skills/session-resume/SKILL.md
Session resume protocol and session repairs handling. Loaded when spellbook_session_init returns resume_available: true, or when session_init returns a repairs array. Triggers: 'resume', 'continue', 'where were we', session resume, session repairs.
npx skillsauth add axiomantic/spellbook session-resumeInstall 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.
When spellbook_session_init returns resume_available: true, follow this protocol exactly.
| Field | Type | Description |
| ------------------------- | ------ | ---------------------------------- |
| resume_available | bool | Recent session (<24h) exists |
| resume_session_id | string | Session soul ID |
| resume_age_hours | float | Hours since bound |
| resume_bound_at | string | ISO bind timestamp |
| resume_active_skill | string | Active skill (e.g., "develop") |
| resume_skill_phase | string | Skill phase (e.g., "DESIGN") |
| resume_pending_todos | int | Incomplete todo count |
| resume_todos_corrupted | bool | Todo JSON malformed |
| resume_workflow_pattern | string | Workflow (e.g., "TDD") |
| resume_boot_prompt | string | Section 0 boot prompt |
resume_boot_prompt IMMEDIATELY (Section 0 actions)--resume <phase> if active, Read() for planning docs, TodoWrite() for todo state, behavioral constraints from prior sessionIf resume_todos_corrupted: true: announce to user that todo state was malformed and requires manual restoration.
| Pattern | Intent | Action |
| ------------------------------------------- | ----------- | --------------------------------------------- |
| "continue", "resume", "where were we" | continue | Execute boot prompt |
| "start fresh", "new session", "clean slate" | fresh_start | Skip resume, return resume_available: false |
| "ok", "next", neutral message | neutral | Execute boot prompt (if session exists) |
When spellbook_session_init returns a repairs array, display each repair according to its severity:
| Severity | Action |
| --------- | --------------------------------------------------------- |
| error | Display prominently. These may affect functionality. |
| warning | Display as informational. Suggest the fix command. |
Welcome to spellbook-enhanced Claude.
Repairs needed:
- TTS is enabled but kokoro is not installed. Fix:
uv pip install 'spellbook[tts]'
testing
Use when creating new skills, editing existing skills, or verifying skills work before deployment. Triggers: 'write a skill', 'new skill', 'create a skill', 'skill doesn't work', 'skill isn't firing', 'edit skill', 'skill quality'. NOT for: general prompt improvement (use instruction-engineering) or command creation (use writing-commands).
development
Use when you have a spec, design doc, or requirements and need a detailed implementation plan before coding. Triggers: 'write a plan', 'create implementation plan', 'plan this out', 'break this down into steps', 'convert design to tasks', 'implementation order'. Also invoked by develop during planning. NOT for: reviewing existing plans (use reviewing-impl-plans).
testing
Use when creating new commands, editing existing commands, or reviewing command quality. Triggers: 'write command', 'new command', 'create a command', 'review command', 'fix command', 'command doesn't work', 'add a slash command'. NOT for: skill creation (use writing-skills).
development
Use when about to claim discovery during debugging. Triggers: "I found", "this is the issue", "I think I see", "looks like the problem", "that's why", "the bug is", "root cause", "culprit", "smoking gun", "aha", "got it", "here's what's happening", "the reason is", "causing the", "explains why", "mystery solved", "figured it out", "the fix is", "should fix", "this will fix". Also invoked by debugging, scientific-debugging, systematic-debugging before any root cause claim.