Ready to supercharge your AI agents?

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

Get Started Free →

Verification Strategy · vstorm-co | DecimalAI

testingby vstorm-co

Verification Strategy

vstorm-co/verification-strategy

Source vstorm-co/pydantic-deepagents ↗License MIT

Thorough verification of completed work before declaring done

SkillScore68Maintained

Automatic

QA & Test Engineering pack

Last verified 8/13/2026

What it changes

Passed 14 of 21 test cases with the skill, and 9 of 21 without it.

Without skill41%

With skill68%

Checks it passed that the model alone missed

Recommends checking file byte count using wc -c.
Instructs checking execution exit code using echo $?.
Recommends using wc -c to measure exact file byte size.

and 8 more in the full report

7 fixed8 passed either way6 still failing1 broke

Pass-rate lift: +27 pp
Tokens: +12%
Agent turns: 0%
Response time: -20%

Model gemini-3.6-flashMeasured 8/13/2026v115 of 22 cases passed with skill · 21 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/vstorm-co-verification-strategy/SKILL.md https://app.decimal.ai/s/vstorm-co-verification-strategy/SKILL.md

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

decimalai skills add vstorm-co-verification-strategy

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

curl -fsSL --create-dirs -o .claude/skills/vstorm-co-verification-strategy/SKILL.md https://app.decimal.ai/s/vstorm-co-verification-strategy/SKILL.md

Raw file: /s/vstorm-co-verification-strategy/SKILL.md ↗ · machine-readable summary at /s/vstorm-co-verification-strategy.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

I generated a binary dataset file /data/processed.bin and a summary log /data/summary.txt in my shell pipeline. Usually I just run cat on the summary file. What bash commands should I run to inspect file existence, detailed permissions, exact byte count, file encoding/type, and initial lines before committing?

What was checked, without and with the skill
Checked	Without skill	With skill
Recommends using ls -la to check file existence and permissions.	Passed	Passed
Recommends using wc -c to measure exact file byte size.	Missed	Passed
Recommends using file command to detect file format.	Passed	Passed

case-07 · gemini-3.6-flash · 8/13/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md82 linessingle file

Verification Strategy

How to verify your work is correct before declaring a task complete.

The Verification Checklist

After implementing a solution, go through ALL of these:

1. Re-read the original task

Re-read the EXACT wording of the task instruction
Check every requirement — file paths, names, formats, constraints
Are there implicit requirements? ("compile with gcc -O3 -lm" means exact flags)

2. Check file outputs

Do all required files exist at the exact paths specified?
Are file sizes within any stated limits?
Is the file format correct? (binary vs text, encoding, line endings)

ls -la /path/to/expected/output
wc -c /path/to/output    # byte count
file /path/to/output      # format detection
head -5 /path/to/output   # content preview

3. Compile and run

Compile with the EXACT flags specified in the task
Run with the EXACT command and arguments specified
Check exit code: echo $? (should be 0 for success)
Check both stdout AND stderr

4. Validate output

Compare output against expected format
Check exact field names, delimiters, number formatting
If the task specifies output format, match it exactly:
- JSON: valid JSON? correct schema?
- CSV: correct headers? correct delimiter?
- Plain text: correct line endings? trailing newline?

5. Test edge cases

Track record

Benchmark

14 / 21

test cases passed, vs 9 / 21 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

vstorm-co / pydantic-deepagents

pydantic_deep/bundled_skills/verification-strategy/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

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 Strategy

The Verification Checklist

1. Re-read the original task

2. Check file outputs

3. Compile and run

4. Validate output

5. Test edge cases

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills