Pandemonium-Research

This skill has a name that uses spaces and capital letters instead of kebab-case, so the validator should flag the name format as non-conformant while every other check in the report stays perfectly valid and passing.

This skill intentionally carries a description that runs well past the one thousand and twenty four character limit defined by the skill specification so that the validator can flag it under the description-format check. It keeps repeating filler guidance about what the skill does and when to use it in order to inflate the character count without adding any real meaning. Use this skill when you want a fixture whose description is long enough to breach the maximum allowed length while still containing plenty of words and reading like a plausible, if overly verbose, description. It goes on to describe imaginary triggers, imaginary file types, and imaginary workflows purely to consume characters. It continues describing more and more scenarios, more and more trigger phrases, and more and more capabilities until the total number of characters comfortably exceeds the documented ceiling of one thousand and twenty four characters, at which point the description-format check should record an error and withhold the as

This skill is well formed except that it includes a README.md inside the skill folder, which the specification disallows, so the validator should emit a warning under the no-readme check without blocking anything.

This skill uses a reserved word in its name, which Anthropic does not permit, so the validator should flag the name as containing a reserved word even though the kebab-case shape is fine.

This skill embeds an XML tag such as the <tool> element inside its description, which is forbidden because frontmatter is injected into the system prompt, so the validator should flag the description format as containing angle brackets.

This skill references a missing file using a markdown link with a fragment anchor. The validator should strip the anchor and flag the missing file as a broken reference.

This skill references a bundled resource using inline-code style, the canonical form from the skill guide. The referenced file is missing so the validator should flag it.

This skill references a bundled resource using inline-code style, and that referenced file exists in the package. The validator should treat referenced resources as passing.

Guides you through designing and writing a new Claude skill from scratch — determines the right complexity tier, writes the SKILL.md with correct frontmatter and instructions, and scaffolds any supporting assets, references, or scripts the skill needs.

Guides you through designing and packaging a complete skillset — determines what skills belong together, writes the SKILLSET.md manifest, identifies shared assets, and produces the full directory layout with all skill files ready to install.

Generates structured competitor breakdowns from information you provide. Uses a bundled analysis framework to evaluate competitors across consistent dimensions — positioning, pricing, features, weaknesses, and moat — and outputs a formatted report ready to share with stakeholders or paste into a product document.

Produces structured summaries of academic or technical papers. Fills a consistent template covering abstract, key contributions, method, results, limitations, and relevance. Calibrates terminology and depth to a named audience using the shared audience personas reference — so the summary is useful to the right reader, not just accurate.

Explains complex technical topics in plain language calibrated to a named audience. Loads a shared audience personas reference to determine vocabulary level, assumed prior knowledge, and preferred explanation style — so the explanation lands for that specific reader, not for a generic one.

Produces CHANGELOG entries from git history following the Keep a Changelog format. Uses a bundled script to extract commits since the last tag, classifies them into changelog sections using the shared commit conventions reference, and outputs a ready-to-paste release block.

Writes well-formed commit messages following the Conventional Commits specification. Infers the commit type and scope from the staged diff and changed file paths, asks for clarification only when the intent is genuinely ambiguous, and formats the result ready to paste into your terminal.

Generates structured pull request descriptions from the staged diff and branch name. Fills in a standard PR template covering summary, what changed and why, testing steps, and any notes for reviewers — so you spend time on the code, not on writing boilerplate.