Borrowing it
Nothing to install: this file belongs to gonzi-stack/deepseek-skills. 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/gonzi-stack/deepseek-skills/main/.agents/.skills/skills/deepseek-performance/SKILL.mdgit clone --depth 1 https://github.com/gonzi-stack/deepseek-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/gonzi-stack/deepseek-skills/deepseek-performance)<a href="https://agentmods.dev/skills/gonzi-stack/deepseek-skills/deepseek-performance"><img src="https://agentmods.dev/badge/skills/gonzi-stack/deepseek-skills/deepseek-performance/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/gonzi-stack/deepseek-skills/deepseek-performance"><img src="https://agentmods.dev/badge/skills/gonzi-stack/deepseek-skills/deepseek-performance.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 | $0.00114 | $0.03942 |
| Opus 5.5 | $0.00046 | $0.01577 |
| Sonnet 5.5 | $0.00023 | $0.00788 |
| Haiku 4.5 | $0.00011 | $0.00394 |
Grade A, and why
deepseek-performance 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 2mo 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 — 507 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepSeek Performance Skill — Universal
La optimización prematura es la raíz de todos los males. La optimización tardía es la raíz de los incidentes en producción. El camino correcto: medir → identificar el bottleneck real → optimizar ese bottleneck → medir de nuevo.
Principio fundamental
Nunca optimizar lo que no mediste. Cada optimización sin medición previa es una apuesta. A veces mejora algo irrelevante. Siempre tiene un costo: complejidad, mantenibilidad, legibilidad.
El ciclo correcto:
SÍNTOMA → MEDIR → BOTTLENECK REAL → HIPÓTESIS → OPTIMIZAR → MEDIR DE NUEVO
❌ El ciclo incorrecto:
SÍNTOMA → INTUICIÓN → OPTIMIZAR ALGO → ASUMIR QUE MEJORÓ
FASE 1 — Identificar el bottleneck real
1.1 Clasificar el síntoma antes de actuar
| Síntoma | Posibles causas | Dónde buscar primero |
|---|---|---|
| Request lento (>500ms) | N+1 queries, query sin índice, cómputo pesado, llamada externa | Logs de queries, tiempo de cada operación |
| Alto uso de CPU | Cómputo en el thread principal, loops costosos, serialización | Profiler de CPU |
| Alto uso de memoria | Leak de memoria, carga de datasets grandes, cache sin límite | Profiler de memoria, heap snapshots |
| Degradación bajo carga | Contención de recursos, pool de conexiones agotado, lock contention | Métricas de concurrencia |
| Lentitud progresiva | Memory leak, acumulación de datos, índices fragmentados | Tendencia en el tiempo |
1.2 Medir antes de tocar nada
// Para identificar dónde se va el tiempo en un request:
const t0 = performance.now();
const user = await userRepo.getById(id); // ¿cuánto tarda esto?
const t1 = performance.now();
const orders = await orderRepo.getByUser(id); // ¿y esto?
const t2 = performance.now();
const enriched = await enrichOrders(orders); // ¿y esto?
const t3 = performance.now();
console.log({
getUser: t1 - t0,
getOrders: t2 - t1,
enrich: t3 - t2,
total: t3 - t0,
});
// Solo después de ver estos números sabés qué optimizar
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.
- 2mo ago First seen · 507 lines · 114 tokens per session scan A 54532c19d1ec
deepseek-performance is a skill published in the GitHub repository gonzi-stack/deepseek-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 114 tokens to every session and 3,942 once invoked, about $0.0005 per session on Opus 5.5. 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
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…