Install
$ agentstack add skill-robabby-claude-skills-pickup ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Pickup Prompt Generator
Generate a handoff prompt that allows resuming work in a fresh session.
Output Format
Output the prompt in a fenced code block so the user can copy it:
## Session Pickup
### Goal
[One sentence: what we're trying to accomplish]
### Context
[2-3 sentences: relevant background the next session needs]
### Progress
- [Completed item 1]
- [Completed item 2]
- ...
### Key Decisions
- [Decision]: [Brief rationale]
- ...
### Current State
[What's the immediate situation? What file/task were we in the middle of?]
### Next Steps
1. [Immediate next action]
2. [Following action]
3. ...
### Open Questions
- [Any unresolved questions or blockers]
Guidelines
- Be specific: Include file paths, function names, exact values—not vague descriptions
- Capture rationale: For decisions, briefly note WHY, not just what
- Prioritize recency: Recent context matters more than early conversation
- Skip the obvious: Don't include information Claude would know from the codebase
- Include blockers: Note anything that was blocking progress or needs investigation
- Keep it scannable: Use bullets and short phrases, not paragraphs
What to Include
| Include | Skip | |---------|------| | Current task and subtasks | General pleasantries | | Files modified or key files referenced | Files just briefly mentioned | | Decisions made and their rationale | Exploratory dead-ends (unless informative) | | Blockers or open questions | Resolved issues | | Next concrete steps | Vague future plans | | Error messages if debugging | Successful outputs |
Example Output
## Session Pickup
### Goal
Add a `/pickup` skill to generate session handoff prompts before /clear.
### Context
Working in Rob's PKM vault. Skills live in `~/.claude/skills/`. Using the skill-creator skill as a guide for proper skill structure.
### Progress
- Clarified requirements: output to clipboard, focus on task state, name it "pickup"
- Initialized skill at `/Users/rob/.claude/skills/pickup`
- Removed unneeded example directories
### Key Decisions
- No scripts/references/assets needed: pure workflow skill
- Task-state focus over full-context: keeps prompts concise and actionable
### Current State
Writing SKILL.md content. Need to complete the instructions and package the skill.
### Next Steps
1. Finish writing SKILL.md
2. Package with package_skill.py
3. Test by invoking /pickup
### Open Questions
- None currently
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: robabby
- Source: robabby/claude-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.