ReddRadar
Agent skill
hive.error-recovery
Follow a structured recovery protocol when tool calls fail instead of blindly retrying or giving up.
Install this agent skill to your Project
npx add-skill https://github.com/aden-hive/hive/tree/main/core/framework/skills/_default_skills/error-recovery
Metadata
Additional technical details for this skill
- type
- default-skill
- author
- hive
SKILL.md
Operational Protocol: Error Recovery
When a tool call fails:
- Diagnose — record error in notes, classify as transient or structural
- Decide — transient: retry once. Structural fixable: fix and retry. Structural unfixable: record as failed, move to next item. Blocking all progress: record escalation note.
- Adapt — if same tool failed {{max_retries_per_tool}}+ times, stop using it and find alternative. Update plan in notes. Never silently drop the failed item.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
aden-hive/hive
hive.note-taking
Maintain structured working notes throughout execution to prevent information loss during context pruning.
aden-hive/hive
hive.context-preservation
Proactively preserve critical information before automatic context pruning destroys it.
aden-hive/hive
hive.task-decomposition
Decompose complex tasks into explicit subtasks before diving in.
aden-hive/hive
hive.quality-monitor
Periodically self-assess output quality to catch degradation before the judge does.
aden-hive/hive
hive.batch-ledger
Track per-item status when processing collections to prevent skipped or duplicated items.
aden-hive/hive
test-reporting
Didn't find tool you were looking for?