Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Backlog Git Tracker

ASecurity

Usar cuando se capturan o comparan snapshots del backlog para detectar drift.

50 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentsgoazuregitapidevops

Works with

cliapi

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/28/2026

$npx -y skills add gonzalezpazmonica/savia --skill backlog-git-tracker --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Backlog Git Tracker?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Backlog Git Tracker
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gonzalezpazmonica-backlog-git-tracker/badge)](https://www.skillsdirectory.com/skills/gonzalezpazmonica-backlog-git-tracker)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
layer: peripheral
name: backlog-git-tracker
description: Usar cuando se capturan o comparan snapshots del backlog para detectar drift.
metadata:
  # --- metadata.savia.* (SE-333) ---
  savia.category: pm-operations
  savia.maturity: beta
  savia.context_cost: medium
  savia.dependencies: "savia-hub-sync, client-profile-manager"
  savia.priority: medium
  savia.summary: "Captura snapshots periodicos del backlog (Azure DevOps, Jira, Savia Flow) y los almacena como markdown en SaviaHub. Compara versiones, detecta scope creep y genera informes de desviacion."
  savia.tags: "backlog, snapshot, audit, tracking"
---

# Skill: BacklogGit Tracker

> Regla: @docs/rules/domain/backlog-git-config.md
> Hub: @docs/rules/domain/savia-hub-config.md

## Prerequisitos

- SaviaHub inicializado: `[ -d "$SAVIA_HUB_PATH/.git" ]`
- Cliente y proyecto existen: `[ -d "$SAVIA_HUB_PATH/clients/$CLIENT/projects/$PROJECT" ]`
- Si no existe `backlog-snapshots/` → crear

## Flujo: Snapshot

1. Detectar fuente del backlog (por orden de prioridad):
   - `AZURE_DEVOPS_ORG_URL` → Azure DevOps (WIQL query)
   - `JIRA_BASE_URL` → Jira (JQL query)
   - `GITLAB_URL` → GitLab (Issues API)
   - Directorio `backlog/` en proyecto → Savia Flow
   - Ninguno → modo manual (PM dicta items)
2. Extraer items: ID, título, estado, asignado, estimación (horas), prioridad, tags
3. Generar timestamp: `date -u +%Y%m%d-%H%M%S`
4. Crear directorio si no existe: `mkdir -p backlog-snapshots/`
5. Escribir snapshot markdown con frontmatter YAML + tabla
6. Calcular resumen: total, por estado, estimación total
7. Commit: `[backlog-git] snapshot: $CLIENT/$PROJECT ($TOTAL items)`
8. Si remote + no flight-mode → push (delegar a savia-hub-sync)
9. Mostrar banner con resumen

## Flujo: Diff

1. Resolver referencias:
   - Sin flags → último vs penúltimo snapshot
   - `--from YYYYMMDD` → buscar snapshot con prefijo
   - Índice numérico (`-1`, `-2`) → contar desde el más reciente
2. Parsear ambos snapshots: extraer frontmatter + tabla → mapa ID→item
3. Calcular deltas:
   - Añadidos: `IDs(to) - IDs(from)`
   - Eliminados: `IDs(from) - IDs(to)`
   - Modificados: `IDs(from) ∩ IDs(to)` con campos diferentes
4. Para cada modificado, registrar: campo, valor anterior, valor nuevo
5. Calcular métricas: scope change %, re-estimación total Δh
6. Mostrar diff formateado con banner 📊

## Flujo: Rollback (solo informe)

1. Cargar snapshot referenciado → parsear items
2. Obtener estado actual (último snapshot o query al PM tool)
3. Generar diff inverso: qué acciones serían necesarias
4. Listar acciones en formato checklist:
   - `[ ] Restaurar item #{ID}: "{título}"`
   - `[ ] Revertir estado de #{ID}: {actual} → {original}`
   - `[ ] Revertir estimación de #{ID}: {actual}h → {original}h`
5. **NUNCA ejecutar** — solo informar al PM
6. Guardar informe en `output/` si se solicita

## Flujo: Deviation Report

1. Listar todos los snapshots: `ls backlog-snapshots/*.md | sort`
2. Parsear serie temporal: para cada snapshot, extraer total, por estado, estimación
3. Calcular métricas acumuladas:
   - Scope creep: `(items_final - items_inicial) / items_inicial × 100`
   - Re-estimación: `Σ deltas de estimación`
   - Completion trend: `closed/total` por snapshot
   - Velocity: items cerrados entre snapshots consecutivos
4. Generar gráfico ASCII de evolución (items totales, cerrados, estimación)
5. Guardar en `output/YYYYMMDD-deviation-{client}-{project}.md`
6. Mostrar resumen con banner 📈

## Snapshot manual

Cuando no hay PM tool conectado:
1. Pedir al PM lista de items (puede ser informal)
2. Estructurar en tabla con IDs secuenciales (M001, M002...)
3. Pedir confirmación antes de guardar
4. Mismo flujo de commit/push

## Errores

| Error | Acción |
|-------|--------|
| SaviaHub no existe | Sugerir `/savia-hub init` |
| Cliente no existe | Sugerir `/client-create` |
| Proyecto no existe | Sugerir `/client-edit {slug}` + añadir proyecto |
| Sin snapshots | Sugerir `/backlog-git snapshot` primero |
| PM tool no accesible | Ofrecer snapshot manual |

## Seguridad

- Snapshots son append-only: NUNCA modificar uno existente
- NUNCA ejecutar rollback automático — solo informar
- NUNCA incluir tokens o credentials en snapshots
- Confirmar con PM antes de push al remote

Attribution

gonzalezpazmonicagonzalezpazmonica
View sourceSee grades on GitHubMore from gonzalezpazmonica →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →