Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Skill Evaluation

ASecurity

Usar cuando se necesita seleccionar el skill más apropiado para una tarea dada.

50 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentsgo

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/28/2026

$npx -y skills add gonzalezpazmonica/savia --skill skill-evaluation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Skill Evaluation?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Skill Evaluation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gonzalezpazmonica-skill-evaluation/badge)](https://www.skillsdirectory.com/skills/gonzalezpazmonica-skill-evaluation)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
layer: peripheral
name: skill-evaluation
description: Usar cuando se necesita seleccionar el skill más apropiado para una tarea dada.
metadata:
  # --- metadata.savia.* (SE-333) ---
  savia.category: reporting
  savia.maturity: beta
  savia.context: fork
  savia.context_cost: low
  savia.priority: low
  savia.summary: "Motor de evaluacion inteligente de skills basado en prompt y contexto. Analiza el prompt del usuario y el proyecto activo. Output: skills recomendados con score de relevancia."
  savia.tags: "skill-eval, prompt-analysis, scoring, activation"
---

# Skill Evaluation Engine

## §1 Prompt Analysis

**Entrada**: user_prompt, active_project, available_skills[]

**Algoritmo**:
1. Tokenizar el prompt en keywords
2. Para cada skill disponible:
   a. Calcular keyword_score = matched_keywords / total_keywords * 100
   b. Calcular context_score = project_type_match * 100
   c. Calcular history_score = previous_activations_success_rate * 100
   d. final_score = keyword_score * 0.4 + context_score * 0.3 + history_score * 0.3
3. Filtrar skills con final_score > threshold (default 30)
4. Ordenar por final_score descendente
5. Retornar top-5

**Salida**: Lista de skills recomendados con scores y razones

## §2 Context Detection

**Tipos de proyecto detectables**:
- software: presencia de package.json, .sln, Cargo.toml, pom.xml
- research: presencia de experiments/, bibliography/, datasets/
- hardware: presencia de hardware/, bom.json, revisions/
- legal: presencia de legal/, deadlines.json, court-calendar.json
- healthcare: presencia de quality/, pdca/, incidents/
- nonprofit: presencia de impact/, volunteers/
- education: presencia de curricula/, classroom/

**Mapping proyecto→skills**:
- software → architecture-intelligence, developer-experience
- research → diagram-generation, knowledge-graph
- hardware → regulatory-compliance, cost-management
- legal → cost-management, regulatory-compliance
- healthcare → regulatory-compliance, enterprise-analytics
- nonprofit → executive-reporting, cost-management

## §3 Instinct Integration

Cuando un instinto de categoría "context" tiene confianza >70%, boost el score de los skills asociados en +20 puntos.

## §4 Feedback Loop

Cada activación registra:
- skill_name, timestamp, prompt_summary, user_accepted (bool)
- Si accepted → +2 al history_score futuro
- Si rejected → -3 al history_score futuro
- Registry: `.opencode/skills/eval-registry.json`

Attribution

gonzalezpazmonicagonzalezpazmonica
View sourceSee grades on GitHubMore from gonzalezpazmonica →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →