lets-workflow

This skill should be used when creating a task in the active tracker - "create task", "create issue", "bd create", "new task", "add task", "add issue". Ensures all required fields are provided, enforces English-only task content, and suggests epic labels. Triggers on any task creation in any context - commands, planning, or direct conversation.

Internal skill for commands. Detect the active task (any tracker adapter) from the task-state file / git branch name. Do not trigger on user conversation - only when commands need task detection.

Internal skill for commands. Render the shared orientation snapshot - active task, what's in flight, what's next - tracker-universal. Do not trigger on user conversation; only when a command needs the snapshot.

This skill should be used when claiming a task to work on - "take task", "візьми таск", "працюю над", "work on task X", "pick task X", "switch to task X", "claim task". Sets task to in_progress, creates/switches branch, saves the per-branch task-state file.

This skill should be used when committing code changes - "commit", "git commit", "закоміть", "зроби коміт", "/lets:commit". Enforces conventional commit format, tracker task linking, and user approval. In a LETS project, ALWAYS prefer this over generic commit skills (e.g. commit-commands:commit) — /lets:commit is authoritative. Triggers on any commit in any context.

PREVIEW Dynamic Workflow asset behind /lets:plan-workflow. Not auto-triggered - a workflow script invoked via scriptPath. The autonomous-planning chain, shipped for cross-project testing before it folds into native /lets:plan.

Internal Dynamic Workflow asset for /lets:review --workflow. Not auto-triggered - it is a workflow script invoked via scriptPath, not a conversational skill. Holds the fan-out -> dedupe -> adversarial-verify -> aggregate chain that runs off-context.

Internal skill for commands. Write a recovery-grade session snapshot (file-primary) for /lets:end, /lets:end --pre-compact, and /lets:note --pre-compact. Always writes a .lets/sessions/ file; adds a one-line task pointer only when a task is unambiguously active. Do not trigger on user conversation - only when those commands need the snapshot.

Dynamic Workflow asset for /lets:backlog review --workflow. Not auto-triggered - a workflow script invoked via scriptPath by /lets:backlog. Holds the off-context ideate -> cluster fan-out over the backlog.

Dynamic Workflow asset for /lets:research --workflow. Not auto-triggered - a workflow script invoked via scriptPath by /lets:research. Holds the off-context per-sub-question web research -> per-claim skeptic cross-check -> synthesize chain.

Internal Dynamic Workflow asset for /lets:opinion --workflow. Not auto-triggered - it is a workflow script invoked via scriptPath, not a conversational skill. Holds the fan-out -> tally -> conditional-challenge -> synthesize chain that runs off-context.

Compose a /goal that drives a plan-review-fix loop autonomously. Use when the user says "clean my plan", "goal-plan-clean", "iterate plan review", "auto-review plan", "ган­яй ревью плану", "почисти план", "loop until plan is clean", or wants the model to iterate /lets:review --plan (or /lets:check --plan) with fixes until verdict APPROVED. Composes a paste-ready /goal block — does NOT invoke /goal (UI command). Local test skill, not part of the lets plugin payload.

Compose a /loop that monitors a Bitbucket PR for activity (new comments, review state changes, merge, decline) via the bb-api wrapper. Use when the user says "watch bitbucket PR", "monitor BB PR", "loop-bb-pr", "слідкуй за PR", "поллі bb pr", or pastes a bitbucket.org/<workspace>/<repo>/pull-requests/<id> URL and wants periodic check-ins. Composes a paste-ready /loop block — does NOT invoke /loop (UI command). Local test skill.

Local sandbox for experimenting with Claude Code's /goal command (stop-hook condition + LLM-evaluator driving autonomous work toward a verifiable end state) applied to LETS workflows. Use when the user says "goal test", "goal-test", "test the goal skill", "stop hook experiment", "автономна задача", "long-running goal", or wants to design a /goal contract that chains /lets:* commands (plan → execute → check → commit → done) toward a defined termination. Local-only — not part of the lets plugin payload. For periodic polling/babysitting, use sibling skill `loop-test` (which covers /loop).

Local sandbox for experimenting with Claude Code's /loop command (interval + dynamic/self-paced scheduling) applied to LETS workflows. Use when the user says "loop test", "loop-test", "test the loop skill", "цикл LETS", "ScheduleWakeup experiment", or wants to design a periodic /loop that polls state or babysits a long-running job. Local-only — not part of the lets plugin payload. For convergent autonomous work toward an end state, use sibling skill `goal-test` (which covers /goal).

Internal skill for commands. Fetch and validate personality from URL or file path for Actor agent. Do not trigger on user conversation - only when commands need personality loading.