Install any skill in seconds. Free to start, no credit card required.
Get Started Free →List this repo's recorded dead ends — approaches already tried and abandoned, with reasons and cost
.claude/skills/karanb192-dead-ends/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 153% | 0% |
!node "${CLAUDE_SKILL_DIR}/../../dead-end-registry.js" --render 2>/dev/null || node "${CLAUDE_PLUGIN_ROOT}/dead-end-registry.js" --render
The list above is this repository's recorded dead ends — approaches that were tried and then reverted or ruled out, newest first, each with the date it was tried, why it was walked back, and the estimated token cost of the detour. It is produced by the dead-end-registry hook, which mines your transcripts as you work.
Briefly summarize the 1–3 most relevant entries and, if any bear on what the user is currently doing, gently flag that they have been down this road before. If the list is empty, just say so. Keep it short; do not re-run any commands.
Other measured skills in the registry, with their headline benchmark lift.