search-first

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

Quality

60%

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

67%Weight 40%Scale 1-5

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

The body is a well-structured, actionable reference with concrete commands, a clear sequenced workflow, and a useful decision matrix. Its main weakness is moderate verbosity in the ASCII diagram, Integration Points, and example sections that could be tightened for token efficiency.

Suggestions

Condense the ASCII workflow diagram into a compact numbered list to reduce token cost while preserving sequence.

Trim or merge the Integration Points section, which is largely abstract and duplicates guidance already implied by the workflow.

Reduce the three worked examples to one canonical example plus a one-line table of variants to reclaim tokens.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient tables and concrete lists without explaining concepts Claude already knows, but the ASCII workflow diagram, the Integration Points section, and three worked examples add length that could be trimmed without losing actionable value.	3 / 5
Actionability	It provides concrete, executable guidance including real commands ('rg --files', 'gh auth status', 'ls ~/.claude/skills'), a copy-ready Agent invocation template, a decision matrix, and named packages to install, with only minor gaps (placeholder template fields).	4 / 5
Workflow Clarity	Steps 0-5 are clearly sequenced and Step 0 includes a preflight with explicit 'If missing' fallbacks plus an anti-pattern against silent skipping; it lacks an explicit validate-fix-retry loop but the operation is non-destructive so no cap applies.	4 / 5
Progressive Disclosure	No bundle files exist and the single SKILL.md is well-organized with clear section headers (Trigger, Workflow, Decision Matrix, How to Use, Shortcuts, Examples, Anti-Patterns); minor organization gaps in the inline Shortcuts and Integration Points sections keep it just below 5.	4 / 5
	Total	15 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 clearly states what the skill does but lacks an explicit 'Use when...' trigger clause and the natural trigger phrases a user would actually say, capping completeness and trigger-term quality. It is reasonably specific and distinct from sibling skills.

Suggestions

Add an explicit trigger clause such as 'Use when adding a feature, dependency, or integration before writing custom code.'

Surface natural user phrasings ('add X functionality', 'add a dependency', 'integrate X') in the description to improve trigger-term quality.

List the concrete capability outcomes (search registries/MCP/skills, evaluate candidates, recommend adopt/extend/build) to lift specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain (research-before-coding) and a couple concrete actions ('Search for existing tools, libraries, and patterns', 'Invokes the researcher agent'), but the action set is essentially one search operation applied to three targets rather than a comprehensive list of capabilities.	3 / 5
Completeness	The 'what' is clear (research-before-coding workflow that searches for existing solutions), but the 'when' is only weakly implied via 'before writing custom code' with no explicit 'Use when...' clause, so completeness is capped at 3 per the rubric guidance.	3 / 5
Trigger Term Quality	It includes some relevant keywords ('existing tools, libraries, and patterns', 'custom code') but omits the natural phrases users actually say ('add a feature', 'add a dependency', 'integrate X'), which only appear in the body rather than the description.	3 / 5
Distinctiveness Conflict Risk	The research-first framing plus 'Invokes the researcher agent' carve out a fairly distinct niche with only minor overlap risk against general coding skills.	4 / 5
	Total	13 / 20 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/search-first/SKILL.md
Commit: e04ea0b

Reviewed: 2 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.