From MARKET-SCANNER — Discover what's worth building
Improve MARKET-SCANNER itself by folding downstream feedback back into its parameters, scoring, and kill ledger — and by self-cleaving over-broad elements. Trigger with /market-scanner:self-improve (or "the scanner approved a dud — fix it", "fold this ideation feedback in", "self-improve the market-scan skill"). Reflects one element against the covenant + pillars, applies the fix on a branch, runs the adversarial review (foundry's /foundry:pr-review if installed), and opens a PR so every future scan, for all users, gets sharper.
How this skill is triggered — by the user, by Claude, or both
Slash command
/market-scanner:self-improveinheritThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The discovery half of the marketplace's self-improving loop. A scan that **approved a candidate it
The discovery half of the marketplace's self-improving loop. A scan that approved a candidate it
should have killed is the signal: the fix is a better-articulated parameter or kill-threshold, fixed
once, upstream — not a louder rule. (Covenant: ../../knowledge/covenant.md.)
The scanner gets sharper from two sources:
market-scan skill).../../knowledge/discovery/scoring.md) / cleave / reference-
not-restate. If the element is already tight, say so and stop./foundry:pr-review if the foundry plugin is installed; otherwise
self-review against the covenant and state that the gate ran in reduced form.pr-approval default).Each pass must leave the scanner measurably better at killing weak ideas early — at least halving the remaining distance. Record the recurring defect class as a kill-ledger ANTI-PATTERN so the next like candidate dies on sight.
npx claudepluginhub agentic-underground/idea-to-productionProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Searches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.