Is the Authoring skill free?

Yes. The skill itself is free from OdradekAI/bundles-forge. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Authoring SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Authoring?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Authoring with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Authoring

Writes and rewrites SKILL.md and agent files to project conventions

by OdradekAI · OdradekAI/bundles-forge

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 31, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 08f68ee

Fetched SKILL.md via the GitHub API tree + raw; all three body-referenced files (skill-writing-guide.md, quality-checklist.md, agent-authoring-guide.md) returned HTTP 200. Frontmatter parses with name+description; no security smells; only external dep is the bundles-forge audit-skill CLI, which the skill documents a manual fallback for. Output test: wrote two SKILL.md drafts for a hypothetical commit-message skill. Baseline used a Title-Case name and a workflow-summary description ("This skill helps you write... formats them...") — exactly the anti-pattern the skill warns against — with no skill-type declaration, no why-motivated steps, no Common Mistakes/Inputs/Outputs/Integration sections, ending in bare Always/Never directives. Following the skill produced a kebab-case name, a 188-char "Use when..." triggering-only description, an Overview with core-principle + skill-type + announce line, process steps each justifying why, a 4-row Common Mistakes table, and Inputs/Outputs/Integration with artifact IDs. Concrete, observed difference.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Authoring does

Guides writing, completing, integrating, or improving SKILL.md and agents/*.md content inside a bundle-plugin, with four explicit paths (new, integrate, complete, improve) plus conventions for descriptions, body structure, and token budget. Triggers when authoring or rewriting skill/agent definitions, filling scaffolded stubs, adapting external skills, or fixing descriptions that do not trigger reliably. Validation runs the bundles-forge audit-skill CLI with a documented manual checklist fallback.

How to install Authoring

git clone --depth 1 https://github.com/OdradekAI/bundles-forge.git /tmp/authoring-src
mkdir -p ~/.claude/skills
cp -R /tmp/authoring-src/skills/authoring ~/.claude/skills/authoring
# Standalone: works without extra deps; references/ (skill-writing-guide.md, quality-checklist.md,
#   agent-authoring-guide.md) ship inside the copied dir.
# Optional validation step: SKILL.md's Post-Action Validation runs `bundles-forge audit-skill <dir>`,
#   which needs the full plugin. Install via Claude Code marketplace instead to get that CLI:
#   /plugin marketplace add OdradekAI/bundles-forge
#   /plugin install bundles-forge@bundles-forge-dev
# Without the CLI the skill falls back to references/quality-checklist.md (manual review).

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Authoring

/authoring Writes and rewrites SKILL.md and agent files to project conventions

It also activates on plain-language prompts like these:

Rewrite this SKILL.md for better triggering
Fill in this scaffolded skill stub
Integrate this external skill into our bundle

Frequently asked questions

Is the Authoring skill free?: Yes. The skill itself is free from OdradekAI/bundles-forge. SkillProof publishes the install command and an independent test verdict at no cost.
Does Authoring work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Tested · Works. Fetched SKILL.md via the GitHub API tree + raw; all three body-referenced files (skill-writing-guide.md, quality-checklist.md, agent-authoring-guide.md) returned HTTP 200. Frontmatter parses with name+description; no security smells; only external dep is the bundles-forge audit-skill CLI, which the skill documents a manual fallback for. Output test: wrote two SKILL.md drafts for a hypothetical commit-message skill. Baseline used a Title-Case name and a workflow-summary description ("This skill helps you write... formats them...") — exactly the anti-pattern the skill warns against — with no skill-type declaration, no why-motivated steps, no Common Mistakes/Inputs/Outputs/Integration sections, ending in bare Always/Never directives. Following the skill produced a kebab-case name, a 188-char "Use when..." triggering-only description, an Overview with core-principle + skill-type + announce line, process steps each justifying why, a 4-row Common Mistakes table, and Inputs/Outputs/Integration with artifact IDs. Concrete, observed difference.
What is the Authoring SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Authoring?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Authoring with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.