captkernel

Use when the user wants a blunt, no-flattery assessment of an idea, plan, or draft. Triggers: "be brutal", "no flattery", "give me your honest take", "tear this apart".

Use to take a business or product idea from concept to first customers via a guided prompt chain. Triggers: "help me build a business", "turn this idea into an offer", "go from idea to customers".

Convene a five-persona advisory council to adversarially pressure-test a decision and counter Claude's tendency to agree with the user. Use BEFORE any consequential or hard-to-reverse decision — a launch, a hire, a pivot, a big spend, a public commitment, an architecture choice, a contract — or any time the user wants real dissent instead of validation. Trigger phrases: "council this:", "convene the council", "pressure-test this", "stress-test this idea", "give me the hardest truth", "play devil's advocate on this", "what am I missing", "tell me why this is a bad idea". Each advisor critiques from a distinct angle, they anonymously peer-review each other, and a chair delivers a verdict plus the single hardest truth.

Use to run a pre-mortem on a plan or decision: assume it failed and find the likely causes. Triggers: "pre-mortem", "how could this fail", "what would kill this plan".

Use to pressure-test a startup or product idea for fatal flaws, YC-partner style. Triggers: "pressure-test my idea", "is this idea any good", "find the fatal flaws", "would a VC fund this".

Use to adversarially attack a plan or argument from the outside. Triggers: "red team this", "attack this plan", "what are the holes", "poke holes".

Use to explain how airline pricing actually works and separate real mechanisms from myths. Triggers: "do flight prices go up if I search twice", "how does airline pricing work", "is incognito cheaper for flights".

Use to find cheaper flight options for a trip. Triggers: "find cheap flights", "cheapest way to fly", "flight deal", "how do I fly cheaper to".

Use when the user is stuck and cannot start a task. Triggers: "I can't start", "help me focus", "I'm procrastinating", "break this down", "I'm overwhelmed by".

Use to create a fast "make me functional" crash plan for a new skill. Triggers: "help me learn X fast", "crash course on", "get me functional in", "I have a few hours to learn".

Use when the user mentions a skill or plugin by name, asks "should I install X?", asks "what skills fit this project?", asks to audit installed skills, asks whether a skill is safe to use, or wants to customize an external skill for their stack. Evaluates skills against the user's actual project (pros / cons / conflicts / ADOPT-PARTIAL-SKIP verdict), recommends what fits, scans for security red flags before adoption, persists every decision to a registry the user keeps in Project Knowledge, and forks stack-mismatched skills into project-tailored versions. Decide once, never re-decide.

Use when the user mentions a skill/plugin by name, asks "should I install X", asks for skill recommendations, wants a security check on a skill, asks about duplicates or conflicts, wants to create a new skill, or wants to migrate skills across agent platforms (Cursor, Codex, Gemini, etc.).

The intelligence layer for Claude skills — without Python. Maintains a trust-rated catalog (curated entries + live GitHub topic search via curl), identifies what fits your project (stack, deps, CLAUDE.md), recommends with pros/cons and per-project customization advice, persists every decision, and migrates across 55 supported agent platforms. Same model as the full version, no engine — the agent does the work via Bash, Read, Glob, Grep, Write. Use when the user mentions a skill, asks "should I install X", asks to evaluate / recommend / audit / check a skill, asks "what skills fit this project", asks for a list of supported platforms, or wants to migrate skills to another agent. Choose this over the full version when you don't have Python, want zero dependencies, or prefer transparent agent reasoning.

Use to generate scroll-stopping opening hooks for a post, reel, or video. Triggers: "give me hooks", "write a hook", "opening lines for content", "how should I open this post".

Use when the user wants AI-sounding writing rewritten to sound like a real person, removing the "AI tell". Triggers: "humanize this", "make this sound human", "remove the AI tone", "less robotic".

Use to cut a draft 30-40% without losing any claim, number, or example. Triggers: "tighten this", "make it more concise", "cut the fluff", "shorten without losing meaning".