Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Majiayu000/Hive Error Recovery — measured AI agent skill | DecimalAI

majiayu000/hive.error-recovery

NewSkillScoreMaintained

Follow a structured recovery protocol when tool calls fail instead of blindly retrying or giving up.

agent-toolingby majiayu000

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/majiayu000-hive-error-recovery/SKILL.md

decimalai skills pull majiayu000-hive-error-recovery --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/majiayu000-hive-error-recovery/SKILL.md https://app.decimal.ai/s/majiayu000-hive-error-recovery/SKILL.md

Raw file: /s/majiayu000-hive-error-recovery/SKILL.md ↗ · machine-readable summary at /s/majiayu000-hive-error-recovery.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 2h ago

—-40% tokens0% turns73% of whole cases pass with skill (16/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	39%	0%
case-09	✗→✓	▲ Improved	-54%	0%
case-11	✗→✓	▲ Improved	-55%	0%
case-15	✗→✓	▲ Improved	-38%	0%
case-17	✗→✓	▲ Improved	-59%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

majiayu000 / claude-skill-registry

skills/agent/error-recovery-aden-hive-hive/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

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 3+ times, stop using it and find alternative.

Update plan in notes. Never silently drop the failed item.

Want to see if majiayu000/hive.error-recovery would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.