Updated 2w ago
by Raidriar7170
hermes-skilleval
Verification-gated skill routing and self-improvement harness for Hermes-style agent skills
29 GitHub stars (29)
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | −96 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 29 skills (29 skills found in its SKILL.md files)
- 1 forks (1 forks)
- 2w ago last update (Last updated 2w ago)
Install
Skills CLI
npx skills add Raidriar7170/hermes-skilleval
Asks which skills and agents to install. Just one: npx skills add Raidriar7170/hermes-skilleval --skill 'Accessibility Tree Inspection' — add -g for every project.
Claude Code
git clone https://github.com/Raidriar7170/hermes-skillevalcp -r "hermes-skilleval/benchmarks/migrated-skills/browser-gui/accessibility-tree-inspection" ~/.claude/skills/
Copies the Accessibility Tree Inspection skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Raidriar7170/hermes-skilleval
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 29 of 91 files.
-
Accessibility Tree Inspection
Inspect accessible names, roles, and tree structure to drive or audit browser UI behavior.
benchmarks/migrated-skills/browser-gui/accessibility-tree-inspection/SKILL.md on GitHub (opens in a new tab) -
Browser Smoke Testing
Open a local web target and verify that the main page renders and core controls respond.
benchmarks/migrated-skills/browser-gui/browser-smoke-testing/SKILL.md on GitHub (opens in a new tab) -
Form Interaction Flow
Drive browser forms and controls through realistic user interactions.
benchmarks/migrated-skills/browser-gui/form-interaction-flow/SKILL.md on GitHub (opens in a new tab) -
Visual Regression Review
Compare browser-rendered UI state against expected layout, content, and responsive behavior.
benchmarks/migrated-skills/browser-gui/visual-regression-review/SKILL.md on GitHub (opens in a new tab) -
MCP Tool Routing
Select local MCP tools for files, browser, documents, spreadsheets, or app control based on the requested task.
benchmarks/migrated-skills/claude-code/mcp-tool-routing/SKILL.md on GitHub (opens in a new tab) -
Plan Mode
Clarify requirements and produce an implementation plan before changing files.
benchmarks/migrated-skills/claude-code/plan-mode/SKILL.md on GitHub (opens in a new tab) -
Slash Command Workflow
Follow explicit slash-command workflows for proposal, apply, review, or archive steps.
benchmarks/migrated-skills/claude-code/slash-command-workflow/SKILL.md on GitHub (opens in a new tab) -
Task Tool Delegation
Delegate independent investigation or implementation work to specialized subagents and review their outputs.
benchmarks/migrated-skills/claude-code/task-tool-delegation/SKILL.md on GitHub (opens in a new tab) -
Apply Patch Discipline
Make small, reviewable file edits with patch-style changes and avoid unrelated rewrites.
benchmarks/migrated-skills/codex/apply-patch-discipline/SKILL.md on GitHub (opens in a new tab) -
Evidence Backed Final Response
Summarize completed engineering work with changed files, exact validation, and known risks.
benchmarks/migrated-skills/codex/evidence-backed-final/SKILL.md on GitHub (opens in a new tab) -
Subagent Worker Protocol
Execute an assigned implementation task as a Worker with scoped edits, validation, and handoff notes.
benchmarks/migrated-skills/codex/subagent-worker-protocol/SKILL.md on GitHub (opens in a new tab) -
Workspace Git Hygiene
Inspect branch and status, protect user edits, and avoid destructive git commands.
benchmarks/migrated-skills/codex/workspace-git-hygiene/SKILL.md on GitHub (opens in a new tab) -
Systematic Debugging
Reproduce a bug, isolate the cause, and fix it only after evidence identifies the failure path.
benchmarks/migrated-skills/superpowers/systematic-debugging/SKILL.md on GitHub (opens in a new tab) -
Test Driven Development
Add or change behavior by confirming a failing test first, then writing the smallest passing implementation.
benchmarks/migrated-skills/superpowers/test-driven-development/SKILL.md on GitHub (opens in a new tab) -
Using Git Worktrees
Create or use an isolated worktree for feature work so concurrent edits do not collide.
benchmarks/migrated-skills/superpowers/using-git-worktrees/SKILL.md on GitHub (opens in a new tab) -
Verification Before Completion
Run fresh validation before claiming that work is complete, fixed, clean, or ready.
benchmarks/migrated-skills/superpowers/verification-before-completion/SKILL.md on GitHub (opens in a new tab) -
Context Management
Compress long interaction history into useful state for future agent turns.
benchmarks/skills/agent/context-management/SKILL.md on GitHub (opens in a new tab) -
Prompt Engineering
Rewrite vague instructions into precise, testable agent prompts.
benchmarks/skills/agent/prompt-engineering/SKILL.md on GitHub (opens in a new tab) -
Self-Improvement Harness
Use failure records to propose, apply, and evaluate skill metadata patches.
benchmarks/skills/agent/self-improvement-harness/SKILL.md on GitHub (opens in a new tab) -
Skill Routing
Select the most relevant agent skill for a user request before execution.
benchmarks/skills/agent/skill-routing/SKILL.md on GitHub (opens in a new tab) -
Tool Planning
Plan safe tool calls and execution order for agent workflows.
benchmarks/skills/agent/tool-planning/SKILL.md on GitHub (opens in a new tab) -
Verifier-Gated Routing
Filter or rerank candidate skills using deterministic verification evidence.
benchmarks/skills/agent/verifier-gated-routing/SKILL.md on GitHub (opens in a new tab) -
Test-Driven Development
Implement behavior by writing failing tests before production code.
benchmarks/skills/coding/test-driven-development/SKILL.md on GitHub (opens in a new tab) -
ASCII Art
Create small text diagrams, visual explanations, and terminal-friendly art.
benchmarks/skills/creative/ascii-art/SKILL.md on GitHub (opens in a new tab) -
Baoyu Comic
Turn technical anecdotes into concise multi-panel comic concepts.
benchmarks/skills/creative/baoyu-comic/SKILL.md on GitHub (opens in a new tab) -
Creative Ideation
Generate divergent ideas, concepts, alternatives, and creative directions.
benchmarks/skills/creative/creative-ideation/SKILL.md on GitHub (opens in a new tab) -
Songwriting and AI Music
Write lyrics, hooks, choruses, melodies, and prompts for AI music tools.
benchmarks/skills/creative/songwriting-and-ai-music/SKILL.md on GitHub (opens in a new tab) -
Data Analysis
Analyze tabular data, compute summary statistics, and explain anomalies.
benchmarks/skills/data-analysis/data-analysis/SKILL.md on GitHub (opens in a new tab) -
Python Data Analysis
Clean datasets and create reproducible Python transformations and charts.
benchmarks/skills/data-analysis/python-data-analysis/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
autoharnessby tigerless-labs Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes t…
-
superpowersby obra An agentic skills framework & software development methodology that works.
-
skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory.
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.