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/vyzn-tech-mandatory-gates
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
Use cases: writing
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/mandatory-gates
What's inside
- Skill name
mandatory-gates- Description
- Pre-implementation gates. MUST be followed before writing any code. Investigation, confidence assessment, and scope confirmation.
- License
- MIT
- Instructions
- 51 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Mandatory Gates (Before ANY Code) These gates are MANDATORY and must not be skipped. ## Gate 1: Investigation > **Think as a Product Owner.** Your goal is to understand the USER's problem, not find the code fix. - Read the ticket/issue fully (description, repro steps, acceptance criteria) - **Identify the affected user workflow** — which user role is impacted? What were they trying to accomplish? - **Assess business impact** — how many users are affected? Is there a workaround? - Explore the codebase to understand the affected area - Download and review any attached screenshots or logs ## Gate 2: Confidence Assessment > **Still thinking as Product Owner.** Confidence means "Do I understand what the user needs?" — NOT "Can I write the code?" State: **"My confidence level: X/10"** Evaluate: - Do I understand the **user's problem** (not just the technical symptom)? - Are the **acceptance criteria** clear and testable? - Do I know the **scope boundaries** (what's in vs. out)? - Could this change **break other user workflows**? - **< 8/10**: STOP immediately. Ask clarifying questions about requirements. - **>= 8/10**: Continue to Gate 3. ## Gate 3: Scope Confirmation (NEVER SKIP) > **Present your understanding as a Product Owner, not as a developer.** 1. State your proposed approach in **business terms first**, then technical approach 2. List what's in scope and what's out of scope 3. Estimate the complexity (trivial / small / medium / large) 4. Ask: **"Please confirm this scope"** 5. **WAIT for human confirmation** before writing any code Include `<!-- WAITING_FOR_HUMAN -->` at the end of your response. ## After Gates: Switch to Developer Mode > From here on, **think as a Senior Developer.** Focus on clean code, tests, and technical correctness. The PO work is done — you have confirmed scope and requirements. ## Important - These gates exist to prevent wasted effort and ensure alignment with requirements - Skipping Gate 3 is the #1 cause of rework
From vyzn-tech/po-agent, MIT.
More from vyzn-tech/po-agent
- 0.408score
merge-conflicts
vyzn-tech
Resolve merge conflicts by rebasing.
SkillDFreshness: DClaude Code +9 - 0.408score
ci-wait-resume
vyzn-tech
Wait for CI checks to complete inline.
SkillDFreshness: DClaude Code +9 - 0.404score
code-quality
vyzn-tech
Run pre-push validation before pushing code.
SkillDFreshness: DClaude Code +9 - 0.404score
playwright-verify
vyzn-tech
Browser verification using Playwright MCP.
SkillDFreshness: DClaude Code +9 - 0.404score
budget-management
vyzn-tech
Session cost tracking and optimization.
SkillDFreshness: DClaude Code +9 - 0.404score
bug-fix-workflow
vyzn-tech
9-phase workflow for fixing bugs.
SkillDFreshness: DClaude Code +9 - 0.404score
rfs-proposal
vyzn-tech
File a Request for Skill (RFS) when a skill gap is detected during execution.
SkillDFreshness: DClaude Code +9 - 0.404score
story-workflow
vyzn-tech
9-phase workflow for implementing user stories.
SkillDFreshness: DClaude Code +9 - 0.404score
review-handling
vyzn-tech
Process review comments from AI review or human reviewers.
SkillDFreshness: DClaude Code +9 - 0.401score
pr-creation
vyzn-tech
Create GitHub pull requests with proper format.
SkillDFreshness: DClaude Code +9 - 0.399score
code-quality
vyzn-tech
Run project-specific pre-push validation.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 1
- Last commit (this folder)
- Mar 1, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/vyzn-tech/po-agent
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from vyzn-tech
- 0.408score
merge-conflicts
vyzn-tech
Resolve merge conflicts by rebasing.
SkillDFreshness: DClaude Code +9 - 0.408score
ci-wait-resume
vyzn-tech
Wait for CI checks to complete inline.
SkillDFreshness: DClaude Code +9 - 0.404score
code-quality
vyzn-tech
Run pre-push validation before pushing code.
SkillDFreshness: DClaude Code +9 - 0.404score
playwright-verify
vyzn-tech
Browser verification using Playwright MCP.
SkillDFreshness: DClaude Code +9 - 0.404score
budget-management
vyzn-tech
Session cost tracking and optimization.
SkillDFreshness: DClaude Code +9 - 0.404score
bug-fix-workflow
vyzn-tech
9-phase workflow for fixing bugs.
SkillDFreshness: DClaude Code +9
Cite this page
mandatory-gates skill. Agent Mart. https://agentmart.dev/skills/vyzn-tech-mandatory-gates (last updated 2026-10-24)