Claude Skills by Samuel0101010

Use when the user asks to "review the agents", "review the subagents", "show me what each agent did", "show the per-agent diffs", "show me each subagent's changes", "open the agent review", "diff per agent", invokes the slash command `/review-agents`, or asks to "test wisp-agentdiff", "verify wisp-agentdiff", "check if wisp-agentdiff is working", "run wisp-agentdiff doctor", "prune wisp-agentdiff", "clean up wisp-agentdiff", or "garbage collect wisp-agentdiff worktrees". Triggers proactively ...

Identifies abandoned worktrees and stale runs (no events for >2h, status=running) to flag for cleanup.

Drafts a docs/solutions/YYYY-MM-DD-<slug>.md entry for a recently completed run, capturing problem/solution/lessons.

Conducts focused research on a topic by reading project files, searching memory, and synthesizing findings into a structured report.

Self-diagnostics for the harness — checks DB integrity, MCP wiring, claude binary availability, and recent run failures.

Compresses a long chat thread into a 5-bullet summary preserving decisions, action items, and unresolved questions.

Use when a WISP run failed unexpectedly or is stuck — fetches the event timeline for a run, highlights failures, and prints the verify-failed payloads with full output so the user can see exactly why a task failed. Trigger on phrases like "why did the run fail", "diagnose the harness", "what went wrong with the run".

Use when the user wants to inspect the result branch of a completed WISP run — shows files in the result branch, the per-task git log graph, and a brief summary. Trigger on phrases like "what did harness produce", "show the run output", "inspect the result branch".

Use when the user wants to create and start a new WISP run from a goal — handles project creation, optional template selection, plan generation, lock + run, and prints the run URL. Trigger on phrases like "start a harness run", "new agent run", "kick off a harness project".

Use when the user wants to resume a previously paused WISP run (e.g. paused by rate-limit, by /pause, or by an earlier shutdown). Lists resumable runs and resumes a chosen one. Trigger on phrases like "resume my run", "continue the harness", "pick up where we left off".