specai-backlog
Use cuando el usuario invoque /specai-backlog, consulte planes pendientes o seleccione una feature del backlog para decidir si implementarla.
Skill by ArceApps SpecAI
Chalk Labs
Need help deploying specai-backlog?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/arceapps-dev-specai-backlog
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/specai-backlog
What's inside
- Skill name
specai-backlog- Description
- Use cuando el usuario invoque /specai-backlog, consulte planes pendientes o seleccione una feature del backlog para decidir si implementarla.
- License
- MIT
- Metadata
- author: ArceApps SpecAI · version: 1.2
- Instructions
- 78 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Visor y selector de backlog
Lee `.specai/backlog.json`, valida su contrato y presenta features completas como planes seleccionables. Cada entrada representa una feature fechada y debe conservar su identidad documental.
## Contrato de cada entrada
Toda entrada debe incluir estos campos:
```json
{
"feature_id": "YYYYMMDD-slug",
"feature_dir": "docs/specai/YYYYMMDD-slug",
"plan_dir": "docs/specai/YYYYMMDD-slug/YYYYMMDD-slug-plan.md",
"status": "backlog"
}
```
- `feature_id` es la identidad estable y debe coincidir con el prefijo común de la feature.
- `feature_dir` identifica la carpeta de la feature. La reconciliación acepta la carpeta activa `docs/specai/<feature_id>/` y la carpeta archivada `docs/specai/feature/<feature_id>/`.
- `plan_dir` debe apuntar a una ruta real dentro de `feature_dir` y al plan de la misma `feature_id`.
- `status` usa exactamente estos estados wire: `backlog`, `in_progress`, `verifying`, `ready_to_finish`, `done`.
- Durante `sync`, `in-progress` solo se acepta como token legacy de entrada y se normaliza inmediatamente a `in_progress`.
- Las interfaces nuevas solo emiten estados wire con guion bajo: `backlog`, `in_progress`, `verifying`, `ready_to_finish` y `done`.
No se aceptan entradas sin identidad, con rutas huérfanas, con prefijos incoherentes ni con estados alternativos fuera de esa normalización de `sync`. La sincronización y reconciliación valida tanto las carpetas activas como las archivadas, detecta `feature_id` duplicados, colisiones de rutas, planes ausentes, destinos incompatibles y conflictos de estado, y nunca sobrescribe silenciosamente una entrada.
## `/specai-backlog` sin argumentos
1. Leer y reconciliar `.specai/backlog.json` con las carpetas activa y archive.
2. Informar cada conflicto antes de presentar elementos seleccionables.
3. Excluir `done`, salvo que se use `--done`.
4. Mostrar `feature_id`, estado, `feature_dir` y el resumen del plan:
```text
BACKLOG — N planes
[1] 🟢 BACKLOG 20260804-example
feature_dir: docs/specai/20260804-example
plan_dir: docs/specai/20260804-example/20260804-example-plan.md
<resumen del plan>
```
Si la lista está vacía o todos los elementos están en `done`, mostrar `BACKLOG — vacío. No hay planes pendientes.`
## `/specai-backlog --done`
Usar la misma validación, pero incluir también las entradas con estado `done`.
## Selección e implementación
Seleccionar un elemento de backlog no crea una rama hasta que el usuario elige implementar.
Al seleccionar una entrada:
1. Resolverla por número o `feature_id` y leer el plan desde `plan_dir`.
2. Presentar la elección explícita: mantener/guardar en backlog o implementar.
3. Si el usuario mantiene la feature en backlog, conservar `feature_dir`, validar/actualizar únicamente el estado `backlog` y la proyección del backlog. No crear rama, worktree ni ejecutar Git: no hacer `checkout`, commit, merge ni pull.
4. Solo si el usuario elige implementar, actualizar el estado a `in_progress` y crear la rama de implementación `feature/<reponame>_<feature-slug>`; después delegar en `specai-executing-plans`.
La elección de backlog es una operación documental y de reconciliación. La creación de rama y cualquier operación Git pertenecen exclusivamente al camino de implementación elegido por el usuario.
## Estados posteriores
| Estado wire | Significado |
|---|---|
| `backlog` | Feature guardada, sin implementación elegida y sin rama. |
| `in_progress` | Implementación elegida y en ejecución. |
| `verifying` | Implementación terminada, pendiente de verificación. |
| `ready_to_finish` | Verificación y aceptación completadas; lista para finish autorizado. |
| `done` | Feature finalizada y archivada según el contrato de finish. |
Las transiciones deben conservar `feature_id`, `feature_dir` y `plan_dir`. Un conflicto o una ruta que deje de existir detiene la reconciliación y se informa al usuario; no se corrige inventando rutas ni sobrescribiendo datos.
## Integración con el flujo specai
El backlog contiene planes completos, no tareas sueltas. La skill de ejecución toma el control solo después de elegir implementar. La verificación puede mover el estado a `verifying` o `ready_to_finish`; el finish autorizado establece `done` y archiva la feature conforme a sus seis documentos.From ArceApps-dev/specai, MIT.
More from ArceApps-dev/specai
- 0.528score
specai-bootstrap
ArceApps SpecAI
Use when establishing SpecAI skill discovery, language, and shared workflow contracts.
SkillBFreshness: BClaude Code +9 - 0.524score
specai-anti-bloat
ArceApps SpecAI
Use when reviewing a diff for overengineering, auditing repository complexity, or listing // td: debt; also handles /specai-review, /specai-audit, and…
SkillBFreshness: BClaude Code +9 - 0.524score
specai-adr
ArceApps SpecAI
Use when una decisión arquitectónica duradera y transversal requiere conservar su rationale sin duplicar la especificación normativa.
SkillBFreshness: BClaude Code +9 - 0.521score
specai-judgment-day
ArceApps SpecAI
Use before creating a PR when adversarial dual-blind review is needed.
SkillBFreshness: BClaude Code +9 - 0.519score
specai-finishing-a-development-branch
ArceApps SpecAI
Use when finishing an accepted SpecAI feature through /specai-finish after global verification and recorded user acceptance.
SkillBFreshness: BClaude Code +9 - 0.518score
specai-living-documents
ArceApps SpecAI
Keep the six feature documents concise and current during implementation.
SkillBFreshness: BClaude Code +9 - 0.518score
specai-agent-clarification
ArceApps-dev
Surface unresolved technical constraints during grounded design clarification.
SkillBFreshness: BClaude Code +9 - 0.518score
specai-antigravity-bridge
ArceApps SpecAI
Use when Antigravity's plan mode would create a second plan alongside an active SpecAI feature.
SkillBFreshness: BClaude Code +9 - 0.518score
specai-dispatching-parallel-agents
ArceApps SpecAI
Use when at least two independent tasks may run concurrently.
SkillBFreshness: BClaude Code +9 - 0.518score
specai-documentation
ArceApps SpecAI
Use when creating or updating concise feature or project documentation.
SkillBFreshness: BClaude Code +9 - 0.518score
specai-grill-me
ArceApps-dev
Interview the user to resolve feature and architecture decisions before planning.
SkillBFreshness: BClaude Code +9 - 0.518score
specai-iteration
ArceApps SpecAI
Use when the user reports an issue or requests a change after implementation or acceptance.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 13, 2026 (2 months ago)
- Last release
- Aug 10, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.2
- License
- MIT
- Repository
- github.com/ArceApps-dev/specai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ArceApps SpecAI
- 0.528score
specai-bootstrap
ArceApps SpecAI
Use when establishing SpecAI skill discovery, language, and shared workflow contracts.
SkillBFreshness: BClaude Code +9 - 0.524score
specai-anti-bloat
ArceApps SpecAI
Use when reviewing a diff for overengineering, auditing repository complexity, or listing // td: debt; also handles /specai-review, /specai-audit, and…
SkillBFreshness: BClaude Code +9 - 0.524score
specai-adr
ArceApps SpecAI
Use when una decisión arquitectónica duradera y transversal requiere conservar su rationale sin duplicar la especificación normativa.
SkillBFreshness: BClaude Code +9 - 0.521score
specai-judgment-day
ArceApps SpecAI
Use before creating a PR when adversarial dual-blind review is needed.
SkillBFreshness: BClaude Code +9 - 0.519score
specai-finishing-a-development-branch
ArceApps SpecAI
Use when finishing an accepted SpecAI feature through /specai-finish after global verification and recorded user acceptance.
SkillBFreshness: BClaude Code +9 - 0.518score
specai-dispatching-parallel-agents
ArceApps SpecAI
Use when at least two independent tasks may run concurrently.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get specai-backlog running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
specai-backlog skill. Agent Mart. https://agentmart.dev/skills/arceapps-dev-specai-backlog (last updated 2026-10-24)