Ready to supercharge your AI agents?

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

Get Started Free →

Call Diagnostics & Repair · sonichi | DecimalAI

devopsby sonichi

Call Diagnostics & Repair

sonichi/call-diagnostics-repair

Source sonichi/sutando ↗License MIT

Analyze phone call observability data, detect problems, track them across calls, and recommend systematic repairs.

SkillScore82Maintained

Automatic

AI Engineer pack

Last verified 8/23/2026

What it changes

Passed 16 of 19 test cases with the skill, and 6 of 19 without it.

Without skill32%

With skill82%

Checks it passed that the model alone missed

Specifies using the '-v' flag with diagnose.py
Specifies using the '-t' option with the diagnose.py script
Prefers modifying system prompts over writing new source code

and 8 more in the full report

11 fixed7 passed either way4 still failing0 broke

Pass-rate lift: +50 pp
Tokens: -9%
Agent turns: 0%
Response time: -56%

Model gemini-3.6-flashMeasured 8/23/2026v118 of 22 cases passed with skill · 19 comparable

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/sonichi-call-diagnostics-repair/SKILL.md https://app.decimal.ai/s/sonichi-call-diagnostics-repair/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add sonichi-call-diagnostics-repair, 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/sonichi-call-diagnostics-repair/ and pins it in .decimal/skills.lock

decimalai skills add sonichi-call-diagnostics-repair

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

curl -fsSL --create-dirs -o .claude/skills/sonichi-call-diagnostics-repair/SKILL.md https://app.decimal.ai/s/sonichi-call-diagnostics-repair/SKILL.md

Raw file: /s/sonichi-call-diagnostics-repair/SKILL.md ↗ · machine-readable summary at /s/sonichi-call-diagnostics-repair.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

During a quiet pause in the conversation, the call assistant suddenly triggered a weather lookup tool even though the user made no request. How is this issue labeled?

What was checked, without and with the skill
Checked	Without skill	With skill
Classifies tool execution without a matching user prompt as an auto-invocation error	Missed	Passed

case-18 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md62 lines3 filesincludes scripts

Call Diagnostics & Repair

Analyze phone call observability data, detect problems, track them across calls, and recommend systematic repairs.

Usage

python3 $CLAUDE_CONFIG_DIR/skills/call-diagnostics/scripts/diagnose.py              # last call
python3 $CLAUDE_CONFIG_DIR/skills/call-diagnostics/scripts/diagnose.py --all        # all calls + repair recommendations
python3 $CLAUDE_CONFIG_DIR/skills/call-diagnostics/scripts/diagnose.py -t           # show timeline
python3 $CLAUDE_CONFIG_DIR/skills/call-diagnostics/scripts/diagnose.py -v           # verbose (show detail)
python3 $CLAUDE_CONFIG_DIR/skills/call-diagnostics/scripts/diagnose.py --all --tracker  # generate HTML tracker + open

When to use

After every phone call: run on latest call to detect issues
Before making fixes: run --all to see persistent patterns and repair recommendations
Never apply ad-hoc patches — check the repair recommendations first to understand if the problem is persistent and what the systematic fix should be

Detections

Tool returned too fast (<10ms) — likely error/not-found
Hallucination — Gemini claimed action state without tool verification
Inline task via work — recording/screenshot/play delegated instead of inline
Long delay — >30s between user request and tool execution
Repeated failures — same tool failing 3+ times
Timestamp lag — caller speech logged after tool that it triggered
Wrong tool — Gemini used the wrong tool for the request
User correction — user explicitly corrected Sutando's behavior
Unmet expectation — user repeated a request (not understood)
Auto-invocation — tool called without matching user request

Repair workflow

ALWAYS follow this workflow. Never skip steps.

Diagnose: run --all --tracker to see the full picture across all calls
Identify persistent problems: only fix issues that appear across multiple calls. Ignore one-offs.
Find root cause: ask "why does this happen?" not "how do I patch this instance?"

Track record

Benchmark

16 / 19

test cases passed, vs 6 / 19 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 v4 — 8/3/2026

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

sonichi / sutando

skills/call-diagnostics/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 2 files · scripts

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

Call Diagnostics & Repair

Usage

When to use

Detections

Repair workflow

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills