search-first

Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Systematizes the "search for existing solutions before implementing" approach. Use when starting new features or adding functionality.

Quality

65%

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 ./.kiro/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 content is well-structured and actionable, with a clear sequenced workflow, concrete package shortcuts, and useful worked examples. Its main weakness is redundancy across the intro, Trigger, and When-to-Use sections plus some speculative integration-point padding.

Suggestions

Merge the intro line, Trigger section, and 'When to Use This Skill' into a single trigger block to remove triplicated content and improve conciseness.

Trim or remove the 'Integration Points' planner/architect sections, which are speculative and add length without actionable steps for the skill itself.

Consider shrinking the ASCII workflow diagram to a compact list, since the Decision Matrix and How-to-Use sections already convey the same steps.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of basic-concept padding, but it repeats the same trigger/setup information in the intro, Trigger, and 'When to Use This Skill' sections, and the large ASCII workflow diagram plus speculative 'Integration Points' with planner/architect agents could be trimmed, matching 'mostly efficient but some unnecessary content'.	3 / 5
Actionability	It gives concrete, executable guidance: named packages per category, actual npm/PyPI search strings, a ready-to-use subagent prompt template, and worked examples with scores, fitting 'mostly executable guidance with minor gaps'.	4 / 5
Workflow Clarity	The five-step workflow (Need Analysis -> Parallel Search -> Evaluate -> Decide -> Approval Checkpoint/Implement) is clearly sequenced with an explicit approval checkpoint and a decision matrix, matching 'clear sequence with most checkpoints present; minor gaps'.	4 / 5
Progressive Disclosure	The single SKILL.md is well organized into clearly labeled sections (Trigger, Scope, Workflow, Decision Matrix, How to Use, Examples, Anti-Patterns) with no bundle files needed; it is slightly long but appropriately structured, matching 'good structure; most content appropriately placed'.	4 / 5
	Total	15 / 20 Passed

Description

62%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 cleanly states both what the skill does and when to use it with a distinct research-before-coding niche, but it is light on concrete actions and trigger-term variety. The redundant restating sentence slightly weakens specificity.

Suggestions

Replace the restated second sentence with an additional concrete action (e.g., 'Evaluate and score candidate libraries by maintenance, license, and fit') to lift specificity.

Broaden the trigger phrase with natural synonyms like 'before writing code', 'adding a dependency', or 'when asked to add X functionality'.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete action ('Search for existing tools, libraries, and patterns before writing custom code'), but the second sentence merely restates the same search action rather than adding distinct capabilities, matching the '1-2 concrete actions' anchor.	3 / 5
Completeness	It answers both 'what' (search for existing tools/libraries/patterns) and 'when' ('Use when starting new features or adding functionality'), but the 'when' clause is general and could be more explicit, fitting the 'both what and when; when could be more specific' anchor.	4 / 5
Trigger Term Quality	'Use when starting new features or adding functionality' provides relevant trigger phrases, but coverage is thin with no synonyms or common variations (e.g., 'add a dependency', 'before writing code'), matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Research-before-coding' is a clearly distinct niche with minimal overlap risk against most skills, though it could conceivably overlap with generic coding/planning skills, matching 'mostly distinct; minor overlap risk'.	4 / 5
	Total	14 / 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: .kiro/skills/search-first/SKILL.md
Commit: d8409a4

Reviewed: 1 day 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.