Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion skills/autonomous-ai-agents/claude-code/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
name: claude-code
description: "Delegate coding to Claude Code CLI (features, PRs)."
description: "Hand a coding task to Claude Code CLI; ignore name mentions."
version: 2.2.0
author: Hermes Agent + Teknium
license: MIT
Expand Down
2 changes: 1 addition & 1 deletion skills/autonomous-ai-agents/codex/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
name: codex
description: "Delegate coding to OpenAI Codex CLI (features, PRs)."
description: "Hand a coding task to OpenAI Codex; ignore name mentions."
version: 1.0.0
author: Hermes Agent
license: MIT
Expand Down
2 changes: 1 addition & 1 deletion skills/autonomous-ai-agents/hermes-agent/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
name: hermes-agent
description: "Configure, extend, or contribute to Hermes Agent."
description: "Edit Hermes source/config; ignore general runtime mentions."
version: 2.3.0
author: Hermes Agent + Teknium
license: MIT
Expand Down
2 changes: 1 addition & 1 deletion skills/autonomous-ai-agents/opencode/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
name: opencode
description: "Delegate coding to OpenCode CLI (features, PR review)."
description: "Hand a coding task to OpenCode CLI; ignore name mentions."
version: 1.2.0
author: Hermes Agent
license: MIT
Expand Down
2 changes: 1 addition & 1 deletion skills/creative/claude-design/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
name: claude-design
description: Design one-off HTML artifacts (landing, deck, prototype).
description: "Build a single-file HTML/CSS design artifact from scratch."
version: 1.1.0
author: BadTechBandit
license: MIT
Expand Down
2 changes: 1 addition & 1 deletion skills/dogfood/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
name: dogfood
description: "Exploratory QA of web apps: find bugs, evidence, reports."
description: "Manually QA a running web app in a real browser for bugs."
version: 1.0.0
platforms: [linux, macos, windows]
metadata:
Expand Down
2 changes: 1 addition & 1 deletion skills/note-taking/obsidian/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
name: obsidian
description: Read, search, create, and edit notes in the Obsidian vault.
description: "Read or edit files in the local Obsidian markdown vault."
platforms: [linux, macos, windows]
---

Expand Down
2 changes: 1 addition & 1 deletion skills/research/research-paper-writing/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
name: research-paper-writing
title: Research Paper Writing Pipeline
description: "Write ML papers for NeurIPS/ICML/ICLR: design→submit."
description: "Author a formal academic ML paper for a venue submission."
version: 1.1.0
author: Orchestra Research
license: MIT
Expand Down
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
name: requesting-code-review
description: "Pre-commit review: security scan, quality gates, auto-fix."
description: "Review a concrete code diff before committing it."
version: 2.0.0
author: Hermes Agent (adapted from obra/superpowers + MorAlekss)
license: MIT
Expand Down
2 changes: 1 addition & 1 deletion skills/software-development/simplify-code/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
name: simplify-code
description: "Parallel 3-agent cleanup of recent code changes."
description: "Simplify or clean up a user's recent code diff on request."
version: 1.0.0
author: Hermes Agent (inspired by Claude Code /simplify)
license: MIT
Expand Down
2 changes: 1 addition & 1 deletion skills/software-development/spike/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
name: spike
description: "Throwaway experiments to validate an idea before build."
description: "Run a throwaway code spike to validate feasibility."
version: 1.0.0
author: Hermes Agent (adapted from gsd-build/get-shit-done)
license: MIT
Expand Down
2 changes: 1 addition & 1 deletion skills/software-development/systematic-debugging/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
name: systematic-debugging
description: "4-phase root cause debugging: understand bugs before fixing."
description: "Debug a concrete, reproducible software defect methodically."
version: 1.1.0
author: Hermes Agent (adapted from obra/superpowers)
license: MIT
Expand Down
16 changes: 9 additions & 7 deletions skills/software-development/test-driven-development/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
name: test-driven-development
description: "TDD: enforce RED-GREEN-REFACTOR, tests before code."
description: "Write code using TDD with a unit/integration test suite."
version: 1.1.0
author: Hermes Agent (adapted from obra/superpowers)
license: MIT
Expand All @@ -23,18 +23,20 @@ Write the test first. Watch it fail. Write minimal code to pass.

## When to Use

**Always:**
**Use when writing or changing testable production source code:**
- New features
- Bug fixes
- Refactoring
- Behavior changes

**Exceptions (ask the user first):**
- Throwaway prototypes
- Generated code
- Configuration files
Once it applies, "skip TDD just this once" is rationalization — stop.

Thinking "skip TDD just this once"? Stop. That's rationalization.
**Do NOT load this skill for (it does not apply):**
- Research, exploration, or optimization loops (e.g. perf/benchmark tuning, kernel/leaderboard work)
- Tasks where "test", "gate", "verify", "PASS", "prove", or "correctness" mean an **external** checker, acceptance gate, or submission mode — not a code-level unit/integration test suite
- Data/ML experiments, throwaway prototypes, generated code, configuration files

If the prompt is saturated with testing/verification vocabulary but isn't asking you to write production code against a test suite, this is a keyword false-positive — do not load TDD.

## The Iron Law

Expand Down
Loading