CtrlK
BlogDocsLog inGet started
Tessl Logo

think-before-coding

Guardrails for writing, modifying, reviewing, or refactoring code. Use whenever a task involves code to clarify ambiguous requirements before implementation, avoid over-engineering and speculative abstractions, and keep changes minimal and scoped.

73

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is think-before-coding in choegyumin/agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 a lean, well-organized instruction skill that gives concrete actionable guidance with a clear decision workflow and feedback loop. It assumes Claude's competence and avoids padding or unnecessary external references.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, with no padding or explanation of basic concepts; every bullet earns its place (e.g., 'No flexibility or configurability for hypothetical future needs').

5 / 5

Actionability

Provides a concrete, copy-paste-ready decision procedure ('Use the first option that applies: 1...2...3...4...') with specific directives; as an instruction-only skill the absence of code is not penalized because the guidance is directly actionable.

5 / 5

Workflow Clarity

The numbered decision sequence is clearly ordered and includes an explicit feedback loop ('Before proceeding, reconsider any unapproved band-aid... and repeat the sequence'), with well-sequenced sections covering the full process.

5 / 5

Progressive Disclosure

Under 50 lines with no need for external references, the content is well-organized into clearly headed sections (## 1, 2, 3) with no nested or buried references, satisfying the simple-skill exception for a top score.

5 / 5

Total

20

/

20

Passed

Description

81%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 is specific and complete, clearly stating both what the skill does and when to use it. Its main weakness is a very broad trigger that risks overlapping with general coding behavior and other skills.

Suggestions

Narrow the trigger from 'whenever a task involves code' to specific situations like 'when requirements are ambiguous, when tempted to over-engineer, or when scoping a change', to reduce overlap with general coding assistance.

Add natural synonyms users actually say, such as 'building', 'implementing', or 'changing code', to broaden trigger-term coverage.

Lead with the distinctive behavior (clarifying requirements and resisting over-engineering) before the generic 'writing/modifying/reviewing code' framing to sharpen distinctiveness.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'writing, modifying, reviewing, or refactoring code' plus 'clarify ambiguous requirements', 'avoid over-engineering and speculative abstractions', and 'keep changes minimal and scoped' — giving comprehensive coverage rather than just a few.

5 / 5

Completeness

Explicitly answers both what ('Guardrails for writing, modifying, reviewing, or refactoring code') and when ('Use whenever a task involves code to clarify ambiguous requirements before implementation') with concrete trigger phrasing.

5 / 5

Trigger Term Quality

'writing, modifying, reviewing, or refactoring code' and 'task involves code' are natural user phrases, but common synonyms like 'building', 'implementing a feature', or 'changing code' are missing, so it is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

The trigger 'Use whenever a task involves code' is very broad and would fire on almost any coding task, creating high overlap risk with the general coding assistant and many other skills, matching the 'very broad; high overlap risk' anchor.

2 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
choegyumin/agent-skills
Reviewed

Table of Contents

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.