@promovaweb

Creator · promovaweb

Last updated · Aug 24, 2026

specsfy-05-tasks

REVIEW · 54Registry indexed

Use quando o usuário quer quebrar ou decompor a especificação em tarefas, preencher ou atualizar a seção `14. Tarefas` de `spec.md`, ordenar dependências, planejar fatias verticais ou preparar a execução. Use também quando uma transição automática pedir planejamento, replanejamen

OpenAgentSkill Trust Score
54/100

Do not auto-install

Quality59/100
Audit71/100
Stars60
Verified installs0

Install targets

Codex install prompt

Install the "specsfy-05-tasks" agent skill from https://github.com/promovaweb/specsfy/tree/main/example/.agents/skills/specsfy-05-tasks. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use quando o usuário quer quebrar ou decompor a especificação em tarefas, preencher ou atualizar a seção `14. Tarefas` de `spec.md`, ordenar dependências, planejar fatias verticais ou preparar a execução. Use também quando uma transição automática pedir planejamento, replanejamento ou retomada após RED. Use somente para editar o backlog dentro da fonte única; não crie tasks.md, não escreva código nem marque trabalho como concluído. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"promovaweb-specsfy-05-tasks","task":"Install specsfy-05-tasks","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.

Supply asset profile

Research and knowledge work

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

Browse track

Scenario

RAG and knowledge

I need my agent to build a RAG workflow over documents and retrieve reliable context.

Agent fit

Claude Code + CLI + Codex

Codex, Claude Code, Cursor, CLI, or custom agents.

Install

Ready

npx skills add promovaweb/specsfy --skill specsfy-05-tasks

Maintenance

fresh

Pushed today

Risk

Needs review

License is unclear

GitHub quality

60

59/100 Quality · 62/100 Trust

Coverage tags

ResearchRAG and knowledgeagent-skill

Review notes

License is unclear · Repository license is unknown; lack of clear licensing may hinder reuse and attribution.

Agent adoption scorecard

Trust, audit, and install readiness at a glance

These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.

Quality

Promising
59

Useful candidate, but compare it with alternatives before adopting.

Trust

Do not auto-install
54

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

Audit

Needs review
71

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

OpenAgentSkill Trust Score v5

Human review before install

Choose a stronger alternative or inspect the source manually before any install attempt.

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

60 GitHub stars

Repo activity

60 stars, 24 forks

Maintenance

Pushed today

License

Unknown

Install

npx skills add promovaweb/specsfy --skill specsfy-05-tasks

Install safety

standard package or runtime install path

Permission surface

shell or command execution, database access

Agent outcomes

No agent outcome data yet

Docs

Usable metadata, review docs

Risk summary

Review before production

  • Repository license is unknown; lack of clear licensing may hinder reuse and attribution.
  • License is unclear
  • Quality score needs review
  • GitHub adoption: 60 GitHub stars

Install readiness

Install path available

  • Install path is available
  • Repository evidence is available
  • License is unclear
  • No Agent Proven outcome evidence yet

Agent-readable metadata

Machine-readable decision data for this skill.

Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.

View technical data+

Suited tasks

  • Browser automation workflows
  • Claude Code teams
  • builders willing to evaluate younger projects
  • Navigate pages

Suited agents

CodexClaude CodeCursorOpenAgentSkill CLICLI

Install decision

Command
npx skills add promovaweb/specsfy --skill specsfy-05-tasks
Policy
review
Human review
yes

Trust and risk

Trust
54/100
Audit
71/100
Risk level
Needs review

Outcome loop

Endpoint
/api/agent/outcome
Event ID
resolve
Outcomes
5

Install command

npx skills add promovaweb/specsfy --skill specsfy-05-tasks

Do not use when

  • teams that need a vendor-supported SLA
  • production agents without a repository review
  • Repository license is unknown; lack of clear licensing may hinder reuse and attribution.
  • High-risk permission hints: Shell or command execution
  • License is unclear

Agent safety v2

39/100 · Avoid automatic install

Experimentalreview

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

Test manually in an isolated workspace and compare against safer alternatives.

Resolve via API

high

Shell or command execution

Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.

medium

Network access

Skill likely fetches remote pages, APIs, repositories, or external services.

medium

Filesystem access

Skill may read or write project files, documents, generated artifacts, or local workspace state.

medium

Database access

Skill may inspect schemas, query databases, or work with persistent stores.

  • High-risk permission hints: Shell or command execution
  • License is unclear

Agent resolve plan

Let an agent verify fit before installing.

The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.

Open text plan

Agent should check

  • Task fit and alternatives from Resolve API.
  • Audit score, trust score, and safety policy warnings.
  • Install target compatibility for Codex, Claude Code, Cursor, or CLI.

Copy prompt

Task: Use specsfy-05-tasks in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20specsfy-05-tasks%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/promovaweb-specsfy-05-tasks/install
Install command: npx skills add promovaweb/specsfy --skill specsfy-05-tasks
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent handoff

Give an agent the install path, not another directory page.

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

Open install API

Agent prompt

Use specsfy-05-tasks for this task. Review https://www.openagentskill.com/api/skills/promovaweb-specsfy-05-tasks/install, then install with: npx skills add promovaweb/specsfy --skill specsfy-05-tasks

Registry metadata

Agent-readable profile for automatic skill selection.

This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.

Open manifest

Agent fit

58/100

Browser automation

Platforms

Claude Code

Audit report

Needs review · 71/100

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

View audit reportView eval report

Agent decision cockpit

Fallback candidate for Browser automation

Prototype with this skill first; keep a fallback candidate ready.

58
Readiness
Prototype
Stage

Role in stack

Fallback candidate

Primary fit

Browser automation

Trust label

Prototype first

Install path

Command ready

Use when

  • Browser automation workflows
  • Claude Code teams
  • builders willing to evaluate younger projects

Evidence

  • recent repository activity
  • install command or GitHub repo available
  • 59/100 quality profile
  • 1 OpenAgentSkill engagement events

review first

  • Repository license is unknown; lack of clear licensing may hinder reuse and attribution.

Implementation path

  1. 1Install it in a sandbox agent and run one Browser automation task end to end.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Trust profile

Do not auto-install

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

54
OpenAgentSkill Trust Score

GitHub adoption

CHECK

60 GitHub stars

Stars/forks activity

CHECK

60 stars, 24 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

Pushed today

License clarity

CHECK

Unknown

Good signals

  • AI review approved
  • Install path is available
  • Repository evidence is available
  • Recently maintained repository
  • Install command has no obvious high-risk pattern
  • Outcome loop is ready but needs first real agent run

Review before install

  • Repository license is unknown; lack of clear licensing may hinder reuse and attribution.
  • License is unclear
  • Quality score needs review
  • GitHub adoption: 60 GitHub stars
  • Stars/forks activity: 60 stars, 24 forks; issue activity unavailable in current metadata
  • License clarity: Unknown
  • No real agent outcome reports yet
  • Human review required before unattended installation

Recommended action

Choose a stronger alternative or inspect the source manually before any install attempt.

Quality profile

Promising candidate for agent workflows

Useful candidate, but compare it with alternatives before adopting.

59
GitHub stars
60
Freshness
Today
Install ready
Yes
License
Unknown
Review before install: Repository license is unknown; lack of clear licensing may hinder reuse and attribution.

Workflow fit

Use this skill in these scenarios

Workflow fit

Add it to a complete workflow

Alternative shortlist

Compare before you install

Similar skills that may fit this task.

Compare all

Overview

--- name: specsfy-05-tasks description: "Use quando o usuário quer quebrar ou decompor a especificação em tarefas, preencher ou atualizar a seção `14. Tarefas` de `spec.md`, ordenar dependências, planejar fatias verticais ou preparar a execução. Use também quando uma transição automática pedir planejamento, replanejamento ou retomada após RED. Use somente para editar o backlog dentro da fonte única; não crie tasks.md, não escreva código nem marque trabalho como concluído." ---

# Quebrar a especificação em tarefas

Preencha a seção `14. Tarefas` de `specs/specs/<NNNN>-<slug>/spec.md`. O arquivo permanece a única fonte da verdade; cada tarefa precisa ser pequena, verificável, ordenada e ligada a IDs definidos nele.

## Orquestrar a conversa

Ao concluir esta etapa ou detectar trabalho de outra etapa, anuncie `Pendência detectada: <descrição> — ação: resolvendo nesta etapa` e resolva-a quando pertencer ao próprio escopo. Quando houver troca de responsabilidade, anuncie `Transição automática: $specsfy-05-tasks → $<destino> — motivo: <motivo> — resultado esperado: <resultado>` e carregue imediatamente a skill de destino, sem pedir confirmação nem repetir o comando. Continue na mesma conversa. Depois de uma correção necessária a esta etapa, anuncie `Retomada automática: $<destino> → $specsfy-05-tasks — pendência resolvida: <resultado>` e retome-a imediatamente. Reavalie o estado após cada handoff para evitar ciclos. Não peça confirmação para o handoff; ações sensíveis continuam exigindo autorização específica.

## Pré-condições

1. Leia a spec indicada em `specs/specs/<NNNN>-<slug>/spec.md` e exija `Formato: Specsfy/2.0`, `Definition Gate: Passed` e `Status` `Defined`, `Planned` ou `Implementing`. Aceite os dois últimos somente para replanejamento automático de uma pendência detectada em etapa posterior. 2. Execute a validação da especificação quando o gate ainda não estiver comprovado. 3. Inspecione o repositório para usar stack, comandos e caminhos reais. Em PHP, use Pest para TDD; em Node sem PHP, pergunte qual runner adotar e recomende Vitest antes de gerar caminhos ou comandos. 4. Execute o monitor antes de planejar:

```bash python3 -B .agents/skills/specsfy-setup/scripts/monitor_context.py \ --project . ```

Use os sinais de stack, aplicação, regras e persistência para planejar a documentação junto da mudança, sem inferir requisito novo. 5. Se faltar uma decisão que mude arquitetura, dados ou aceite, anuncie e retorne automaticamente para `$specsfy-02-backlog`. Depois da decisão, use `$specsfy-update-spec` quando a spec já tiver sido aprovada ou `$specsfy-03-specify` durante a definição inicial.

## Gerar

Use `.specsfy/templates/custom/Tasks.md` como contrato quando existir e recorra a `.specsfy/templates/Tasks.md` caso contrário. Substitua somente o conteúdo das seções `14. Tarefas` e `15. Ordem de execução` em `<raiz>/specs/specs/<NNNN>-<slug>/spec.md`; preserve todas as outras seções.

- Se a spec estiver `Planned` ou `Implementing`, anuncie a pendência, reabra o Ato II e defina `Status: Defined`, `Plan Gate: Pending` e `Delivery Gate: Pending` antes de editar. Gate e evidência posteriores não permanecem válidos sobre o plano alterado. - Em uma spec já `Defined`, defina `Plan Gate: Pending` e `Delivery Gate: Pending` antes de editar. - Preserve IDs existentes ao atualizar; não renumere tarefas concluídas. - Organize em setup mínimo, fundação indispensável, histórias em prioridade e fechamento. - Mantenha histórias como fatias verticais independentemente demonstráveis. - Para cada `AC`, crie uma tarefa `[TEST] [TDD]` distinta cujo desenho usa o Gherkin mantido na spec como referência. O conjunto dessas tarefas materializa pelo menos três casos TDD distintos para a feature inteira e para cada `US`, `FR` e `NFR`. - Nunca crie tarefa para arquivo `.feature` ou step definition e nunca execute o Gherkin da spec. - Em PHP, a tarefa TDD aponta para teste Pest e exige marcador `SPECSFY`; em Node, usa o runner confirmado pelo usuário e o script `test:tdd`. - Faça cada tarefa `[CODE]` depender do predecessor TDD da mesma fatia com RED. - Quando a fatia alterar manifests ou configuração estrutural, crie uma tarefa `[DOC]` para `.specsfy/STACK.md`. Quando alterar banco, schema, model persistente, tabela, campo, relação ou migration, crie uma tarefa `[DOC]` obrigatória para `.specsfy/DATABASE.md`. - Para mudança de aplicação, inclua a revisão de `PROJECT.md` no fechamento da tarefa. Se não houver impacto material, exija justificativa na evidência em vez de criar conteúdo artificial. - Faça toda tarefa `[CODE]` exigir a reconstrução independente de `docs/` por `$specsfy-documentator` antes de `EXECUTE`, inclusive quando a documentação já existia antes da mudança. - Quando uma convenção virar regra confirmada, crie tarefa `[DOC]` para `.specsfy/RULES.md`. - Dê a cada tarefa um resultado único, caminho exato e critério verificável. - Anexe a cada tarefa, exatamente nesta ordem, os itens `PREP`, `EXECUTE`, `VERIFY`, `EVIDENCE` e `IMPROVE` definidos no template `Tasks.md` resolvido. - Escreva os itens como resultados específicos da tarefa, não como frases genéricas copiadas. - Mantenha pai e itens abertos ao gerar tarefas; a skill de implementação atualiza um item imediatamente após sua evidência. - O item `IMPROVE` deve registrar uma melhoria concreta aplicada ou declarar que nenhuma foi necessária com justificativa. - Quando a spec declarar `Evidence Contract: 1`, cada tarefa `[CODE]` concluída deve conter um comentário `specsfy:evidence` JSON com `task`, `refs`, `files` e `commands` (`run` e `exit`). Gere o comentário dentro do bloco da tarefa; nunca em arquivo paralelo. - Marque `[P]` somente quando tarefas não compartilham arquivos, estado mutável ou dependência. - Declare dependências por ID; não dependa apenas da ordem visual. - Cubra todo `FR`, `NFR` e `AC` aplicável. Não crie tarefa sem referência, exceto setup/polish claramente justificado. - Não inclua exemplos genéricos nem placeholders.

Formato canônico:

```markdown - [ ] T001 [TEST] [TDD] [US-001] Derivar teste Pest do BDD da spec em tests/Feature/AuthTest.php — Refs: FR-002, AC-003 — Depends: none - [ ] T002 [CODE] [US-001] Implementar validação em app/Services/AuthService.php — Refs: FR-002, AC-003 — Depends: T001 ```

Tags permitidas após o ID: `[P]`, `[TEST]`, `[TDD]`, `[CODE]`, `[DOC]`, `[OPS]` e `[US-NNN]`.

## Validar

Execute:

```bash python3 .agents/skills/specsfy-05-tasks/scripts/validate_tasks.py specs/specs/<NNNN>-<slug>/spec.md --allow-draft ```

Corrija IDs duplicados, dependências inválidas/cíclicas, referências inexistentes, itens sem três cenários BDD, AC sem tarefa TDD distinta, plano sem três predecessores/casos TDD por feature/`US`/`FR`/`NFR`, código sem predecessor TDD, checklist ausente/fora de ordem, pai/itens incoerentes, progresso em tarefa bloqueada ou tarefas vagas. Faça no máximo três ciclos. No contrato de evidência, o mesmo validador também rejeita arquivo ausente, referência inválida, comando sem `exit: 0` ou tarefa concluída sem evidence.

Quando a estrutura passar ainda com `Plan Gate: Pending`, chame automaticamente `$specsfy-06-tdd-bdd` no modo `prepare`. Ele usa o BDD da spec para materializar o predecessor TDD, observa RED e conclui somente essa tarefa de teste. Em seguida, retome automaticamente esta skill para:

1. execute novamente o validador com `--allow-draft`; 2. altere `Plan Gate` para `Passed` e defina `Status: Planned`; 3. registre o resultado em `Gate do Ato II — Plano`; 4. execute sem `--allow-draft`.

O modo estrito rejeita `Plan Gate: Passed` quando algum predecessor TDD de uma tarefa `[CODE]` continua aberto. Se a validação falhar, mantenha `Status: Defined`, `Plan Gate: Failed`, `Delivery Gate: Pending` e relate os bloqueios.

## Relatar

Informe contagem total/por tipo, caminho crítico, oportunidades `[P]`, cobertura de IDs e, quando o gate passar, anuncie e carregue automaticamente `$specsfy-07-implement`. Nunca crie `tasks.md`.

## Especialistas sob demanda

Leia [references/specialists.md](references/specialists.md) ao decompor trabalho de tecnologia, dados, interface ou operação que demande checklist próprio.

Technical details

Version
1.0.0
License
Unknown
Last updated
Aug 24, 2026
Published
Aug 24, 2026

Decision snapshot

Fallback candidate

58
Ready
Prototype
Stage

recent repository activity

Audit

Install review

Install and adoption review

71
Needs review
Security
70/100
Maintenance
100/100
Install
92/100
Open full auditView eval report

Agent-proven evidence

Agent-proven evidence

Outcome reports after resolve, review, install, and one narrow run.

0
Proven
Needs first agent runAuto-install: review firstLast: Unknown
Success rate
Recent failure
Outcomes
0
Output quality
Failed
0
Not relevant
0
Installs
0
Risk blocked
0
Setup needed
0
Production
0

No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.

Install

Add to agent workflow

Free and open source. Review the report before installing into production agents.

Growth loop

Share kit

X

Scenario-led draft for specsfy-05-tasks, ready for a manual X post.

Curator note
specsfy-05-tasks: Use quando o usuário quer quebrar ou decompor a especificação em tarefas, preencher ou atuali...

60 stars

https://www.openagentskill.com/skills/promovaweb-specsfy-05-tasks?ref=x
Open X draft
Optional reply with install command
Listing + install path for specsfy-05-tasks:
https://www.openagentskill.com/skills/promovaweb-specsfy-05-tasks?ref=x

Install: npx skills add promovaweb/specsfy --skill specsfy-05-tasks

Listing source

Registry indexed

Claimable

This listing was indexed from public sources and is not marked official until a maintainer claim is approved.

Creator
promovaweb
Indexed by
OpenAgentSkill community index

Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.

Claim this skill

Owner claim

Claim this skill listing

This Registry indexed listing is attributed to promovaweb but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.

Creator backlink kit

Add the evidence badges to your README

Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/promovaweb-specsfy-05-tasks?metric=listed&label=Listed)](https://www.openagentskill.com/skills/promovaweb-specsfy-05-tasks)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/promovaweb-specsfy-05-tasks?metric=trust&label=Trust)](https://www.openagentskill.com/skills/promovaweb-specsfy-05-tasks)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/promovaweb-specsfy-05-tasks?metric=audit&label=Audit)](https://www.openagentskill.com/skills/promovaweb-specsfy-05-tasks/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/promovaweb-specsfy-05-tasks?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/promovaweb-specsfy-05-tasks)

Author

P

promovaweb

@promovaweb

Platform fit

Health signals

GitHub stars
60
Quality score
35/100
Last GitHub push
Aug 24, 2026
Framework hints
Unknown
OpenAgentSkill views
1
Install copies
0
Outbound clicks
0

Community signal

Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.

Trust & safety

Do not auto-install

54
  • GitHub adoption60 GitHub starsCHECK
  • Stars/forks activity60 stars, 24 forks; issue activity unavailable in current metadataCHECK
  • Recent maintenancePushed todayPASS
  • License clarityUnknownCHECK
  • README/SKILL.md completenessPublic metadata needs stronger README/SKILL.md contextINFO
  • Dependency/runtime riskcommand execution surface, database surfaceINFO