Use when you need to fully restore working context from a previous session - loads STATUS.json, reads key files, rebuilds mental model of current work state. Do NOT use for quick questions or when starting fresh unrelated work - the full context restoration adds overhead that isn't needed for standalone tasks.
/plugin marketplace add jrc1883/popkit-claude/plugin install popkit@popkit-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
scripts/find_context.pyworkflows/restore-workflow.jsonFully restore working context when resuming after a break. Goes beyond STATUS.json to rebuild complete understanding.
Core principle: Don't just know what to do - understand why and how.
Trigger: After session-resume for Fresh Start sessions, or manual deep restore
Read and parse the status file:
# See what's changed
git status
# Review recent commits for context
git log --oneline -10
# See uncommitted changes
git diff --stat
Based on focus area, read relevant files:
If working on feature:
If debugging:
If refactoring:
# Run tests to verify state
npm test
# Check for lint errors
npm run lint
# Verify build passes
npm run build
Construct understanding:
## Current Context
### What We're Building
[Feature description from STATUS.json focus area]
### Where We Are
- Branch: [branch name]
- Last commit: [commit message]
- Uncommitted: [files and their purpose]
### Key Files
- `path/to/main.ts` - [what it does, current state]
- `path/to/test.ts` - [test coverage status]
### Decisions Made
- [Decision 1 from keyDecisions]
- [Decision 2]
### What's Next
1. [nextAction from STATUS.json]
2. [Logical following step]
### Potential Issues
- [Any warnings from tests/lint]
- [Any blockers noted]
Present restored context and options:
Context fully restored. Here's where we are:
[Mental model summary]
Ready to continue. Options:
1. Proceed with: [next action]
2. Review specific file first
3. Run full test suite
4. See detailed task breakdown
What would you like to do?
For complex projects or long breaks:
š Full Context Restore
Loading STATUS.json...
ā Project: my-app
ā Branch: feature/user-auth
ā Focus: Authentication system
Reviewing git state...
ā Last commit: a7f3c2e - feat: add login form
ā 2 uncommitted files:
- src/auth/reset.ts (new)
- src/auth/reset.test.ts (new)
Reading key files...
ā src/auth/login.ts - Login form complete
ā src/auth/reset.ts - Password reset in progress (50%)
ā Tests: 45 passing, 0 failing
Mental Model:
- Building password reset flow
- Login and validation complete
- Reset flow needs: email template, token generation
- Using nodemailer (decided last session)
Next action: Add forgot password email template
Ready to continue?
Use context-restore when:
Skip context-restore when:
Pairs with:
Calls:
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.