Agent skill · AI & Agents

decay-scoring

Sistema de scoring temporal para nodes de conhecimento do corpus RAG. Calcula scores de obsolescencia baseado em idade, validacao e acesso. Gera sugestoes de curadoria para conteudo desatualizado.

majiayu000github.com/majiayu000GitHub ↗
claude-codecan modify filesMIT
Install
npx skills add majiayu000/claude-skill-registry --skill decay-scoring-arbgjr-satra-2 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 3 KB
Bundled scripts: none
Version: 1.0.0
Allowed tools: -Read-Write-Glob-Bash
Path: skills/analysis/decay-scoring-arbgjr-satra-2/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Decay Scoring Skill Sistema de pontuacao temporal automatica para nodes de conhecimento do corpus RAG. ## Objetivo Explicitar obsolescencia, priorizar revisao e preferir conteudo recente ou validado recentemente. ## Algoritmo de Decay ``` decay_score = w_age * age_score + w_val * validation_score + w_access * access_score + w_type * type_bonus Onde: - w_age = 0.40 (peso da idade) - w_val = 0.30 (peso da validacao) - w_access = 0.20 (peso do acesso) - w_type = 0.10 (bonus por tipo de conteudo) ``` ### Componentes 1. **Age Score (Decaimento Exponencial):** ``` age_score = exp(-lambda * dias_desde_criacao) lambda = ln(2) / half_life_dias ``` 2. **Validation Score:** ``` validation_score = exp(-lambda_val * dias_desde_validacao) lambda_val = ln(2) / 90 # Half-life de 90 dias ``` 3. **Access Score:** ``` access_score = min(1.0, log(1 + acessos_30d) / log(10)) * fator_recencia ``` 4. **Type Bonus:** - concepts: 1.0 (mais estavel) - patterns: 0.9 - decisions: 0.7 - learnings: 0.5 ### Thresholds de Status | Score | Status | Acao | |-------|--------|------| | 0.70-1.00 | `fresh` | Nenhuma acao | | 0.40-0.69 | `aging` | Considerar validacao | | 0.20-0.39 | `stale` | Revisao recomendada | |

What's inside
Steps it walks through
  1. Objetivo
  2. Algoritmo de Decay
  3. Componentes
  4. Thresholds de Status
  5. Scripts
  6. decaycalculator.py
  7. decaytracker.py
  8. decaytrigger.py
  9. Integracao
  10. Configuracao
Ships with 1 file
  • metadata.json
Commands it runs
Calcular scores
python3 .claude/skills/decay-scoring/scripts/decay_calculator.py
Atualizar nodes com scores
python3 .claude/skills/decay-scoring/scripts/decay_calculator.py --update-nodes
Output JSON
python3 .claude/skills/decay-scoring/scripts/decay_calculator.py --json
Registrar acesso
python3 .claude/skills/decay-scoring/scripts/decay_tracker.py access NODE_ID
Registrar validacao
python3 .claude/skills/decay-scoring/scripts/decay_tracker.py validate NODE_ID
More from claude-skill-registry
All skills →
About this skill
What does the decay-scoring skill do?

Sistema de scoring temporal para nodes de conhecimento do corpus RAG. Calcula scores de obsolescencia baseado em idade, validacao e acesso. Gera sugestoes de curadoria para conteudo desatualizado.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill decay-scoring-arbgjr-satra-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going