Is doncheli-tea-bdd0aa safe to install?

SaferSkills independently audited doncheli-tea-bdd0aa (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

.opencode/skills/doncheli-tea/SKILL.md · 1 file

.opencode/skills/doncheli-tea/SKILL.md1.6 KB · Markdown

name: doncheli-tea

description: Run the full autonomous test suite end-to-end and report results. Activate when user mentions "test end to end", "autonomous testing", "run all tests", "full test run", "E2E tests", "test suite".

Don Cheli: Test End-to-End Autonomous (TEA)

Instructions

Detect the test runner from package.json, pyproject.toml, Makefile, or .dc/config.yaml
Run tests in this order: unit → integration → E2E (stop on catastrophic failure at each tier)
Capture stdout/stderr; do not swallow errors silently
Categorize results: passed, failed, skipped, flaky (failed then passed on retry)
For each failing test, provide:

Test name and file path
Error message (full, not truncated)
Likely root cause (one sentence)
Suggested fix (if deterministic)

If the same test fails twice in a row with the same error, escalate to the user instead of retrying
Report coverage if the runner supports it; flag if below the 85% threshold
Save the full report to .dc/test-report-<timestamp>.md
Exit with a clear pass/fail summary — no ambiguous "some tests failed" messages

Output Format

## TEA Report — 2026-03-28T14:32Z

### Summary
- Passed:  142
- Failed:    3
- Skipped:   7
- Coverage: 88% ✅

### Failures

#### 1. UserService.createUser — duplicate email
File: src/user/user.service.spec.ts:88
Error: Expected status 409, got 500
Root cause: Missing unique constraint handler in UserRepository
Fix: Add try/catch for PG error code 23505 and throw ConflictException

### Coverage Warning
- src/payments/refund.ts — 61% (below 85% threshold)

doncheli-tea-bdd0aa— agent skill

Is doncheli-tea-bdd0aa safe to install?

Don Cheli: Test End-to-End Autonomous (TEA)

Instructions

Output Format

Audit the pieces. Scan the whole. Decide.