search-first

Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/search-first/SKILL.md

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 highly actionable with concrete commands, package names, and copy-paste examples, and the workflow is well-sequenced, but it lacks explicit validation checkpoints and keeps reference-style content inline in a longer single file rather than splitting it out.

Suggestions

Add an explicit validation checkpoint in the workflow, e.g. after EVALUATE: "Install the candidate in a scratch test, verify it meets constraints, and only then ADOPT/EXTEND; if it fails, re-search."

Move the per-category search shortcuts and integration-points material into a reference file (e.g. references/search-shortcuts.md) linked from the main body to slim the SKILL.md overview.

Trim redundancy between the ASCII workflow diagram and the decision matrix so each token earns its place.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but the ASCII workflow diagram, decision matrix, and how-to-use section overlap somewhat, and the ~130 lines could be tightened despite being mostly actionable.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance: `rg` searches, `npm install textlint-rule-no-dead-link`, checks of `~/.claude/settings.json` and `~/.claude/skills/`, a filled-in Task() agent prompt, and named packages per category.	3 / 3
Workflow Clarity	The five-step sequence (Need Analysis → Parallel Search → Evaluate → Decide → Implement) is clear and the decision matrix maps signals to actions, but there is no explicit validation/verification checkpoint or fix-and-retry feedback loop before adopting a dependency.	2 / 3
Progressive Disclosure	Sections are well-organized with clear headers and no nested references, but the file exceeds 50 lines with all content inline; reference-style material (search shortcuts, integration points) could be split into separate files for a cleaner overview.	2 / 3
	Total	9 / 12 Passed

Description

60%

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

The description is specific about what the skill does and names concrete actions, but lacks an explicit "Use when..." trigger clause and has only moderate coverage of natural user phrasings, leaving the when-implied and distinctiveness somewhat weak.

Suggestions

Add an explicit trigger clause, e.g. "Use when starting a new feature, adding a dependency or integration, or before writing a new utility/helper/abstraction layer."

Broaden trigger terms to natural user phrasings such as "find a library for", "is there an existing package", or "avoid reinventing the wheel".

Sharpen distinctiveness by naming the researcher agent and the adopt/extend/build decision up front so it cannot be confused with a generic research or planning skill.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Search for existing tools, libraries, and patterns" and "Invokes the researcher agent" — rather than vague language, matching the multiple-specific-actions anchor.	3 / 3
Completeness	The "what" is clear (research-before-coding, search existing solutions, invoke researcher agent), but there is no explicit "Use when..." clause; the "when" is only implied by "before writing custom code", which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Relevant keywords appear ("existing tools", "libraries", "patterns", "custom code") but coverage of natural phrasings a user would say is limited and misses common variations like "find a library for X" or "don't reinvent the wheel".	2 / 3
Distinctiveness Conflict Risk	The "researcher agent" + "before writing custom code" framing gives it a niche, but it could still overlap with generic research or planning skills, so it does not reach the clear-distinct-triggers anchor.	2 / 3
	Total	9 / 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: xu-xiang/everything-claude-code-zh
Path: skills/search-first/SKILL.md
Commit: dfbf946

Reviewed: 16 minutes 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.