Skill Claude CodeCodex
Use before any AI product messaging ships externally. Audits capability claims for accuracy, quantified claims for evidence, and "AI" labels for specificity. Blocks "10x productivity" without measurement and "AI-powered" without definition.
Skill Claude CodeCodex
Use before any campaign moves from strategy to execution. Transforms a growth strategy and offer into an executable brief — campaign objective, audience, offer, message, channel, creative requirements, landing destination, CTA, success metric, review gates, and launch checklist. Blocks "the team knows what we're going…
Skill Claude CodeCodex
Use before building any campaign, content plan, or outbound motion. Scores every candidate growth channel against eight criteria — audience presence, intent, cost to test, feedback speed, trust requirement, sales cycle fit, operational complexity, and measurement feasibility — before one is chosen. Blocks "let's try…
Skill Claude CodeCodex
Use before any external-facing copy ships. Applies three tests — "so what?", "who cares?", and "why now?" — to every claim in the copy. Blocks "it explains what we do" completions.
Skill Claude CodeCodex
Use before running any growth experiment — pricing test, copy variant, onboarding flow, feature gate — that will inform a ship/no-ship decision. All six elements must be defined before the test starts. Blocks "we'll run it for a while and see" completions.
Skill Claude CodeCodex
Use before beginning any conversion rate optimisation effort. Requires the leak to be identified and root-caused before any solution is proposed. Blocks "let's improve our conversion rate" without knowing which step breaks.
Skill Claude CodeCodex
Use before executing any growth initiative — campaign, launch, or experiment. Requires north star metric, input/output metrics, leading/lagging indicators, activation/retention/conversion metrics, measurement cadence, minimum viable tracking, and a named owner per metric to be defined before execution starts. Blocks…
Skill Claude CodeCodex
Use before any copy, campaign, or experiment work begins on a new project or growth initiative. Requires growth stage, target segment, growth goal, primary constraint, channel hypothesis, core offer, north star metric, a 90-day hypothesis, and named risks to be defined before any execution starts. Blocks "let's just…
Skill Claude CodeCodex
Use before launching any approved project, product, feature, or campaign externally. Requires launch goal, audience, offer, assets, channels, timeline, pre-launch and launch-day tasks, post-launch follow-up, success metrics, risks, and rollback criteria to be defined before launch day. Blocks "we'll figure out launch…
Skill Claude CodeCodex
Use before any copy or campaign is built around an offer. Requires target customer, painful problem, promised outcome, mechanism, proof, risk reversal, pricing or exchange model, CTA, and objection handling to be defined before the offer is used in any external-facing work. Blocks "the offer is implied by the product"…
Skill Claude CodeCodex
Use before any marketing copy is written for a product, feature, or campaign. Requires a clear category, a specific audience, and a differentiated claim — verified against the "so what?" test — before any copy is produced. Blocks "we'll develop the messaging as we write" completions.
Skill Claude CodeCodex
Use before publishing or changing any pricing, packaging, or plan page. Reviews pricing clarity, plan differentiation, target customer per tier, CTA clarity, risk reversal, objections, comparison logic, anchoring, limitations, upgrade path, and trust/proof. Blocks "the pricing speaks for itself" completions.
Skill Claude CodeCodex
Use before launching any new feature or product. Requires the activation moment, habit loop, and reactivation path to be designed before launch. Blocks "users will come back if they like it" completions.
Skill Claude CodeCodex
Use before any testimonial, case study, logo, quantified result, screenshot, review, or before/after claim is used in marketing. Verifies source, context, permission, and accuracy for every piece of proof. Blocks "this looks credible enough" completions and unsourced or misleading proof.
Plugin Claude Code
AI product quality enforcement: 7 skills and 3 agents for product teams.
Agent Claude Code
Use when defining measurement frameworks for new features. Designs north star, guardrail, and diagnostic metrics with baselines, logging plans, and instrumentation requirements. Writes the measurement plan to product/metrics/ - .md before any build begins.
Agent Claude Code
Use after writing a PRD, feature scope, or product decision to audit it against all builder-product skill gates before any engineering time is committed. Produces a written critique with PASS, CONDITIONAL, or BLOCK verdict at product/reviews/ / -product-critique.md.
Agent Claude Code
Use after user research sessions to produce a synthesis document where every insight maps to a decision. Writes to product/research/ -synthesis- .md. Blocks "users said X" reports with no actionable direction.
Instructions file CodexOpenCode
AGENTS.md instructions for RBraga01/builder-product, covering builder-product — agent directory, product-critic, metric-designer and research-synthesiser.
Instructions file
Claude Code instructions for RBraga01/builder-product, covering builder-product — claude configuration, pack version, file conventions, skill trigger sequence and agent usage.
Skill Claude CodeCodex
Use before running any experiment that will inform a product decision. All six elements — hypothesis, metric, sample size, duration, stopping rule, and decision rule — must be defined before the test starts. Blocks "we'll stop when we see something" completions.
Skill Claude CodeCodex
Use before any AI feature is approved for build. Covers four AI-specific risks that standard PRD review misses: hallucination UX, trust calibration, scope creep, and reversibility. Blocks "we validated it like any other feature" completions.
Skill Claude CodeCodex
Use before any engineering estimate is made. Requires a written scope before an estimate, and a written estimate before a commit. Blocks "we'll scope as we go" and "just give me a rough number" completions.
Skill Claude CodeCodex
Use before writing any implementation code for a new feature. North star metric, guardrail metrics, and diagnostic metrics must be defined — with baselines — before the build begins. Blocks "we'll figure out the metrics from the data" completions.
At most 3 mods per repository are shown here — the rest are on their repository pages: