From atv-starter-kit
Small bug-fix lane with bounded diagnosis, agent-owned verification, and escalation. Use when the user reports a bug, failing test, broken behavior, or asks for a narrow fix that should not require a full brainstorm or plan unless it grows.
How this skill is triggered — by the user, by Claude, or both
Slash command
/atv-starter-kit:kb-fix [bug description, failing command, or issue path][bug description, failing command, or issue path]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Fix narrowly, verify yourself, and escalate when the bug is not actually small.
Fix narrowly, verify yourself, and escalate when the bug is not actually small.
todo.md, docs/context/PROJECT.md, and relevant handoff/subsystem docs.docs/context/research/ and docs/solutions/ for related failures.todo.md, handoff files if needed, and learning docs when the fix teaches something reusable.kb-map refresh when the fix changes behavior, architecture, run/test commands, integrations, sharp edges, or "do not repeat" knowledge. Skip with a note when the fix is cosmetic or isolated.Do not tell the user to test normal app behavior if the agent can test it.
Default ceiling:
Progress can extend the ceiling. Progress means the failure narrows, reproduction improves, evidence points to a subsystem, or one verification layer now passes.
No progress means the same failure persists after unrelated edits, hypotheses change without evidence, or the next attempt cannot say what it proves.
Escalate to:
kb-research when external/framework behavior is unclear.kb-brainstorm when product behavior or scope is unclear.kb-plan when the fix becomes multi-slice.kb-map refresh when architecture docs changed.When stuck, produce:
## Bug Escalation Report
### Symptom
### Expected Behavior
### Reproduction
### Attempts
| Attempt | Hypothesis | Change/Test | Result |
|---|---|---|---|
### Evidence
### Current Best Theory
### Why I Am Stuck
### Recommended Route
Park only the blocked slice or handoff; continue unrelated runnable work when possible.
npx claudepluginhub irtechie/atv-starterkit --plugin atv-starter-kitGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.
Dispatches multiple subagents concurrently for independent tasks without shared state. Use when facing 2+ unrelated failures or subsystems that can be investigated in parallel.