work-unit-protocol
Use when starting, tracking, or closing a discrete unit of work. Enforces ULTRA §13 reporting contract — what/why/tests/deps/reuse/risks/follow-ups/completion table. Invoke when user says "start work unit", "close work unit", "work unit report", or when a multi-step implementation task begins.
What this skill does
# Work Unit Protocol A work unit is one scope-bounded outcome with a measurable completion criterion. This skill is the rhythm each unit follows — from kickoff through closing report. ## Phases ### 1. Kickoff - Scope stated in **one sentence** with a measurable completion criterion. - Scan existing tooling (installed plugins, skills, commands, agents, MCPs) — never re-build. - Identify dependencies and blocked-by relationships. - If creating or modifying a library, confirm no parallel module already exists. ### 2. Plan - List artifacts to be produced with paths. - List tests to be written (success path / idempotent / WhatIf / error). - Identify library modules to extend vs. create. Default: extend. - Note any policy files (`policies/*.json`) that must stay in sync. ### 3. Execute - Each action emits an entry to `state/change-log.jsonl`. - New code gets comment-based help + at least one Pester (or equivalent) test. - Refactors preserve behavior; a paired test proves no regression. - Commit cadence: small commits per sub-repo during multi-repo work. ### 4. Verify - `tools/run-all-tests.ps1` (or project equivalent) is green. - For live-impacting scripts, re-run against real target — must be a no-op (idempotence check). - `tools/validate-all-policies.ps1` reports no drift (when policies apply). ### 5. Close — the report Produce a Work Unit Report with these sections: ```markdown # Work Unit <NN> — <title> ## What was implemented - `<path>` — one-line purpose - ... ## Test totals `<suite>`: N/N PASS === TOTAL: N/N PASS (Xs) === ## Why (ULTRA §13 answers) - What breaks if this changes? - What proves this works? - Can this be reused? - Can this be simplified? - Is this observable? - Is this documented? - Is this the best long-term design? ## What's COMPLETE (Section 20) | Artifact | Status | Evidence | |---|---|---| | ... | ✅ | path | ## What's INCOMPLETE - <item> — <time estimate> ## Risks flagged - ... ## Awaiting decision - <blocking user decision> ``` ## Invocation patterns | User says | Do | |---|---| | "Let's start a work unit for X" | Run phase 1. Produce one-sentence scope + criterion. Confirm before phase 2. | | "Close work unit" or "work unit report" | Produce phase-5 report from current session artifacts. | | "Ship it" / "merge it" | Block until phases 4 and 5 are done and green. | ## Non-negotiables - No "done" without evidence (file path + test result). - No "complete" without green tests across the affected suite. - No "shipped" without an idempotent re-run for live-impacting code. - No hidden state — every fact in the report must be verifiable from files in the repo. ## Related - `rules/ultra-mode.md` — the governing constitution. - `skills/harness-automation` — CI pipeline is part of verification. - `commands/wa-report` — one-shot report generator.
Related in Productivity
gitea-workflow
IncludedOrchestrate agile development workflows for Gitea repositories using the tea CLI. Use when working with Gitea-hosted repos and asking to 'run the workflow', 'continue working', 'what's next', 'complete the task cycle', 'start my day', 'end the sprint', 'implement the next task', or wanting guided step-by-step development assistance. Keywords: workflow, orchestrate, agile, task cycle, sprint, daily, implement, review, PR, standup, retrospective, gitea, tea.
microsoft-graph-gateway
IncludedRoute Microsoft Graph work in this workspace. Use when users want to read or write Outlook mail, calendar events, contacts, OneDrive or SharePoint files, Teams, Planner, To Do, users, groups, directory data, or arbitrary Microsoft Graph endpoints from VS Code. Prefer WorkIQ for common read scenarios. Use Microsoft Graph for write actions and gap-read scenarios that need exact Graph properties, filters, permissions, or endpoints.
copilotkit
IncludedUse when building with CopilotKit — setup, development, integrations, debugging, upgrading, or contributing. Routes to the appropriate specialized skill based on the task.
wordly-wisdom
IncludedProvides calibrated decision analysis using Charlie Munger-style multiple mental models, inversion, incentive mapping, circle-of-competence checks, misjudgment audits, second-order effects, and forecast updates. Use when the user asks for an oracle take, a hard call, a decision memo, a premortem, an outside view, a red-team, a sanity-check, what am I missing, think this through, or wants a strategy, hire, investment, plan, product, partnership, or major life choice analysed. Avoid for simple factual lookups or time-sensitive legal, medical, or market questions without fresh evidence.
swain-session
IncludedSession management and project status dashboard. Owns the full session lifecycle (start/work/close/resume), focus lane, bookmarks, worktree detection, and tab naming. Also serves as the project status dashboard — shows active epics, progress, actionable next steps, blocked items, tasks, GitHub issues, and recommendations. Worktree creation is deferred to swain-do task dispatch (SPEC-195). Triggers on: 'session', 'status', 'what's next', 'dashboard', 'overview', 'where are we', 'what should I work on', 'show me priorities', 'bookmark', 'focus on', 'session info'.
gandi
IncludedComprehensive Gandi domain registrar integration for domain and DNS management. Register and manage domains, create/update/delete DNS records (A, AAAA, CNAME, MX, TXT, SRV, and more), configure email forwarding and aliases, check SSL certificate status, create DNS snapshots for safe rollback, bulk update zone files, and monitor domain expiration. Supports multi-domain management, zone file import/export, and automated DNS backups. Includes both read-only and destructive operations with safety controls.