Results for “working-backwards”

Resume work from previous session with full context restoration

Discover, audit, repair, adapt, and design bounded, verifiable AI-agent loops with explicit triggers, actions, stopping conditions, and guardrails.

Establishes a two-party working posture where the user directs and the agent executes, surfacing every genuine fork as a batched single-select question with a recommended default.

Run a user story mapping workshop with adaptive questions and a structured map output, generating backbone activities, user tasks, and release slices for a workflow.

Flip core assumptions to reveal hidden constraints and alternative approaches by asking what if the opposite were true.

Facilitates structured sprint retrospectives, analyzing team feedback and sprint data to generate prioritized, actionable improvement items.

Track multi-step work with todo, plan mode, kanban, and missions, each suited to different lifespans.

Use this skill for queues, retries, idempotency, cron, dead-letter queues, background processing. Trigger when the task involves programming work related to Background Jobs Queues, implementation, audits, debugging, strategy, or validation.

Runs a full retrospective and dev cycle analysis, chaining /recall and /new-features to reconstruct what went wrong, extract lessons learned, identify rework patterns, and synthesize feature ideas from the findings.

Resume an interrupted workflow run with verify-first strategy — loads sidecar state, verifies the last step, and continues execution.

Turns vague features, bug clusters, roadmap items, or launch work into an execution-ready planning packet by choosing the right packet type, separating discovery from delivery, and making blockers, dependencies, and the next move explicit.