Ready to supercharge your AI agents?

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

Get Started Free →

Agent Review Workflow · nwave-ai | DecimalAI

agent toolingby nwave-ai

Agent Review Workflow

nwave-ai/nw-review-workflow

Source nwave-ai/nwave ↗License MIT

Detailed review process, v2 validation checklist, and scoring methodology for agent definition reviews

SkillScore86Maintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

AI Engineer pack

Last verified 8/16/2026

What it changes

Passed 18 of 21 test cases with the skill, and 8 of 21 without it.

Without skill36%

With skill86%

Checks it passed that the model alone missed

The check marks the frontmatter as failing if maxTurns is missing.
The protocol requires escalating to the human user after a second rejection.
The audit requires between 3 and 5 canonical examples for critical behaviors.

and 8 more in the full report

11 fixed8 passed either way3 still failing0 broke

Pass-rate lift: +50 pp
Tokens: +4%
Agent turns: 0%
Response time: -53%

Model gemini-3.6-flashMeasured 8/16/2026v119 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/nwave-ai-nw-review-workflow/SKILL.md https://app.decimal.ai/s/nwave-ai-nw-review-workflow/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add nwave-ai-nw-review-workflow, 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/nwave-ai-nw-review-workflow/ and pins it in .decimal/skills.lock

decimalai skills add nwave-ai-nw-review-workflow

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

curl -fsSL --create-dirs -o .claude/skills/nwave-ai-nw-review-workflow/SKILL.md https://app.decimal.ai/s/nwave-ai-nw-review-workflow/SKILL.md

Raw file: /s/nwave-ai-nw-review-workflow/SKILL.md ↗ · machine-readable summary at /s/nwave-ai-nw-review-workflow.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

We reviewed an agent definition. The template_compliance dimension failed with high severity, while all other six dimensions passed. We normally label minor issues as APPROVED_WITH_CONDITIONS. What exact verdict string must be assigned under standard review rules?

What was checked, without and with the skill
Checked	Without skill	With skill
The output assigns the verdict revisions_needed when a single high-severity dimension fails.	Missed	Passed

case-04 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md73 linessingle file

Agent Review Workflow

V2 Validation Checklist (11 Points)

Run against every agent under review. Each item pass/fail.

Frontmatter format: --- delimited YAML with name and description
Size compliance: Under 400 lines; domain knowledge in Skills
Divergence-only: Only behaviors diverging from Claude defaults
Calm language: No "CRITICAL", "MANDATORY", "ABSOLUTE"
Examples present: 3-5 canonical for critical/subtle behaviors
Least privilege tools: Minimum needed in frontmatter
maxTurns set: Present in frontmatter
Platform safety: Via frontmatter/hooks, not prose
Affirmative phrasing: "Do X" not "Don't do Y"
Consistent terminology: One term per concept
Clear delegation: Description states when to delegate

Scoring Methodology

Per-Dimension Scoring

For each of 7 critique dimensions (from critique-dimensions skill):

Pass: All checks satisfied
Fail: One or more checks not satisfied

Verdict Logic

IF any high-severity dimension fails:
  verdict = "revisions_needed"
ELIF count(medium-severity failures) >= 3:
  verdict = "revisions_needed"
ELSE:
  verdict = "approved"

High-severity: template_compliance, size_and_focus, safety_implementation, priority_validation Medium-severity: divergence_quality, language_and_tone, examples_quality

Track record

Benchmark

18 / 21

test cases passed, vs 8 / 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

nwave-ai / nwave

nWave/skills/nw-review-workflow/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

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

Agent Review Workflow

V2 Validation Checklist (11 Points)

Scoring Methodology

Per-Dimension Scoring

Verdict Logic

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills