CtrlK
BlogDocsLog inGet started
Tessl Logo

tdg-personal/search-first

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

47

Quality

59%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Overview
Quality
Evals
Security
Files

Quality

Content

50%

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

This skill provides a reasonable framework for research-before-coding but suffers from verbosity (ASCII diagrams, listing well-known tools) and lacks truly actionable, executable guidance. The workflow is well-structured conceptually but missing validation checkpoints and feedback loops. The content would benefit from being trimmed and split across supporting files.

Suggestions

Remove the search shortcuts section (Claude already knows these tools) or move it to a separate SHORTCUTS.md reference file to reduce token usage.

Add explicit validation steps to the workflow, e.g., 'After adopting a package: verify it installs cleanly, check for version conflicts, run a minimal smoke test before proceeding.'

Make the Quick Mode checklist more actionable with actual commands (e.g., specific `rg` patterns, `npm search` commands, `pip search` alternatives) rather than abstract instructions.

Replace the ASCII art workflow diagram with a concise numbered list — the diagram consumes many tokens without adding clarity beyond what the existing sections already provide.

DimensionReasoningScore

Conciseness

The skill includes useful content but is verbose in places — the ASCII workflow diagram, the search shortcuts section (listing well-known tools Claude already knows), and the integration points section add bulk without proportional value. The anti-patterns section states obvious things.

2 / 3

Actionability

The subagent Task invocation template and the decision matrix provide some concrete guidance, but much of the content is conceptual rather than executable. The 'Quick Mode' is a mental checklist rather than concrete commands, and the examples show outcomes rather than step-by-step executable processes.

2 / 3

Workflow Clarity

The 5-step workflow is clearly sequenced and the decision matrix adds useful branching logic. However, there are no validation checkpoints — no step to verify the chosen package actually works, no feedback loop for when an adopted package doesn't meet requirements, and no rollback guidance.

2 / 3

Progressive Disclosure

The content is organized with clear sections and headers, but it's monolithic — the search shortcuts, integration points, and examples sections could be split into separate reference files. No bundle files exist to offload this content, resulting in a long single file.

2 / 3

Total

8

/

12

Passed

Description

50%

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 communicates the core concept of a research-first coding workflow but lacks explicit trigger guidance ('Use when...') and comprehensive natural language trigger terms. It's moderately specific but could be significantly improved with concrete examples of when to invoke this skill and more user-facing keywords.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to find existing libraries, check for packages, research solutions before implementing, or says things like "is there a library for..." or "find a package that..."'

Include more natural trigger terms users would say, such as 'find a package', 'existing solution', 'npm/pip/cargo package', 'dependency', 'look up', 'before implementing'

List more specific concrete actions beyond searching, e.g., 'Evaluates library options, compares alternatives, checks compatibility, and recommends dependencies before writing custom implementations'

DimensionReasoningScore

Specificity

Names the domain (research-before-coding) and some actions (search for existing tools, libraries, and patterns), but doesn't list multiple concrete specific actions beyond searching. 'Invokes the researcher agent' adds some specificity about mechanism.

2 / 3

Completeness

The 'what' is reasonably covered (search for existing tools/libraries/patterns before writing custom code), but there is no explicit 'Use when...' clause. The 'when' is only implied by the workflow description rather than stated with explicit triggers.

2 / 3

Trigger Term Quality

Includes some relevant keywords like 'tools', 'libraries', 'patterns', and 'research', but misses common user phrasings like 'find a library for', 'is there an existing package', 'look up', 'check if there's already', 'npm package', 'dependency', etc.

2 / 3

Distinctiveness Conflict Risk

The concept of 'research-before-coding' is somewhat distinctive, and mentioning the 'researcher agent' helps, but 'search for existing tools, libraries, and patterns' could overlap with general coding assistance or documentation lookup skills.

2 / 3

Total

8

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Reviewed

Table of Contents