claude-code-templates

Boilerplate templates for Claude Code extensions. Triggers on: create agent, new skill, command template, hook script, extension scaffold.

1.23x

Quality

—

Does it follow best practices?

Impact

100%

1.23x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is action-oriented with concrete copy-paste commands and clear section structure, but it redundantly lists the same four templates three times and references an assets directory that does not exist. Validation guidance is present but shallow.

Suggestions

Consolidate the Template Selection, Template Locations, and Assets sections into a single table to remove the triple repetition of the four template files.

Ship the referenced bundle files under ./assets/ (agent-template.md, skill-template.md, command-template.md, hook-script.sh) so the disclosed references resolve, or remove the file references.

Strengthen the Validation section into a real checkpoint — e.g., verify frontmatter parses and `name:` matches the filename before proceeding — instead of the superficial `head`/`grep` checks.

Dimension	Reasoning	Score
Conciseness	The body is table-driven and free of concept-padding, but the same four template files are listed three times (Template Selection table, Template Locations table, and the Assets list), which is unnecessary repetition that could be tightened.	2 / 3
Actionability	Quick Start provides fully executable, copy-paste-ready commands with concrete paths — `cp ~/.claude/skills/.../agent-template.md`, `mkdir -p`, `chmod +x`, `just test`.	3 / 3
Workflow Clarity	Four creation workflows are clearly sequenced with copy-then-edit steps, but the Validation section (`head -20`, `grep "^name:"`, `just test`) is superficial with no real validation feedback loop or checkpoint.	2 / 3
Progressive Disclosure	Sections are well organized with one-level-deep references to `./assets/` files, but the referenced bundle files (agent-template.md, skill-template.md, command-template.md, hook-script.sh) do not exist — the assets directory is missing, breaking the disclosed navigation.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concise description that states a clear purpose and supplies explicit, natural-language triggers covering each extension type. It answers both what and when without fluff.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "create agent, new skill, command template, hook script, extension scaffold" — covering the full range of extension types rather than partial naming.	3 / 3
Completeness	It answers both "what" ("Boilerplate templates for Claude Code extensions") and "when" via the explicit "Triggers on:" clause, matching an explicit Use-when trigger.	3 / 3
Trigger Term Quality	"Triggers on: create agent, new skill, command template, hook script, extension scaffold" gives good coverage of natural phrases a user would actually say across the four extension kinds.	3 / 3
Distinctiveness Conflict Risk	The niche is clearly Claude Code extension scaffolding with per-type triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.