Productivity & Workflow Agent Skills

Audit something Claude built for the unstated assumptions baked into it — the silent interpretive leaps, not the caveats already written…

Goal-integrity skill. Use for backend/API/persistence, preserve/do-not-change, tests/validation, mocks, rework, multi-part requests. Emits…

Companion to atlas-contract. Auto-invoked by its Final Audit on caught drift; also use after Post Reviews or user requests to record a…

Enterprise memory audit: Is what the company knows actually being retrieved, and are your AI agents working within your context or…

Efficiency audit of a skill library on four measured axes — token cost, ceremony/duplication bloat, trigger-description precision, and…

Auditing a company's internal processes to identify what deserves to be automated: guided interview, automatability scoring…

Use when creating, consolidating, editing, testing, or reviewing coding-agent skills, skill packs, orchestration skills, reusable…

Analyze a screen recording of a manual process and produce targeted, working automation scripts.

MUST read before requests involving automated execution, recurring execution, background execution, event-triggered execution, bot/agent…

Safely inspect and edit structured background-automation task queues.

Event-triggered and schedule-triggered automations with natural-language conditions.

Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing.

Autonomous iterative experimentation loop for any programming task.

Operating procedure for the conflict-autoresolver agent: sweep open PostHog/posthog PRs that conflict with master, resolve the trivial…

When it comes to the interface between the General Terms and Conditions (GTC) and the General Terms and Conditions (GTC) in the GTC law…

Use when the operator's requirement, the failing test, the stakeholder argument, or any other inputs are STILL IN FLUX and the temptation…

Unattended best-judgment mode.

Reconstruct workflow behind a past coding-agent artifact using local ax sessions/commits/skills/tool traces.

Take an Azure Boards work item from "read it" to "PR open, Pipelines green, review comments addressed, work item updated" with maximum…

Run a task end to end through the full delivery pipeline — product discovery, architecture, build, verification, release.

Evaluates loan application readiness for Japan-based founders and small businesses using structured rubrics, document intake, and…