audit-orphan-runs
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.
$ npx -y skills add Samuel0101010/wisp-orchestrator --skill auto-doc --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/auto-docContext preview
The summary Claude sees to decide when to auto-load this skill.
Drafts a docs/solutions/YYYY-MM-DD-<slug>.md entry for a recently completed run, capturing problem/solution/lessons.
name: auto-doc description: Drafts a docs/solutions/YYYY-MM-DD-<slug>.md entry for a recently completed run, capturing problem/solution/lessons. model: sonnet allowed-tools: ["Read", "Write", "Bash"] argument-hint: "<run-id> <slug>" timeout-ms: 180000
Given the run-id and slug in the user message: 1. Read the run's events via the orchestrator 2. Read the latest commit message for the run's worktree (`git -C <worktree> log -1 --format=%B`) 3. Synthesize a docs/solutions entry with frontmatter:
--- date: <today YYYY-MM-DD> tags: [<2-5 kebab-case>] files: [<paths touched>] related: [] --- # <title> ## Problem ## Root cause ## Solution ## Verification ## Lessons
4. Write to `docs/solutions/<date>-<slug>.md`. Output the path.
Visual team-builder, plan-as-artifact, and live execution graph for autonomous Claude Code agent crews. Spawn a 3-role team, generate a DAG plan, run for hours, watch it ship in your browser.
Repo: Samuel0101010/wisp-orchestrator
Identifies abandoned worktrees and stale runs (no events for >2h, status=running) to flag for cleanup.
Working discipline for code-writing agents — read before edit, smallest correct change, run the gates before claiming done. Injected into builder roles' system…
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.
Visual + interaction quality bar for frontend roles — states, responsiveness, accessibility, consistency. Injected into frontend roles' system prompts.
Verification method for QA roles — execute, don't assume; report evidence, not impressions. Injected into QA roles' system prompts.