core/capabilities/orchestration/sage-help/SKILL.md
Provides specific, actionable guidance on what to do next based on current project state. Reads progress files and context to give one clear next step. Use when the user says "help", "what do I do", "sage help", "what's next", "I'm stuck", or "status".
npx skillsauth add xoai/sage sage-helpInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Tell the user exactly what to do next. Not documentation. Not a feature list. Specific, actionable guidance based on WHERE THEY ARE right now.
Core Principle: A beginner should never feel lost. One command, one clear answer.
Check these files in order:
.sage/work/ frontmatter — what's the current phase?.sage/config.yaml — is Sage configured?.sage/ directory exists👋 This project isn't set up with Sage yet.
Say "set up sage" and I'll configure it (~2 minutes).
I'll detect your tech stack and set up quality guidance.
Or just tell me what you want to build — I'll set up as we go.
.sage/ exists, no active feature✅ Sage is configured. Ready to work.
What would you like to do?
• Describe a feature to build → I'll guide you through spec → plan → build
• Describe a bug to fix → I'll debug systematically and verify the fix
• Say "new project" → I'll help you start from scratch with architecture guidance
Your stack: [from config.yaml]
Active packs: [from config.yaml]
📋 Working on: [feature name]
Phase: Specification
Your spec is at: .sage/work/[YYYYMMDD-slug]/spec.md
[status: draft / awaiting approval / approved]
Next: [Review and approve the spec / Answer the remaining questions / Plan implementation]
📝 Working on: [feature name]
Phase: Planning
Plan: .sage/work/[YYYYMMDD-slug]/plan.md
[status: draft / awaiting approval / approved]
Next: [Review and approve the plan / Start implementation]
🔨 Working on: [feature name]
Phase: Implementation
Progress: [X] of [Y] tasks complete
Next task: Task [N]: [name]
Blocked: [any blocked tasks]
Next: [Implement Task N / Review completed work / Fix failing gate]
✅ Working on: [feature name]
Phase: Review
All [N] tasks complete. Running final quality review.
Next: [Address review feedback / Merge / Create PR]
If the user asks "sage help [specific question]", answer the question directly using knowledge of Sage's workflow, skills, and packs. Examples:
MUST (violation = useless help):
SHOULD (violation = suboptimal experience):
tools
Captures agent mistakes, corrections, and discovered gotchas so they are not repeated. Use when: (1) a command or operation fails unexpectedly, (2) the user corrects the agent, (3) the agent discovers non-obvious behavior through debugging, (4) an API or tool behaves differently than expected, (5) a better approach is found for a recurring task. Also searches past learnings before starting tasks to avoid known pitfalls. Activate alongside the sage-memory skill — they share the same MCP backend but serve different purposes (sage-memory = codebase knowledge, sage-self-learning = agent mistakes and gotchas).
development
Typed knowledge graph stored in sage-memory. Use when creating or querying structured entities (Person, Project, Task, Event, Document), linking related objects, checking dependencies, planning multi-step actions as graph transformations, or when skills need to share structured state. Trigger on "remember that X is Y", "what do I know about", "link X to Y", "show dependencies", "what blocks X", entity CRUD, cross-skill data access, or any request involving structured relationships between things.
tools
Integrates sage-memory into Sage workflows. Teaches the agent when to remember (store findings during work), when to recall (search memory at session start and task start), and how to learn (structured knowledge capture via sage learn). Use when the user mentions memory, remember, recall, learn, capture knowledge, onboard to codebase, or when starting any session where sage-memory MCP tools are available.
tools
Captures agent mistakes, corrections, and discovered gotchas so they are not repeated. Use when: (1) a command or operation fails unexpectedly, (2) the user corrects the agent, (3) the agent discovers non-obvious behavior through debugging, (4) an API or tool behaves differently than expected, (5) a better approach is found for a recurring task. Also searches past learnings before starting tasks to avoid known pitfalls. Activate alongside the sage-memory skill — they share the same MCP backend but serve different purposes (sage-memory = codebase knowledge, sage-self-learning = agent mistakes and gotchas).