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

Devops Validation

ASecurity

Usar cuando se conecta un proyecto nuevo a Azure DevOps para validar su configuración Agile.

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

Works with

api

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 10/4/2026

$npx -y skills add gonzalezpazmonica/savia --skill devops-validation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Devops Validation?

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

Security grade badge for Devops Validation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gonzalezpazmonica-devops-validation/badge)](https://www.skillsdirectory.com/skills/gonzalezpazmonica-devops-validation)

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: devops-validation
description: Usar cuando se conecta un proyecto nuevo a Azure DevOps para validar su configuración Agile.
metadata:
  # --- metadata.savia.* (SE-333) ---
  savia.agent: azure-devops-operator
  savia.maturity: beta
  savia.category: devops
  savia.context: fork
  savia.context_cost: low
  savia.priority: medium
  savia.summary: "Valida configuracion de Azure DevOps contra requisitos Agile ideales. Comprueba areas, iteraciones, campos custom, politicas de branch. Output: informe de gaps + plan de remediacion."
  savia.tags: "validation, azure-devops, agile, configuration"
---

# Skill: devops-validation

> Audits an Azure DevOps project to verify it matches pm-workspace's "ideal Agile" configuration. Generates a remediation plan for manual approval if mismatches are found.

**Prerequisite:** Read `.opencode/skills/azure-devops-queries/SKILL.md` first.

---

## When to Invoke

- PM connects a new project to pm-workspace (provides org URL, project, team, PAT)
- PM runs `/devops-validate --project {p} [--team {t}]`
- Before first `/sprint-status` or `/pbi-decompose` on a new project

---

## What Gets Validated

8 checks, in order — each returns PASS / WARN / FAIL:

| # | Check | What | FAIL if | WARN if |
|---|---|---|---|---|
| 1 | Connectivity | PAT can reach org | HTTP != 2xx or no network | — |
| 2 | Project | Project name exists | Not found (404) | — |
| 3 | Process | Template (or its parent) is Agile | Basic, CMMI or unknown | Scrum |
| 4 | Types | Epic, Feature, User Story, Task, Bug | Any missing | — |
| 5 | States | US/Bug: New, Active, Resolved, Closed · Task: New, Active, Closed | Required state missing | — |
| 6 | Fields | StoryPoints, RemainingWork, etc. per type | — | Required field missing (queries return nulls) |
| 7 | Backlog | User Story in requirements backlog + bugs as requirements | — | Either condition unmet |
| 8 | Iterations | Team sprints have start dates | No iterations at all | Iterations without dates |

**Fail-closed:** in any check, an API error (HTTP non-2xx, no network) or a response that is not a JSON object is FAIL with message `API request failed: <reason>`. A crashed check is recorded as FAIL. Network or credential problems never produce PASS or WARN.

Full field/state mapping: → `references/ideal-agile-config.md`

---

## Running the Validation

```bash
scripts/validate-devops.sh \
  --project "ProjectName" \
  --team "ProjectName Team" \
  --output output/devops-validation.json
```

Returns JSON report to stdout and optionally to file (directory created). Logs go to stderr.

- `--team` defaults to `"{project} Team"`. Project, team and type names are URL-encoded, so names with spaces work.
- `AZURE_DEVOPS_ORG_URL` is required: the placeholder default (`MI-ORGANIZACION`) is rejected before any request.
- PAT from `AZURE_DEVOPS_PAT_FILE` (default `~/.azure/devops-pat`); empty or missing file is rejected. The PAT reaches curl through stdin (`curl -K -`), never as a process argument, and never appears in logs or in the report. Long PATs (84 chars) are supported.

**Exit codes:** `0` no FAIL (PASS/WARN only) · `1` at least one FAIL · `2` usage or configuration error (missing PAT, placeholder org URL, bad arguments); no report is emitted. `--help` works without PAT or network.

---

## Interpreting Results

**All PASS** → Project is ready for pm-workspace. Proceed with `/sprint-status` or `/pbi-decompose`.

**Any WARN** → Non-blocking issues. WIQL queries will work but some fields may return null or behavior may differ. List warnings to PM with remediation steps.

**Any FAIL** → Blocking issues. Generate remediation plan for PM approval:
1. List each FAIL with its `remediation` field
2. Group by action type (process change, type addition, etc.)
3. All changes require manual execution in Azure DevOps UI
4. After PM applies changes → re-run `/devops-validate` to confirm

---

## Remediation Categories

| Category | Action Required | Where |
|---|---|---|
| Process template | Change to Agile | Organization Settings > Process |
| Missing types | Add via inherited process or migrate | Organization Settings > Process |
| Missing states | Customize via inherited process | Organization Settings > Process |
| Missing fields | Add to WIT layout | Organization Settings > Process > WIT |
| Bug behavior | Change to "as requirements" | Project Settings > Boards > Team config |
| No iterations | Create sprints with dates | Project Settings > Iterations |

---

## JSON Report Schema

```json
{
  "project": "PM-Workspace",
  "team": "PM-Workspace Team",
  "org": "https://dev.azure.com/OrgName",
  "timestamp": "2026-02-28T10:00:00Z",
  "summary": { "total": 8, "pass": 6, "fail": 1, "warn": 1 },
  "checks": [
    {
      "check": "process",
      "status": "FAIL",
      "message": "Process Basic not compatible",
      "remediation": "Organization Settings > Process > Change to Agile"
    }
  ]
}
```

---

## References

- `references/ideal-agile-config.md` — Complete field/state/type mapping
- `../azure-devops-queries/references/wiql-fields.md` — WIQL field reference
- Command: `/devops-validate`
- Scripts: `scripts/validate-devops.sh`, `scripts/validate-devops-checks.sh`

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', ...

698461 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 →