Ready to supercharge your AI agents?

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

Get Started Free →

Bitwarden Skill — measured AI agent skill | DecimalAI

sundial-org/bitwarden

NewSkillScoreMaintained

Access and manage Bitwarden/Vaultwarden passwords securely using the rbw CLI.

Securityby sundial-org

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

Automatic

Security & AppSec pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/sundial-org-bitwarden/SKILL.md

decimalai skills pull sundial-org-bitwarden --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/sundial-org-bitwarden/SKILL.md https://app.decimal.ai/s/sundial-org-bitwarden/SKILL.md

Raw file: /s/sundial-org-bitwarden/SKILL.md ↗ · machine-readable summary at /s/sundial-org-bitwarden.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

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 1h ago

—-44% tokens0% turns83% of whole cases pass with skill (19/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-23	✗→✓	▲ Improved	-44%	0%
case-04	✗→✓	▲ Improved	-50%	0%
case-05	✗→✓	▲ Improved	-49%	0%
case-06	✗→✓	▲ Improved	-52%	0%
case-07	✗→✓	▲ Improved	-62%	0%

Showing 5 of 23 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

sundial-org / awesome-openclaw-skills

skills/bitwarden/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

Bitwarden Skill

Interact with Bitwarden or Vaultwarden vaults using the rbw CLI.

Usage & Configuration

1. Setup (First Run)

bash
rbw config set email <your_email>
rbw config set baseurl <vault_url> # Optional, defaults to bitwarden.com
rbw login

Note: Login requires the Master Password and potentially 2FA (email/TOTP).

2. Unlock

bash
rbw unlock

Note: rbw caches the session key in the agent. If interactive input is required (pinentry), see if you can setup pinentry-curses (CLI-based pinentry) as the pinentry provider.

3. Management

List items: rbw list
Get item: rbw get "Name"
Get JSON: rbw get --full "Name"
Search: rbw search "query"
Add: rbw add ...
Sync: rbw sync (Refresh vault)

Note: Always sync before getting details to ensure accuracy.

Tools

The agent uses exec to run rbw commands.

For unlocking, use tmux if rbw prompts for a password via pinentry-curses.
For adding items, rbw add may require EDITOR configuration or tmux.

Want to see if sundial-org/bitwarden 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.