debug_agent_traces
Debug props agent traces. Read LLM request/response history, parse tool calls, and "speak with dead" — resurrect a past agent conversation to ask follow-up questions about its decisions.
narrow_matchability
Propose narrowing of grader match_file_restriction for unrestricted TP/FP occurrences in a specimen. Produces verifiable, link-rich output that lets the user confirm each restriction is correct.
props_evaluator
Operate the live props cluster as evaluator — fetch credentials from k8s, call the API at props.allegedly.works, trigger critic/grader runs, and inspect results.
cihealth
>
web_selfcheck
>
test_props
Manual live props deployment testing — sets up Podman infrastructure (postgres, registry, backend) and runs real agent containers. NOT for standard Bazel tests (use `bazel test //props/...` for those).
update_container_re
Update the Claude Code web container reverse engineering effort. Detects changed binaries, captures new references, runs parallel RE subagents for bindiff/decompilation, updates container snapshot/diff, and refreshes all documentation.
cluster_health
Scan cluster health — Flux kustomizations, pod status, recurring crashes, node conditions, active Alertmanager alerts, CNPG databases, certificate expiry — and output an actionable summary with fix plan. Use when user asks "how's the cluster", "cluster health", "what's broken", "check the cluster", or similar.
cnpg_region_switch
Migrate a single-instance CNPG PostgreSQL cluster between regions or region-pinned storage classes via streaming replication with sub-second downtime
flux_reconcile_audit
Audit every Flux Kustomization + HelmRelease over a window (default 7d) and classify each into Broken / Slow-but-converges / Miswired-but-converges / Propagating / Suspended / Healthy. Per non-healthy item, surface the underlying-resource culprit (parsed from Flux's own condition message), the in-window failure/success counts, the p99 reconcile duration, and a label-selector probe of objects this Kustomization manages. Use when the user asks "what's slow", "what's stuck", "what's been broken this week", or wants targeted attribution of reconciliation lag.
hetzner_vnc_screenshot
Take and view screenshots of Hetzner Cloud servers via WebSocket VNC console. Use to diagnose issues when text commands fail — boot problems, unresponsive servers, kernel panics, stuck boot screens, graphical output inspection.
proxmox_vm
Interact with Proxmox VMs - screenshots, keystrokes, network info (user)
cpap
>
buildbuddy_api
>
startup-hook-skill
Creating and developing startup hooks for Claude Code on the web. Use when the user wants to set up a repository for Claude Code on the web, create a SessionStart hook to ensure their project can run tests and linters during web sessions.
workspace-gc
>
debundle_architect
Audit a debundle spec's named modules for idiomatic JavaScript structure, infer project conventions from source behavior, and maintain current-state architecture notes and reorganization recommendations. Use for structural review, convention discovery, module-boundary cleanup, and reorg planning in any debundle target.
debundle_intake
Turn `debundle modules propose` output into named, dispatchable seed clusters for debundle lane workers. Use for reading factorizer proposals, lightly grounding source meaning, choosing tentative destinations, and producing seeds.json without editing the spec or running gates.
debundle_integrator
Integrate multiple debundle lane-worker branches through a validated merge train. Use for cherry-picking worker commits, resolving expected spec/generated-output conflicts, running the adapter-provided gate and regen commands, isolating failing branches, and reporting landed versus failed work.
debundle_lane_worker
Apply one scoped debundle module-assignment or reorganization task in a worktree. Use for confirming atomic-DAG unit coverage, reading binding context, choosing honest module boundaries, editing debundle YAML (directly or via `debundle bindings assign` / `bindings rename` / `modules merge`), running the adapter-provided gate and regen commands, and committing one reviewable worker branch.
debundle_mint_names
>
debundle_orchestrator
Coordinate a generic AI-driven debundling loop across intake, lane worker, architect, integrator, planning, and naming skills. Use for multi-agent debundle rounds, work routing, graph refreshes, gate/regen command broadcast, progress tracking, and adapter-specific workflow control.
debundle_plan_work
Plan and inspect generic JS debundle spec work using read-only `debundle` queries. Use when an agent needs to turn owner_graph.json plus a modules tree into dispatchable module extraction work, query atomic-DAG and coverage status, inspect graph/source context, or decide what debundle spec edits should be made. Generic to any debundle target.
debundle_stabilize
>
forensic-surgeon
Deep forensic debugging that never stops until root cause is found or visibility limit is proven. Use when user wants to understand exactly why something is broken, not work around it. Activates on "why is this happening", "dig deeper", "don't work around it", "I want to understand", "find the root cause", "this seems suspicious", or when a problem suggests deeper breakage.
hetzner-vnc-screenshot
Take and view screenshots of Hetzner Cloud servers via WebSocket VNC console
proxmox-vm
Interact with Proxmox VMs - screenshots, keystrokes, network info (user)
session-logs
Discover and analyze Claude Code session logs from ~/.claude/projects, including finding the current session and extracting tool calls, user messages, and conversation history
superforecaster
Make well-calibrated probability estimates using superforecasting methodology. Use when user asks about probability, likelihood, chance, odds, "will X happen", "when will X happen", "how much will X cost", "what could go wrong", failure modes, risk assessment, forecasting, or any question involving uncertainty and estimation.
backtrace
Show the current task stack and context. Use when user says "bt", "backtrace", "stack", "where are we", or asks about current progress on a multi-step task.
branch_splitter
Split a large branch with many changes into independent, reviewable PRs. Use when preparing a messy development branch for code review, when asked to "split this into PRs", "make this reviewable", "break this up", or when a branch does too many unrelated things. Produces a DAG of branches/PRs that can be reviewed and merged independently.
empty_skill
Eval-only stub skill. Contains no guidance — used as the "skill off" baseline arm so the sandbox shape stays uniform across `--skill on/off` rollouts.
followups
>
forensic_surgeon
Deep forensic debugging that never stops until root cause is found or visibility limit is proven. Use when user wants to understand exactly why something is broken, not work around it. Activates on "why is this happening", "dig deeper", "don't work around it", "I want to understand", "find the root cause", "this seems suspicious", or when a problem suggests deeper breakage.
freecad-sketcher
Use this skill for parametric 2D/3D technical drawings using FreeCAD Sketcher and TechDraw. Triggers when the user wants constrained parametric floor plans, mechanical sketches, layout diagrams, or any drawing where dimensions drive geometry. Also use when the user mentions FreeCAD, .FCStd files, Sketcher, TechDraw, parametric CAD, or technical drawings. Use this skill even for seemingly simple 2D layouts — the parametric constraint approach prevents coordinate drift and makes edits safe. Always read this skill before writing any FreeCAD scripting code.
ground-skill
>
info-gathering
>
later
Record a TODO item persistently in the repo (TODO.md, PLAN.md, or GitHub issue). PRIORITY - execute immediately, preempting any in-progress work. Use when user says "/later <thing>".
lint_audit
Audit and improve linter/checker configuration across any repo and language. Discovers languages, proposes useful checks to enable with real examples, creates PRs for approved checks, documents rejected ones. Also fixes misconfigurations, updates outdated versions, removes stale exclusions, and proposes tightenings.
mcp-design
Design an MCP server tool surface for an AI agent. Starts from common workflows, derives tool schemas, audits for completeness and safety. Use when designing a new MCP server or redesigning an existing one.
pave
>
readback
>
reverse_engineer
Systematic binary reverse engineering toolkit. Extract source code, understand functions, document protocols, compare versions. Uses strings, symbols, disassembly, and differential verification.
session_logs
Discover and analyze Claude Code session logs from ~/.claude/projects, including finding the current session and extracting tool calls, user messages, and conversation history
update_deps
>
verify-docs
Verify documentation claims against actual code, finding and fixing stale or incorrect docs. Audit docs for token efficiency — cut what strong LLMs already know, keep local specifics and gotchas. Use when asked to review docs, trim docs, or check docs are accurate.
forgejo
Inspect Forgejo repositories through the REST API and web endpoints, especially Actions CI, task/run metadata, logs, package registry tags, haku-state CI, and Flux/image rollout debugging. Use when diagnosing Forgejo Actions failures, missing logs, branch badge state, package/image publish gaps, or when endpoint shape is unclear.
google-photos-link
>-
ikea-3d-models
>-
knowledge_hygiene
Audit documentation, notes, runbooks, wiki-style knowledge bases, prompts, comments, UI/help copy, and other natural-language information systems for SSOT drift, duplication, stale claims, unclear ownership, and maintenance gaps. Produce prioritized, evidence-backed improvement suggestions with stable shorthand IDs like A, B, C so the user can choose what to execute.