Ready to supercharge your AI agents?

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

Get Started Free →

Multi Platform Messenger Bridge · stijnman | DecimalAI

agent toolingby stijnman

Multi Platform Messenger Bridge

stijnman/multi-platform-messenger-bridge

Source stijnman/grok-custom-skills ↗License MIT

Unifies WhatsApp, Telegram, and future channels with shared memory and ratin g.

SkillScore100Maintained

Automatic

Personal Assistant pack

Last verified 8/15/2026

What it changes

Passed 26 of 26 test cases with the skill, and 8 of 26 without it.

Without skill31%

With skill100%

Checks it passed that the model alone missed

The response identifies hitl-approver as the human approval gate.
The response specifies storing custom metadata in the meta field.
The response includes outbound dispatch authorization via hitl-approver.

and 17 more in the full report

18 fixed8 passed either way0 still failing0 broke

Pass-rate lift: +69 pp
Tokens: -41%
Agent turns: 0%
Response time: -58%

Model gemini-3.6-flashMeasured 8/15/2026v226 of 26 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/stijnman-multi-platform-messenger-bridge/SKILL.md https://app.decimal.ai/s/stijnman-multi-platform-messenger-bridge/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add stijnman-multi-platform-messenger-bridge, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

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

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/stijnman-multi-platform-messenger-bridge/ and pins it in .decimal/skills.lock

decimalai skills add stijnman-multi-platform-messenger-bridge

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

curl -fsSL --create-dirs -o .claude/skills/stijnman-multi-platform-messenger-bridge/SKILL.md https://app.decimal.ai/s/stijnman-multi-platform-messenger-bridge/SKILL.md

Raw file: /s/stijnman-multi-platform-messenger-bridge/SKILL.md ↗ · machine-readable summary at /s/stijnman-multi-platform-messenger-bridge.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 18 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 18

Prompt

What specific integration module handles message quality rating for incoming WhatsApp messages in this pipeline?

What was checked, without and with the skill
Checked	Without skill	With skill
The response identifies whatsapp-message-rater as the rating integration module.	Missed	Passed

case-08 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md40 lines2 files

Multi Platform Messenger Bridge

When to Use

User says bridge messengers or task matches this capability
User says unified chat memory or task matches this capability
User says cross-platform reply or task matches this capability

Workflow

Normalize message format across platforms (sender, channel, body, meta).
Route through whatsapp-message-rater (or platform equivalent).
Apply shared contact profile from semantic-memory-manager.
Dispatch reply via platform adapter; same HITL rules everywhere.

References

Read references/messenger-setup.md when setup, backends, or rubric details are needed.

Integrations

whatsapp-auto-responder
whatsapp-message-rater
semantic-memory-manager
hitl-approver

Error Handling

Failure	Response
Platform not configured	Read references/messenger-setup.md; guide setup.
Channel policy mismatch	Apply strictest policy across channels.

Gotchas

Read references/messenger-setup.md before first use.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Track record

Benchmark

26 / 26

test cases passed, vs 8 / 26 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/15/2026

View 15 scanner checks

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

stijnman / grok-custom-skills

.grok/skills/multi-platform-messenger-bridge/SKILL.md

View on GitHub ↗

License MITImported 8/15/2026Version v2Bundled 1 file

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Multi Platform Messenger Bridge

When to Use

Workflow

References

Integrations

Error Handling

Gotchas

Example

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills