skills/claude-status/SKILL.md
# Session Status Skill Shows active Claude sessions across all projects with key metadata. ## Usage ```bash /claude-status # Show all active sessions /claude-status --here # Show only current project sessions /claude-status --clean # Identify stale/abandoned sessions ``` ## Output Format ``` Active Sessions (7 total) ═══════════════════════════════════════════════════════════ sim2d /home/midori/_dev/sim2d ├─ docs-modularity 2h ago 3 uncommitted [RES
npx skillsauth add api-haus/my-claude-workflow skills/claude-statusInstall 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.
Shows active Claude sessions across all projects with key metadata.
/claude-status # Show all active sessions
/claude-status --here # Show only current project sessions
/claude-status --clean # Identify stale/abandoned sessions
Active Sessions (7 total)
═══════════════════════════════════════════════════════════
sim2d /home/midori/_dev/sim2d
├─ docs-modularity 2h ago 3 uncommitted [RESUME]
├─ crate-merge 30m ago clean [RESUME]
└─ main 2d ago 5 uncommitted [STALE?]
p7 /home/midori/_dev/p7
├─ player-api-tests 4h ago clean [RESUME]
└─ game-api 1d ago 2 uncommitted [STALE?]
Unreal/UE_5.7 /mnt/archive4/UNREAL/UE_5.7
└─ fab-plugin-fix 6h ago clean [RESUME]
⚠️ 2 stale sessions (>24h, uncommitted changes)
💡 Run `/claude-status --clean` to identify for cleanup
This skill is read-only. It never modifies sessions or code.
Use /resume manually after reviewing status.
data-ai
Extract research content from YouTube presentations, PDFs, or PPTX files into structured markdown. Dispatches each pass to a dedicated sub-agent (research-extractor / research-vision / research-refiner) so per-deck vision passes scale to hundreds of slides without bloating the parent context.
development
Build, run, and analyze Unity profiler data with perf-report-style call-stack attribution
documentation
Write a handoff prompt for a future session. A handoff is a continuation-link — minimal context plus a kickoff line the user can copy-paste. Never a diagnosis, never an investigation script, never a prescribed deliverable.
testing
Multi-agent orchestration mode. The orchestrator never reads, edits, runs, or tests directly — it scopes work, runs a re-implementation audit, presents a freeform method brief with grounded recommendations, then dispatches every step to sub-agents through shared context files at `docs/orchestrate/<topic>/`. Use when invoked via /delegate, when the user asks to orchestrate or coordinate multi-agent work, or when the task explicitly calls for delegation.