning — they accumulate years of experience and plateau. Once an activity becomes automatic, executing it no longer builds new neural architecture. Ericsson, Krampe & Tesch-Römer (1993) showed the predictive variable is not hours of doing but hours of specifically deliberate practice — targeted, uncomfortable, feedback-rich repetition designed to build mental representations.
Cross-skill composition: Use feedback-loops first (audit your error signal); then metacognition (surface your current representation gap); use instead of deep-work when acquiring skills, not producing output; use alongside cognitive-evolution-stages for stage-aware practice design.
When to Use
Trigger: plateau despite experience; designing high-performance learning program; training hours high but skill transfer low; evaluating whether practice is building capability or maintaining it; skill atrophy or deskilling as AI copilots absorb the routine reps (AI adoption, AI hype, "will AI make me worse at my craft"). When NOT: goal is execution not acquisition (use deep-work); no expert benchmark exists; bottleneck is motivational not representational.
Coaching Novices (Adaptive Front Door)
Engine mode: user has a concrete case → run The Process directly. Coach mode: user is unfamiliar or has no concrete case → guide step by step.
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
- Ask the plateau question: "When you practice X, what does it feel like after 15 minutes — harder, the same, or easier?" Comfort/easy = automatic = not building representations.
- Find the expert performance structure: "Who is world-class at X? What do they perceive in the first 3 seconds that you don't?" This locates the mental representation gap.
- Identify the discomfort zone: "What part of practicing X makes you most want to stop?" That is almost always where the gap lives.
[WAIT — do not advance until user responds]
- Design the smallest feedback loop: "How would you know within 60 seconds whether a move was correct?" Latency over 24h kills representation-building.
[WAIT — do not advance until user responds]
- Set the repetition target and stop-rule: "How many reps of this specific discomfort can you sustain before concentration drops?" (1–4 hours/day is Ericsson's ceiling.)
[WAIT — do not advance until user responds]
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 120 lines · 99 tokens per session scan A 013f444330bd
deliberate-practice is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 5d ago), licensed MIT. It adds 99 tokens to every session and 1,833 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
voice-builder
Ingests 5–20 of the user's writing samples and distils a reusable voice-profile.md — signature phrases, sentence-length distribution, opener/closer habits, punctuation quirks, vocabulary do/don't lists, tone sliders, and three calibration paragraphs with self-checks. Other skills load this file so every post sounds…
english-swe-daily
Daily English expression coach for intermediate software engineers. Use this skill whenever the user wants to improve their spoken or written English in a software engineering work context — especially for standups, Slack messages, 1:1s, meetings, giving feedback on code, asking for help, disagreeing politely, or…
agent-teacher
A teaching aid that explains technical ideas with a small runnable code example and a guided walkthrough. It is meant for learning how something works, not fixing existing code.
lecture-notes
Transform raw lecture content (transcript, plain text, or slides) into clean, structured, study-ready notes in Markdown. Use this skill whenever the user pastes lecture material — a transcript (with or without timestamps), course/lecture text, or slide content — and asks for notes, a summary, or help studying. Also…
master-debate
A skill for running an adversarial, multi-round debate between two Buddhist teachers. It is designed for questions where the teachers argue from different positions.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.