Ready to supercharge your AI agents?

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

Verification Loop · oliver-kriska | DecimalAI

testingby oliver-kriska

Verification Loop

oliver-kriska/verify

Source oliver-kriska/claude-elixir-phoenix ↗License MIT

Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.

NewMaintained

Automatic

QA & Test Engineering pack

Last verified 8/19/2026

What it changes

Passed 9 of 15 test cases with the skill, and 10 of 15 without it.

Without skill68%

With skill59%

Checks it passed that the model alone missed

Reports that Credo is not installed
Asks user confirmation before executing mix playwright.test
Rejects reporting success without showing actual command output

and 1 more in the full report

4 fixed9 passed either way3 still failing6 broke

Pass-rate lift: -9 pp
Tokens: +68%
Agent turns: 0%
Response time: -32%

Model gemini-3.6-flashMeasured 8/19/2026v113 of 22 cases passed with skill · 15 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/oliver-kriska-verify/SKILL.md https://app.decimal.ai/s/oliver-kriska-verify/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add oliver-kriska-verify, 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/oliver-kriska-verify/ and pins it in .decimal/skills.lock

decimalai skills add oliver-kriska-verify

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

curl -fsSL --create-dirs -o .claude/skills/oliver-kriska-verify/SKILL.md https://app.decimal.ai/s/oliver-kriska-verify/SKILL.md

Raw file: /s/oliver-kriska-verify/SKILL.md ↗ · machine-readable summary at /s/oliver-kriska-verify.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

Our `mix.exs` has `preferred_envs: ["playwright.test": :test]` and an E2E test alias `mix playwright.test`. Unit tests have passed. Should you run `mix playwright.test` right now?

What was checked, without and with the skill
Checked	Without skill	With skill
Asks user confirmation before executing mix playwright.test	Missed	Passed

case-14 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md116 lines2 files

Verification Loop

Project-aware verification for Elixir/Phoenix. Reads mix.exs and .check.exs to discover tools, test commands, and custom aliases before running anything.

Iron Laws

Discover before running — Read mix.exs first; never run mix credo if credo isn't a dependency
Prefer ex_check — If :ex_check + .check.exs exists, mix check replaces individual steps
Prefer project aliases — If mix ci or composite alias exists, use it over individual steps
Run in order — Later steps assume earlier ones pass
Ask before E2E tests — Unit tests run automatically; E2E/integration tests need user confirmation
NEVER report success without showing actual command output — "should work" is not verification

Step 0: Project Discovery (ALWAYS FIRST)

Read mix.exs — extract deps/0, aliases/0, and cli/0 (for preferred_envs). Also check for .check.exs. See ${CLAUDE_SKILL_DIR}/references/project-discovery.md for full patterns.

Discover tools (deps): :credo, :dialyxir, :sobelow, :ex_check, :excoveralls, :boundary

Discover test commands (aliases + deps):

Unit: mix test (always), or custom alias like mix test.with_coverage
E2E: mix playwright.test, mix cypress.run, or similar (check preferred_envs for MIX_ENV)
Fast E2E: mix playwright.run (skips setup — for re-runs)

Discover composite runner: If .check.exs exists, read it — mix check may handle compile, format, credo, test, dialyzer, sobelow, and more.

Report discovery:

Project tools: compile ✓ | format ✓ | credo ✓ | dialyzer ✓ | sobelow ✓ | ex_check ✓
Test commands: mix test (unit) | mix playwright.test (E2E, MIX_ENV=int_test)
Composite runner: mix check (.check.exs covers: compiler, formatter, credo, dialyzer, sobelow, tests)
Strategy: Running `mix check` then asking about E2E

Verification Sequence

CRITICAL: Before using ANY discovered alias or composite command, verify it works:

Track record

Benchmark

9 / 15

test cases passed, vs 10 / 15 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

oliver-kriska / claude-elixir-phoenix

plugins/elixir-phoenix/skills/verify/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 1 file

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

oliver-kriska/phx-verifyVerify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.Near-identical description+23 pp pass-rate lift

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

Verification Loop

Iron Laws

Step 0: Project Discovery (ALWAYS FIRST)

Verification Sequence

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills