Personal Hermes Agent Skills

Autonomously retrieve full-text PDFs for references in the full-text review stage of a Covidence systematic review, in the user's Chrome session via CDP. Looks up open-access copies via Unpaywall, Semantic Scholar, and arXiv, with an optional NotebookLM-assisted last-resort web search, then uploads any PDF it finds through Covidence's "Upload full text" action. References with no locatable full text get a note logged for manual follow-up. Never casts an Include/Exclude decision -- that stays manual.

Autonomously screen references at the title & abstract stage of a Covidence systematic review in the user's Chrome session via CDP. Votes Yes/Maybe/No per the user's PICO criteria, writes a one-line rationale for Maybe votes, and runs unattended after an approve-first-N onboarding phase.

Use when a paywalled DOI's full text is needed and no open-access copy exists — retrieving PDFs via Sci-Hub mirrors, and joining/using Sci-Net (sci-net.xyz) for post-2022 papers. Covers mirror discovery, direct PDF fetch, Turnstile gate, and the Sci-Net invite-code API.

Use when asked for the status of worktrees, which worktree branches are ready to review, pushed, merged or shipped, which worktrees are stale, idle or purgeable, or for a periodic worktree audit across one or several repos

Use when running Hermes Agent with a DeepSeek-family model (deepseek, or deepseek-v4-flash/pro via an aggregator like opencode-go) and want to see, graph, or reset DeepSeek's prefix-cache hit rate, diagnose cache misses, or confirm the deepseek_cache.enabled config — OR when you want to port/apply the deepseek_cache.py module (DeepSeek prefix-cache telemetry, /cache-stats /cache-graph /cache-reset, prefix-break diagnostics, stable tool ordering, cache-friendly compaction) into a Hermes source tree. Covers use + integration.

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

Launch the Mnemosyne browser UI to inspect stored memory.

Use when setting up or refreshing the oh-my-ghostty terminal stack on macOS - Ghostty config, fastfetch on new-terminal startup, and bat/eza/zoxide aliases for zsh.

Deliver structured text content (verdicts, reports, summaries) directly to the macOS clipboard via pbcopy so the user can Cmd+V into Word without Warp terminal soft-wrap artifacts.

Use when ending or pausing a session, switching between sessions, or asked to save/compress session state with TODOs - compresses the current session into a handoff file, updates a task index, and creates Apple Reminders for follow-up. Also used by the daily reminder cron in review mode to pick up leftover tasks.

Use when asked what was done, left pending, in progress, blocked, or waiting for review over the past week or N days; for a weekly recap, wrap-up, or standup (including the weekly worktree cleanup); "where did I leave off", "what should I continue"; or instead of clicking through old sessions with /resume.

Use when a repo has accumulated worktrees under .worktrees/ from finished PRs, when asked to clean up or prune worktrees whose branches were merged or deleted on the remote, or when `git worktree list` shows stale/prunable entries

Use when the user asks for a TL;DR or before/after summary.

Use when the user asks for a report, research write-up, benchmark/model/tool comparison, or any 'give me the report' request.

Troubleshoot/operate the Oh-My-Pi (omp) coding agent.

Summarize today's Slack activity on demand -- one channel or every channel/DM the bot is in.

Autonomously advance HCL iLearning / SAP SuccessFactors compliance courses (Articulate Storyline SCORM, Ethena GoEthena, or direct-HTML SVG players) via raw CDP on port 9222. Resumes paused audio, clicks interactive slide topics/cards, answers quizzes, navigates to the next slide.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Index and invocation guide for the Superpowers skills. Use when the user asks for a Superpowers skill by name or wants to know which skills exist.

Use when executing implementation plans with independent tasks in the current session

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when implementing any feature or bugfix, before writing implementation code

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when starting any conversation - establishes how to find and use skills, requiring skill loading (skill_view) before ANY response including clarifying questions

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when you have a spec or requirements for a multi-step task, before touching code

Use when creating new skills, editing existing skills, or verifying skills work before deployment