Claude assistants and Claude Code workflows. This directory includes agent skill packages and prompt templates; each card identifies its type. A prompt template is copied from its source, while a skill package needs the appropriate agent setup. Compatibility may be inferred from the content unless a recorded test is linked.
Author, validate, test, and deploy YARA-L 2.0 detection rules and evaluate end-to-end detection coverage gaps in Google SecOps. Use when writing new detection rules, tuning existing rules, validating syntax, testing logic against historical telemetry, or evaluating detection coverage against threat intelligence blogs, CVE disclosures, and Threat Detection Opportunities (TDOs) using synthetic UDM events and long-running coverage analysis. Don't use for alert triage (use secops-triage), deep forensic event reconstruction on infected hosts (use secops-investigate), or case management operations (use secops-cases).
Validate specs and autonomously execute implementation tasks with status tracking. Use after /shep-kit:plan when ready to start implementation. Part of the Shep autonomous SDLC platform — https://shep.bot
Prepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
Search existing local, marketplace, GitHub, and web skill sources before creating a new skill. Use when the user wants to create, build, fork, or find a skill for a workflow.
Grounds every implementation decision in official documentation. Use when you want to verify an approach against the official docs before implementing it, or when you want authoritative, source-cited code free from outdated patterns. Use when building with any framework or library where correctness matters.
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and scope, or when requirements are unclear, ambiguous, or only exist as a vague idea. Use when a single requirement spans several independently testable capabilities and needs decomposing into a capability map of modules before specifying.
Use this skill to test strategy changes against a fresh test repository. Invoke when the user asks to "test against a test repo", "validate the changes", or wants to verify session hooks, commits, and checkpoint creation work correctly.
Render a token-usage stat card from local Claude Code, Codex, Gemini CLI, and OpenCode session logs and commit it into the repository as a file. Use when someone wants a current usage figure in a README, or asks for a shareable card of their coding-agent activity.
Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.
Run a six-phase verification of a Claude Code session's work — build, type check, lint, tests with coverage, security grep, and diff review — then produce a PASS/FAIL verification report. Use when verifying work after completing a feature or refactor, before creating a PR, or when quality gates must pass.
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
Bulk-classify a list of test262 pass→other transitions from a CI run. Distinct from handle-regression (single fix) and analyze-regression (diff two runs). Use after a merge wave when the sharded run reports N regressions and you need to bucket them by root cause and decide which are false positives.
Sweep leaked ad-hoc dev scratch files (check-.ts, debug-.ts, test--debug.ts, tests/probe-.test.ts, etc.) into .tmp/ so git status stays clean and token cost per tool call stays low.
End-of-session checkpoint — append diary, update active sprint doc with interim results/retro, write tech-lead handoff, commit and push. Use before /compact or at end-of-day. Distinct from sprint-wrap-up which closes a sprint.
Cleanly shut down a dev teammate — instruct them to write a context summary to plan/agent-context/{name}.md first, receive their approval, verify process exit. Use for scale-down, rotation, sprint wrap-up.
Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log. Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by model, session, or date.
Install and operate Everything Claude Code (ECC) on the DeepSeek Harness (DSH): native skill roots (/.dsh/skills, .agents/skills), the @deepseek-ai/dsh-hooks-claude-code bridge for command hooks, bare-insert patch mounting, generator usage, event-support limits, and update workflow. Use when setting up ECC on DeepSeek Harness, wiring ECC hooks into a DSH profile, or debugging why ECC skills or hooks do not appear in a DSH session.
Close a merged Topping Out job (one ticket): check the acceptance ledger is all PASS, reconcile planned-vs-built, fill and archive the job file, then hand over to the board close. Use when the user runs /f-signoff, says "close this job", "we're done, wrap it up", after the merge is verified. No deferrals, no close-anyway, never retires the blueprint. Not for committing or pushing (the owner's word). Also answers to its old name, /f-close.
Manual only. Invoked when somebody is contributing to MailFathom for the first time — the welcome, an orientation in what the project is and how it is licensed, then the Linux-only platform check, the toolchain both stacks need and its installation, what this machine's credentials may and may not do here, the base remote, the local instruction file naming the role, the permissions an agent harness needs, and the first green verification run in both stacks. Invoked again on a machine it has already set up, it refreshes that machine against what the repository has changed since instead of repeating any of it.
Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or when feedback like "move this, change that" is easier pointed at than typed.
This skill should be used when the user asks to "optimize a prompt", "improve prompt performance", "design a prompt template", "write better prompts", "debug prompt issues", "use chain-of-thought", "structured prompting", "few-shot prompting", or wants to apply advanced prompt engineering patterns for production LLM applications.