Helps agents compare intended and observed product outcomes, update evidence-backed assumptions, assess feature health, choose lifecycle actions, and plan retirement with migration, customer treatment, and retained learning.
Compare intended product outcomes against observed results to close the launch-to-learning loop: collect post-launch evidence, distinguish expected from observed from uncertain from inferred claims, update assumptions, assess feature health, and choose among continue/improve/harvest/pivot/pause/retire — including retirement lifecycles with deprecation, migration, customer treatment, and retained reusable learning. Do not use for incident postmortems or root-cause analysis (routes to incident-learning or site-reliability-engineering); do not use for analytics instrumentation or metric dashboard design (routes to product-analytics-and-measurement); do not use arbitrary thresholds as universal retirement rules — decisions require human judgment and context.
evals/evals.json
JSON
Other
README.md
Markdown
Other
templates/assumption-ledger-update.md
Markdown
Other
templates/feature-health-record.md
Markdown
Other
templates/outcome-review.md
Markdown
Other
templates/retained-learning-record.md
Markdown
Other
templates/retirement-decision.md
Markdown
Other
templates/sunset-plan.md
Markdown
Reference
references/discovery-brief.md
Markdown
Reference
references/epistemic-discipline.md
Markdown
Reference
references/feedback-destinations.md
Markdown
Reference
references/retirement-lifecycle.md
Markdown
SKILL.md
SKILL.md
Markdown
Provides a Justin Sun-inspired perspective for analyzing crypto industry trends, business decisions, competitive strategy, regulation, attention economics, and entrepreneurial cho…
Provides a methodology for designing and operating AI governance programs, including risk tiering, lifecycle controls, accountability, compliance mapping, agent reviews, GxP overl…
Helps agents design and run product governance through decision rights, review cadences, evidence standards, operating patterns, exception records, and escalation paths.
Helps evaluate whether AI-enabled workflows should be adopted, scaled, constrained, redesigned, or retired using outcome evidence, countermetrics, full operating costs, uncertaint…
Helps coordinate multi-project technical programs by defining mandates, aligning dependencies and capacity, governing risks and decisions, tracking benefits, managing adoption, an…
Guides end-to-end product experiments by mapping assumptions, selecting appropriate test methods, defining guardrails and decision rules, and recording readouts that update produc…
A platform-agnostic method for comparing evidence-based current and target states, explaining gaps and uncertainty, prioritizing interventions, and producing traceable registers, …
Helps agents manage technical projects through initiation, planning, delivery, recovery, handoffs, and closure using predictive, iterative, Scrum, flow-based, or hybrid approaches.