EONRaider
UserBuild, validate, secure, and maintain Claude Skills — a plugin superseding Anthropic's shipped skill-creator with spec-compliant, security-hardened tooling.
Categories
Indexed Skills (6)
creating-skills
Create new Claude Skills from scratch, or validate, secure, and evaluate ones already drafted. Use when the user wants to build a skill, package a repeated workflow into something Claude can reuse, or asks whether something "should be a skill" — this runs a decision gate first (skill vs. CLAUDE.md vs. AGENTS.md vs. MCP vs. subagent vs. plugin) and checks whether something already covers the request before writing anything new. Also use for validating a SKILL.md's frontmatter, gerund naming, or portable-field compliance; scanning a skill for leaked secrets or unsafe patterns; benchmarking a skill's task-success rate with and without it enabled; or optimizing a description for triggering accuracy. Covers Claude Code, Claude.ai, Cowork, Claude Tag, and Messages API authoring, targeting the cross-vendor agentskills.io spec by default. Use even without the word "skill" — "turn this into something Claude can reuse", "why isn't my skill triggering", "is this safe to publish", "does this frontmatter look right".
user-invoked-fixture
Export the current fixture data to a formatted report file.
drafting-changelog-entries
Draft a CHANGELOG.md entry for SkillArtisan by cross-referencing what was actually built against the master spec's Gap Table, so nothing gets marked closed that isn't verifiably true of the repo. Use when a build session (or a stage/prompt) has finished and it's time to record what shipped, when asked to "update the changelog," "draft release notes," "write up what we just built," or "check what's still open," or when preparing a version bump (major = v-stage boundary per this project's semver interpretation, minor = new capability within a stage, patch = a fix). Use even without the word "changelog" — "what's left before this ships," "summarize this session for the log," "did we close row 12."
third-party-fixture
Reviews dependency manifests for known-vulnerable version pins. Use when the user asks for a dependency security review or mentions vulnerable packages.
gha-fix-pr-smoke-test
Use when manually smoke-testing the GitHub Action's fix-PR path end to end. This is a disposable test fixture for skill-artisan's own CI, not a real user-facing skill, and is deliberately missing evals/lifecycle classification so the audit always finds FAIL items to fix.
model-triggered-fixture
Use when the user wants to export fixture data to a formatted report, mentions exporting test data, or wants to generate a fixture report file, even if they don't say "report" explicitly. This is a test fixture for skill-artisan's own test suite, not a real user-facing skill.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.