demo-use-case-skills

Audit deployed AI agent context artifacts for contradictions, duplications, and coverage gaps. Supports Claude Code, GitHub Copilot, and Cursor agents. Use proactively when the user says 'audit ai context'. Also use after bulk artifact updates, before onboarding, or on a regular cadence. Produces ai-context-issues-report.md at project root. Optionally transitions to packmind-update-playbook to create change proposals from the findings.

Analyze SonarQube issues for the current repository, identify the most violated coding rules, fetch their details, and propose Packmind playbook updates (standards, commands, skills) based on the findings. Use this skill when the user wants to set up coding context from SonarQube, import SonarQube rules into Packmind, or bridge static analysis findings with team coding standards. Triggers on requests like "setup context from sonar", "import sonar rules", "sync sonar issues to packmind", "analyze sonar issues".

Use when updating, adding, fixing, changing, or deprecating Packmind playbook artifacts (standards, commands, skills). Triggers on explicit phrases like "update packmind standard", "add a packmind skill", "fix packmind command", "change packmind playbook", "deprecate a standard". Also triggers when the conversation reveals an opportunity to update the playbook — e.g., a convention was established, a pattern emerged, a workflow changed, or an artifact is stale. This skill defines a mandatory workflow: do NOT edit artifact files directly — follow all phases (0→4) regardless of change size. Supports non-interactive mode via `CI=true` or `--non-interactive` for automated playbook updates from PR review findings.

Manually triggered skill that browses Notion documentation using Notion MCP tools, extracts coding practices and technical knowledge, classifies them for playbook relevance, and auto-invokes packmind-update-playbook with structured findings. Use when wanting to mine Notion pages for conventions, architectural decisions, best practices, or technical knowledge that should be captured in the Packmind playbook. Supports non-interactive mode via `CI=true` or `--non-interactive` for scheduled runs.

Manually triggered skill that analyzes Slack channel discussions using MCP tools, classifies them for playbook relevance, and auto-invokes packmind-update-playbook with structured findings. Use when wanting to mine Slack conversations for recurring patterns, conventions, decisions, or action items that should be captured in the Packmind playbook. Supports non-interactive mode via `CI=true` or `--non-interactive` for scheduled GitHub Actions runs.

Manually triggered skill that harvests merge request review comments from a GitLab project using MCP tools, classifies them for playbook relevance, and auto-invokes packmind-update-playbook with structured findings. Use when wanting to mine merged MR discussions for recurring patterns, missing conventions, or stale rules that should be captured in the Packmind playbook. Supports non-interactive mode via `CI=true` or `--non-interactive` for scheduled runs.

Manually triggered skill that harvests PR review comments from a GitHub repository using MCP tools, classifies them for playbook relevance, and auto-invokes packmind-update-playbook with structured findings. Use when wanting to mine merged PR reviews for recurring patterns, missing conventions, or stale rules that should be captured in the Packmind playbook. Supports non-interactive mode via `CI=true` or `--non-interactive` for scheduled GitHub Actions runs.

Manually triggered skill that analyzes recently resolved Jira issues using Atlassian MCP tools, classifies them for playbook relevance, and auto-invokes packmind-update-playbook with structured findings. Use when wanting to mine resolved Jira issues for recurring patterns, conventions, decisions, or action items that should be captured in the Packmind playbook. Supports non-interactive mode via `CI=true` or `--non-interactive` for scheduled runs.

Reference for Packmind CLI listing commands. This skill should be used when an agent needs to discover available standards, commands, or skills in the Packmind organization.

Manually triggered skill that browses Confluence documentation using Atlassian MCP tools, extracts coding practices and technical knowledge, classifies them for playbook relevance, and auto-invokes packmind-update-playbook with structured findings. Use when wanting to mine Confluence pages for conventions, architectural decisions, best practices, or technical knowledge that should be captured in the Packmind playbook. Supports non-interactive mode via `CI=true` or `--non-interactive` for scheduled runs.