LaansDole / my-hermes-skills

Personal Hermes Agent Skills

A curated collection of reusable skills for Hermes Agent — covering systematic review automation, productivity utilities, and Slack tooling. Each skill is self-contained with its own SKILL.md and setup instructions.

25 skills
5 categories
MIT license

Quick Setup

1
Clone or fork this repo, then symlink (or copy) any skill folder into ~/.hermes/skills/
2
Merge .hermes-config/config-patch.yaml into ~/.hermes/config.yaml for auto-approvals needed by CDP browser skills
3
For skills with a README.md, follow the per-skill setup steps (env vars, browser profiles, criteria files)
4
Hermes auto-discovers skills in ~/.hermes/skills/ — just start a new session and the skill will be available
🔬
Systematic Review (Covidence) 3 skills
covidence-full-text-retrieval v1.2.0

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.

covidence systematic-review full-text open-access notebooklm browser-automation
covidence-full-text-review v2.0.0

Review full-text papers in a Covidence systematic review. Mode 1 (websearch_queue): walks the Covidence queue, web-searches each title, opens the first result in the papers-access browser profile, reads the full text, and reports verdicts in chat (no Covidence writes). Mode 2 (secondary_reviewer): receives a URL from the user, reads the paper, returns a structured Include/Exclude verdict with rationale, and optionally casts the vote in Covidence when a ref_id is supplied.

covidence systematic-review full-text review browser-automation
covidence-screening v1.0.0

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.

covidence systematic-review screening browser-automation
Productivity 5 skills
i-have-adhd

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".

memory-ui

Launch the Mnemosyne browser UI to inspect stored memory.

pbcopy-word-delivery v1.0.0

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.

clipboard word macos pbcopy formatting
session-handoff v1.2.0

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.

session handoff todo reminders macos productivity cron
tldr v1.0.0

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

tldr summary recap before-after communication concise
💬
Slack 1 skill
slack-scan v1.0.0

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

slack summary notifications todo
📦
ilearning-autoadvance 1 skill
ilearning-autoadvance v5.0.0

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.

📦
superpowers 15 skills
superpowers-brainstorming v1.0.0

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.

superpowers planning design requirements
superpowers-dispatching-parallel-agents v1.0.0

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

superpowers delegation parallel
superpowers-executing-plans v1.0.0

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

superpowers planning execution
superpowers-finishing-a-development-branch v1.0.0

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

superpowers git branch workflow
superpowers-receiving-code-review v1.0.0

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

superpowers code-review feedback
superpowers-requesting-code-review v1.0.0

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

superpowers code-review quality
superpowers-slash-commands v1.0.0

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.

superpowers skills navigation
superpowers-subagent-driven-development v1.0.0

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

superpowers delegation subagents execution
superpowers-systematic-debugging v1.0.0

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

superpowers debugging root-cause
superpowers-test-driven-development v1.0.0

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

superpowers tdd testing
superpowers-using-git-worktrees v1.0.0

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

superpowers git worktrees isolation
superpowers-using-superpowers v1.0.0

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

superpowers skills workflow
superpowers-verification-before-completion v1.0.0

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

superpowers verification quality
superpowers-writing-plans v1.0.0

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

superpowers planning implementation
superpowers-writing-skills v1.0.0

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

superpowers skill-authoring tdd