Skill reviews

Use when turning a song into a kinetic-typography or motion-design music video, lyric video, visualizer or K-pop style MV with Scenario, landscape or vertical 9:16 for TikTok, Reel

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (3 tags): a typed call is more reliable

Front door to STATVS (said status), the one append-only record of what happened across LifeOS and every app it runs: checks the record's health, says whether a system, app or site

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Verify and debug changes to CORAL itself — smallest reproduce loop per area (grader / daemon / CLI / hooks / manager / workspace / hub / template / config / web), where to look whe

• References files that are not bundled: examples/<task>/, examples/<task>/results/
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (7 tags): a typed call is more reliable

Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start
• Linear process with no failure handling

Validation-first design for Cavekit — every kit requirement must be automatically verifiable. Six-gate validation pipeline, phase gates, merge protocol, completion signals, accepta

• References files that are not bundled: references/validation-gates.md
• 10 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Produce honest product reviews and buying guides without fabricated first-hand experience, using disclosed evidence tiers: verified specs, owner-experience synthesis at scale, expe

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Make sure email actually reaches inboxes. Use this skill when setting up email authentication (SPF, DKIM, DMARC), diagnosing emails landing in spam, planning a domain reputation st

• The skill tells the model to perform an irreversible action with no human approval
• 44 mutating operations with no state check
• Says nothing while it works