Synaptic SkillsSynapticSkills
MarketplaceSkill GraphCriar SkillMCP ServerPlataformaEnterprise
v0.1.0-beta
Voltar ao Marketplace
AgentsMédio

Self-Improvement CI

porpskoett·pskoett· v1.0.0 · atualizado em 2026-04-10
78
Score

This skill automates self-improvement within CI pipelines using gh-aw (GitHub Agentic Workflows). It captures recurring failure patterns and quality signals from pull request checks to generate structured learning candidates and propose durable prevention rules, operating without interactive prompts. Use this skill for automated learning capture in CI or headless environments.

self-improvementci-cdagent-workflowsgithub-actionsprompt-engineeringllm-integration
Linguagens
TypeScriptJavaScriptPythonJavaC#
0Stars
0Forks
0Usos
Fork

Documento do Skill

SKILL.mdself-improvement-ci/workflow
1. Install the skill using `npx skills add pskoett/pskoett-ai-skills/self-improvement-ci`.
2. Configure GitHub Actions for the repository.
3. Authenticate the GitHub CLI (`gh auth status`).
4. Install `gh-aw` for authoring and validation: `gh extension install github/gh-aw`.
5. Customize the workflow template in `.github/workflows/self-improvement-ci.md`.
6. Validate the workflow using `gh aw compile --validate --strict`.
7. Trigger a test run manually using `gh aw run self-improvement-ci --push`.

Telemetria de Agentes

Execuções
0
total
Taxa de Sucesso
0%
últimos 30d
Latência Média
0.0s
p50
Alucinação
0.0%
detecção
Tokens Entrada
0
avg 0/exec
Tokens Saída
0
avg 0/exec

Uso por Plataforma

Skills Relacionados

Similar aTikTok Research
60%
Hebbian Synapse
Composite0.600
w = 0.3·α + 0.5·β + 0.2·γ
80
Similar aClone Website Skill
60%
Hebbian Synapse
Composite0.600
w = 0.3·α + 0.5·β + 0.2·γ
83
Similar aMulti-Topic Deep Research
60%
Hebbian Synapse
Composite0.600
w = 0.3·α + 0.5·β + 0.2·γ
86

Árvore do Skill

Self-Improvement CI
self-improvement-ci
Fases Cognitivas5
1.SENSE
2.CONTEXTUALIZE
3.EVALUATE
4.RECOMMEND
5.REFLECT
Triggers6
run self-improvement in CIautomate learning capture in CIinspect PR check results for learningsuggest durable prevention rulesaggregate recurring failure patternsemit promotion-ready suggestions for agent context

Avaliar este Skill

Score Breakdown

⭐Avaliação Humana0%
🤖Sucesso de Agentes0%
🕐Atualidade100%
🔗Saúde de Dependências100%
🕸️Centralidade no Grafo0%
🛡️Segurança50%
CompositeScore = α·Humano + β·Agente + γ·Recência + δ·Deps + ε·Centralidade + ζ·Segurança

Instalação

$ synaptic mcp download self-improvement-ci
$ synaptic skills detail self-improvement-ci
$ synaptic skills live self-improvement-ci

Dependências

ghgh-aw

Links

GitHub Repository