Agent skill
dev-skillify
Convert the current conversation into a reusable skill. Different from skill-creator (which creates from scratch) — skillify captures what just happened and templatizes it.
Install this agent skill to your Project
npx add-skill https://github.com/EvolutionAPI/evo-nexus/tree/main/.claude/skills/dev-skillify
SKILL.md
Dev Skillify
Derived from oh-my-claudecode (MIT, Yeachan Heo). Adapted for the EvoNexus Engineering Layer.
Convert the current conversation into a reusable skill. Unlike skill-creator (which builds a skill from a description), skillify captures the actual workflow that just happened and templatizes it.
Use When
- You just completed a complex multi-step task that you'll want to repeat
- You want to formalize an ad-hoc workflow before it's lost
- Post-task: "I want to be able to do this again with one command"
Do Not Use When
- The task is one-off — won't be repeated
- The task is too project-specific — won't generalize
- A skill for this already exists → use it instead
- You haven't actually completed the task yet —
dev-skillifyis retrospective
Workflow
Phase 1 — Capture
- Scroll through the conversation
- Identify the actual sequence of actions taken
- Note which agents were invoked and in what order
- Note what inputs were given and what outputs were produced
Phase 2 — Generalize
- Replace specific values with placeholders (e.g.,
{component},{date}) - Identify the trigger phrases that should activate this skill
- Identify which steps were necessary vs incidental
Phase 3 — Structure
Format as a skill:
---
name: {prefix}-{action}
description: {one-line — when to use}
---
# {Skill Name}
## Use When
[trigger conditions]
## Workflow
1. {step}
2. {step}
...
## Output
[expected artifact]
## Pairs With
[agents/skills]
Phase 4 — Save & Register
- Save to
.claude/skills/{prefix}-{action}/SKILL.md - Update
.claude/rules/skills.mdwith the new entry - Test by re-invoking it
Output
## Skillify Report
### Captured Workflow
[summary of what happened]
### Generalized Steps
[the workflow with placeholders]
### Proposed Skill
- **Name:** `{prefix}-{action}`
- **Path:** `.claude/skills/{prefix}-{action}/SKILL.md`
- **Triggers:** [list]
- **Pairs with:** [agents]
### Status
- ✅ Skill created
- ✅ rules/skills.md updated
- ✅ Tested by re-invocation
Pairs With
skill-creator(builtin) — for from-scratch skill creationdev-learner— for batch pattern extraction across multiple sessionscreate-agent(builtin) — if a new agent is needed instead
Anti-patterns
- Skillifying one-off tasks
- Capturing too much detail (skills should be general)
- Capturing too little (skills should be actionable)
- Skipping the test phase
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
data-create-viz
Cria visualizações de dados de qualidade profissional com Python no tema Evolution (fundo escuro, acento
cs-customer-escalation
Empacota uma escalação para Devs, Produto ou Davidson com contexto completo. Use quando um bug precisa de atenção além do suporte normal, vários clientes reportam o mesmo problema, um cliente está ameaçando cancelar, ou um problema ficou sem resolução além do SLA. / Package an escalation for engineering, product, or leadership with full context. Use when a bug needs engineering attention beyond normal support, multiple customers report the same issue, a customer is threatening to churn, or an issue has sat unresolved past its SLA.
mkt-draft-content
Draft blog posts, social media, email newsletters, landing pages, press releases, and case studies with channel-specific formatting and SEO recommendations. Use when writing any marketing content, when you need headline or subject line options, or when adapting a message for a specific platform, audience, and brand voice.
gog-tasks
Create, manage, and prioritize tasks and todo items. Convert emails to tasks, set priorities (P0-P3) and categories (Work/Personal/Errands/Admin), review daily priorities, track blocked and overdue tasks. Use when user mentions tasks, todos, action items, or wants to convert emails to tasks. Requires confirmation before creating or deleting tasks.
discord-get-messages
Retrieve messages from Discord channels via the Discord API. Use this skill when the user wants to read, search, or analyze messages from a Discord channel.
cs-customer-research
Pesquisa multi-fonte sobre pergunta ou tópico de cliente com atribuição de fontes. Use quando um cliente pergunta algo que precisa ser verificado, investigando se um bug foi reportado antes, verificando o que foi dito anteriormente a uma conta específica, ou coletando contexto antes de redigir uma resposta. / Multi-source research on a customer question or topic with source attribution. Use when a customer asks something you need to look up, investigating whether a bug has been reported before, checking what was previously told to a specific account, or gathering background before drafting a response.
Didn't find tool you were looking for?