Ready to supercharge your AI agents?

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

Get Started Free →

Claude Watch Bridge — measured AI agent skill | DecimalAI

shobhit99/claude-watch

NewSkillScoreMaintained

Bridge your Claude Code session to the Agent Watch app on Apple Watch

agent-toolingby shobhit99

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

Automatic

Coding pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/shobhit99-claude-watch/SKILL.md

decimalai skills pull shobhit99-claude-watch --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/shobhit99-claude-watch/SKILL.md https://app.decimal.ai/s/shobhit99-claude-watch/SKILL.md

Raw file: /s/shobhit99-claude-watch/SKILL.md ↗ · machine-readable summary at /s/shobhit99-claude-watch.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 5h ago

Yes — +32% lift-60% tokens0% turns77% of whole cases pass with skill (17/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-21	✗→✓	▲ Improved	-66%	0%
case-07	✗→✓	▲ Improved	-58%	0%
case-08	✗→✓	▲ Improved	-73%	0%
case-22	✗→✓	▲ Improved	-74%	0%
case-13	✗→✓	▲ Improved	-62%	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

shobhit99 / claude-watch

skill/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v2

Skill contents

SKILL.md

Claude Watch Bridge

Starts a local bridge server that connects your active Claude Code session to the Claude Watch iOS/watchOS app.

What it does

Runs a Node.js bridge server on your LAN
Registers HTTP hooks for real-time event forwarding
Generates a 6-digit pairing code for the iPhone app
Enables voice commands from your Apple Watch

Usage

Run /claude-watch to start the bridge. Enter the pairing code in the Claude Watch iPhone app.

Setup

The bridge requires Node.js 18+ and the node-pty package. Run the setup script: cd skill/bridge && npm install

Want to see if shobhit99/claude-watch 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.