Ready to supercharge your AI agents?

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

Get Started Free →

Joy Check · notque | DecimalAI

documentationby notque

Joy Check

notque/joy-check

Source notque/vexjoy-agent ↗License MIT

Validate content framing on joy-grievance spectrum.

NewMaintained

Automatic

Writing & Editing pack

Last verified 8/27/2026

What it changes

Passed 2 of 8 test cases with the skill, and 3 of 8 without it.

Without skill36%

With skill28%

Checks it passed that the model alone missed

Formats report header as JOY CHECK: docs/user-guide.md
Selects instruction mode for skill-creator pipeline verification
Places joy-check after voice-validator and scan-ai-patterns in pipeline sequence

3 fixed4 passed either way13 still failing5 broke

Pass-rate lift: -8 pp
Tokens: +129%
Agent turns: 0%
Response time: -5%

Model gemini-3.6-flashMeasured 8/27/2026v2 · latest is v37 of 25 cases passed with skill · 8 comparable

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

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/notque-joy-check/SKILL.md https://app.decimal.ai/s/notque-joy-check/SKILL.md

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

decimalai skills add notque-joy-check

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

curl -fsSL --create-dirs -o .claude/skills/notque-joy-check/SKILL.md https://app.decimal.ai/s/notque-joy-check/SKILL.md

Raw file: /s/notque-joy-check/SKILL.md ↗ · machine-readable summary at /s/notque-joy-check.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

Format the evaluation output header and status for checking `docs/user-guide.md` in writing mode.

What was checked, without and with the skill
Checked	Without skill	With skill
Formats report header as JOY CHECK: docs/user-guide.md	Missed	Passed
Includes explicit Status line with PASS or FAIL	Passed	Passed

case-18 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md170 lines3 files

Joy Check

Two modes:

writing — Joy-grievance spectrum for human-facing content (blog posts, emails, articles). Evaluates curiosity/generosity vs. grievance/accusation framing.
instruction — Positive framing for LLM-facing content (agents, skills, pipelines). Evaluates "what to do" vs. "what to avoid" (ADR-127).

Evaluates each paragraph/instruction independently, produces a score (0-100), suggests reframes without modifying content. Flags: --fix rewrites flagged items in place and re-verifies; --strict fails on any item below 60; --mode writing|instruction overrides auto-detection.

Checks framing, not topic or voice. The writing workflow owns voice fidelity and AI-pattern detection.

Reference Loading Table

Signal	Load These Files	Why
Scoring agents, skills, pipelines, or toolkit documentation	`references/instruction-rubric.md`	Positive-framing patterns, scoring, and examples.
Scoring articles, emails, posts, or other human-facing prose	`references/writing-rubric.md`	Joy-grievance patterns, scoring, and examples.

Instructions

Phase 0: DETECT MODE

Auto-detection (priority order):

Explicit --mode flag → use that
agents/*.md → instruction
skills/*/SKILL.md → instruction
skills/workflow/references/*.md → instruction
CLAUDE.md or README.md → instruction
Everything else → writing

Load references/{mode}-rubric.md for scoring criteria and examples.

GATE: Mode determined, rubric loaded.

Phase 1: PRE-FILTER

Regex scanning as a fast gate before LLM semantic analysis.

Writing mode:

Track record

Benchmark

2 / 8

test cases passed, vs 3 / 8 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 v5 — 9/25/2026

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

notque / vexjoy-agent

skills/code-quality/joy-check/SKILL.md

View on GitHub ↗

License MITImported 9/25/2026Version v3Bundled 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

Joy Check

Reference Loading Table

Instructions

Phase 0: DETECT MODE

Phase 1: PRE-FILTER

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills