Ready to supercharge your AI agents?

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

Reality Verification · tzachbon | DecimalAI

testingby tzachbon

Reality Verification

tzachbon/reality-verification

Source tzachbon/smart-ralph ↗License MIT

This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy test anti-patterns.

SkillScore73Maintained

Automatic

QA & Test Engineering pack

Last verified 8/20/2026

What it changes

Passed 12 of 16 test cases with the skill, and 7 of 16 without it.

Without skill41%

With skill73%

Checks it passed that the model alone missed

Classifies the goal type as Add
Selects pnpm lint as the reproduction command
Selects the WebFetch tool for API endpoint verification

and 8 more in the full report

10 fixed6 passed either way3 still failing3 broke

Pass-rate lift: +32 pp
Tokens: +3%
Agent turns: 0%
Response time: -55%

Model gemini-3.6-flashMeasured 8/20/2026v116 of 22 cases passed with skill · 16 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/tzachbon-reality-verification/SKILL.md https://app.decimal.ai/s/tzachbon-reality-verification/SKILL.md

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

decimalai skills add tzachbon-reality-verification

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

curl -fsSL --create-dirs -o .claude/skills/tzachbon-reality-verification/SKILL.md https://app.decimal.ai/s/tzachbon-reality-verification/SKILL.md

Raw file: /s/tzachbon-reality-verification/SKILL.md ↗ · machine-readable summary at /s/tzachbon-reality-verification.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 10

Prompt

What exact command should be placed under the 'Verify' line of task 4.3 VF for a spec named auth-fix?

What was checked, without and with the skill
Checked	Without skill	With skill
Uses grep -q "Verified: Issue resolved" ./specs/auth-fix/.progress.md	Missed	Passed

case-14 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md103 lines3 files

Reality Verification

For fix goals: reproduce the failure BEFORE work, verify resolution AFTER.

Goal Detection

Classify user goals to determine if diagnosis is needed. See references/goal-detection-patterns.md for detailed patterns.

Quick reference:

Fix indicators: fix, repair, resolve, debug, patch, broken, failing, error, bug
Add indicators: add, create, build, implement, new
Conflict resolution: If both present, treat as Fix

Command Mapping

Goal Keywords	Reproduction Command
CI, pipeline	`gh run view --log-failed`
test, tests	project test command
type, typescript	`pnpm check-types` or `tsc --noEmit`
lint	`pnpm lint`
build	`pnpm build`
E2E, UI	Playwright MCP browser tools
API, endpoint	WebFetch tool

For E2E/deployment verification, use MCP tools (Playwright MCP browser tools for UI, WebFetch tool for APIs).

BEFORE/AFTER Documentation

BEFORE State (Diagnosis)

Document in .progress.md under ## Reality Check (BEFORE):

## Reality Check (BEFORE)

**Goal type**: Fix
**Reproduction command**: `pnpm test`
**Failure observed**: Yes
**Output**:

Track record

Benchmark

12 / 16

test cases passed, vs 7 / 16 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

tzachbon / smart-ralph

plugins/ralph-specum/skills/reality-verification/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 2 files

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

Reality Verification

Goal Detection

Command Mapping

BEFORE/AFTER Documentation

BEFORE State (Diagnosis)

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills