@mediadatafusion/pi-workflow-suite 0.0.1

package/skills/git-safe-summary/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: git-safe-summary
+description: Generate safe git status, diff summaries, changed file summaries, and commit message suggestions without committing or pushing. Use after execution or validation.
+---
+
+# Git Safe Summary
+
+Summarize git status and diffs without committing, pushing, resetting, cleaning, switching branches, or staging files unless explicitly requested by the user outside this workflow.
+
+Mermaid diagrams are rendered by Workflow Suite in a uniform dark-mode visual style. For user-facing workflows, export/share paths, request lifecycles, architecture, data flow, multi-step sequences, state transitions, dependencies, validation flow, or implementation phases, include a meaningful Mermaid diagram plus concise prose unless the user requested prose only or the response is trivial. Use concise labels and the right diagram type; do not hardcode random style/classDef/light-theme overrides unless the user explicitly asks.
+## Professional Constraints
+
+- Check project instructions before recommendations when the task touches code, docs, settings, or workflow behavior.
+- Keep scope bounded to the user request and approved workflow phase.
+- Do not print secrets, credentials, tokens, auth/session values, private runtime state, or `.env` contents.
+- Avoid destructive commands, deploys, pushes, resets, cleans, database mutations, and dependency installs unless explicitly approved outside this workflow.
+- Prefer concise, evidence-based output with exact files or commands reviewed.
+## Skills vs Agents
+
+Use this skill as in-process guidance for the current model. Use a sub-agent only when the task benefits from an isolated context window, parallel read-only research, forced preflight, or independent validation. Do not use both this skill and a same-purpose agent for the same narrow job unless the workflow or user explicitly requires it.

package/skills/implementation-planning/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: implementation-planning
+description: Convert a user task into an execution-ready implementation plan with assumptions, risks, files likely to change, validation steps, rollback notes, and approval readiness. Use during Plan Mode.
+---
+
+# Implementation Planning
+
+Produce concrete plans only. Ask follow-up questions when required. Include task summary, assumptions, files likely to change, off-limits files, implementation steps, risks, validation steps, rollback notes, and readiness status.
+
+Mermaid diagrams are rendered by Workflow Suite in a uniform dark-mode visual style. For user-facing workflows, export/share paths, request lifecycles, architecture, data flow, multi-step sequences, state transitions, dependencies, validation flow, or implementation phases, include a meaningful Mermaid diagram plus concise prose unless the user requested prose only or the response is trivial. Use concise labels and the right diagram type; do not hardcode random style/classDef/light-theme overrides unless the user explicitly asks.
+## Professional Constraints
+
+- Check project instructions before recommendations when the task touches code, docs, settings, or workflow behavior.
+- Keep scope bounded to the user request and approved workflow phase.
+- Do not print secrets, credentials, tokens, auth/session values, private runtime state, or `.env` contents.
+- Avoid destructive commands, deploys, pushes, resets, cleans, database mutations, and dependency installs unless explicitly approved outside this workflow.
+- Prefer concise, evidence-based output with exact files or commands reviewed.
+## Skills vs Agents
+
+Use this skill as in-process guidance for the current model. Use a sub-agent only when the task benefits from an isolated context window, parallel read-only research, forced preflight, or independent validation. Do not use both this skill and a same-purpose agent for the same narrow job unless the workflow or user explicitly requires it.

package/skills/project-rules-audit/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: project-rules-audit
+description: Find and respect project rules such as AGENTS.md, CLAUDE.md, README.md, .cursor/rules, .factory/rules, .pi, and .env.example before planning or execution.
+---
+
+# Project Rules Audit
+
+Before planning or execution, look for project instructions and safety rules. Check AGENTS.md, CLAUDE.md, README.md, .cursor/rules, .factory/rules, .pi, and .env.example. Preserve project-specific conventions and do not override existing agent rules.
+
+Mermaid diagrams are rendered by Workflow Suite in a uniform dark-mode visual style. For user-facing workflows, export/share paths, request lifecycles, architecture, data flow, multi-step sequences, state transitions, dependencies, validation flow, or implementation phases, include a meaningful Mermaid diagram plus concise prose unless the user requested prose only or the response is trivial. Use concise labels and the right diagram type; do not hardcode random style/classDef/light-theme overrides unless the user explicitly asks.
+## Professional Constraints
+
+- Check project instructions before recommendations when the task touches code, docs, settings, or workflow behavior.
+- Keep scope bounded to the user request and approved workflow phase.
+- Do not print secrets, credentials, tokens, auth/session values, private runtime state, or `.env` contents.
+- Avoid destructive commands, deploys, pushes, resets, cleans, database mutations, and dependency installs unless explicitly approved outside this workflow.
+- Prefer concise, evidence-based output with exact files or commands reviewed.
+## Skills vs Agents
+
+Use this skill as in-process guidance for the current model. Use a sub-agent only when the task benefits from an isolated context window, parallel read-only research, forced preflight, or independent validation. Do not use both this skill and a same-purpose agent for the same narrow job unless the workflow or user explicitly requires it.

package/skills/safe-execution/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: safe-execution
+description: Keep code changes bound to an approved plan, avoid unrelated refactors, respect off-limits files, and summarize changed files. Use during Execute Mode.
+---
+
+# Safe Execution
+
+Execute only the approved plan. Restate expected files before editing. Prefer surgical edits. Do not commit, push, switch branches, install dependencies, deploy, or run destructive commands. Stop and ask if the approved plan is insufficient.
+
+Mermaid diagrams are rendered by Workflow Suite in a uniform dark-mode visual style. For user-facing workflows, export/share paths, request lifecycles, architecture, data flow, multi-step sequences, state transitions, dependencies, validation flow, or implementation phases, include a meaningful Mermaid diagram plus concise prose unless the user requested prose only or the response is trivial. Use concise labels and the right diagram type; do not hardcode random style/classDef/light-theme overrides unless the user explicitly asks.
+## Professional Constraints
+
+- Check project instructions before recommendations when the task touches code, docs, settings, or workflow behavior.
+- Keep scope bounded to the user request and approved workflow phase.
+- Do not print secrets, credentials, tokens, auth/session values, private runtime state, or `.env` contents.
+- Avoid destructive commands, deploys, pushes, resets, cleans, database mutations, and dependency installs unless explicitly approved outside this workflow.
+- Prefer concise, evidence-based output with exact files or commands reviewed.
+## Skills vs Agents
+
+Use this skill as in-process guidance for the current model. Use a sub-agent only when the task benefits from an isolated context window, parallel read-only research, forced preflight, or independent validation. Do not use both this skill and a same-purpose agent for the same narrow job unless the workflow or user explicitly requires it.

package/skills/validation-review/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: validation-review
+description: Review implementation against an approved plan and return PASS, PARTIAL PASS, or FAIL with missing requirements, unexpected changes, risks, and test/build status. Use during Validator Mode.
+---
+
+# Validation Review
+
+Use read-only review. Compare changed files and implementation behavior against the approved plan. Report PASS, PARTIAL PASS, or FAIL. Include coverage, missing requirements, unexpected changes, regression risks, test/build status, and next action.
+
+Mermaid diagrams are rendered by Workflow Suite in a uniform dark-mode visual style. For user-facing workflows, export/share paths, request lifecycles, architecture, data flow, multi-step sequences, state transitions, dependencies, validation flow, or implementation phases, include a meaningful Mermaid diagram plus concise prose unless the user requested prose only or the response is trivial. Use concise labels and the right diagram type; do not hardcode random style/classDef/light-theme overrides unless the user explicitly asks.
+## Professional Constraints
+
+- Check project instructions before recommendations when the task touches code, docs, settings, or workflow behavior.
+- Keep scope bounded to the user request and approved workflow phase.
+- Do not print secrets, credentials, tokens, auth/session values, private runtime state, or `.env` contents.
+- Avoid destructive commands, deploys, pushes, resets, cleans, database mutations, and dependency installs unless explicitly approved outside this workflow.
+- Prefer concise, evidence-based output with exact files or commands reviewed.
+## Skills vs Agents
+
+Use this skill as in-process guidance for the current model. Use a sub-agent only when the task benefits from an isolated context window, parallel read-only research, forced preflight, or independent validation. Do not use both this skill and a same-purpose agent for the same narrow job unless the workflow or user explicitly requires it.