fp-errors

Stop throwing everywhere - handle errors as values using Either and TaskEither for cleaner, more predictable code

Quality

48%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/fp-errors/SKILL.md

Quality

Content

52%Scale 1-5

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

This skill provides solid, actionable fp-ts error handling patterns with realistic before/after comparisons and executable code. However, it is significantly over-length due to extensive 'before' anti-pattern examples and explanations of concepts Claude already knows. The monolithic structure with no progressive disclosure into supporting files makes it a heavy context-window consumer that could be substantially tightened.

Suggestions

Cut the 'before' anti-pattern blocks significantly — a 1-2 line description of the problem is sufficient; Claude doesn't need 20-line examples of messy try/catch code to understand why Either is better.

Remove explanations of basic concepts like 'Left = error case, Right = success case (think "right" as in "correct")' — Claude knows fp-ts.

Split the Real Scenarios section and Quick Reference table into separate bundle files (e.g., EXAMPLES.md, REFERENCE.md) and link to them from the main skill.

Ensure all imports are complete — `O` from fp-ts/Option is used in processAllCollectErrors without being imported.

Dimension	Reasoning	Score
Conciseness	The skill is significantly verbose at ~500+ lines. It extensively shows 'before' anti-patterns that Claude already understands, explains basic concepts like what Either is ('Left = error case, Right = success case'), and includes lengthy 'messy' code blocks that pad the content. The core patterns could be conveyed in roughly half the space.	2 / 5
Actionability	The code examples are concrete, executable TypeScript with proper imports and realistic usage patterns. Minor gaps exist (some functions use `{ ... }` placeholder bodies, and some imports like `O` from Option are used without being imported), but overall the guidance is highly actionable with copy-paste ready patterns.	4 / 5
Workflow Clarity	The skill follows a logical progression from simple Either usage through chaining, validation, async TaskEither, and conversion patterns. The sequence is clear and builds well. However, there are no explicit validation/verification checkpoints (e.g., 'test your pipeline by running X'), though this is less critical for a pattern/library skill than for destructive operations.	4 / 5
Progressive Disclosure	All content is inlined in a single monolithic file with no references to supporting files. The quick reference table, real-world scenarios, and detailed validation examples could easily be split into separate reference files. For a skill this long (~500+ lines), the lack of any file decomposition is a notable organizational weakness.	2 / 5
	Total	12 / 20 Passed

Description

45%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 communicates a clear concept (functional error handling with Either/TaskEither) but reads more like a persuasive tagline ('Stop throwing everywhere') than a skill selection description. It lacks an explicit 'Use when...' clause and misses important trigger terms and synonyms that users might naturally use when seeking this kind of help.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to refactor try/catch blocks, handle errors functionally, or work with fp-ts Either/TaskEither types.'

Include more natural trigger terms and synonyms such as 'fp-ts', 'try/catch refactoring', 'Result type', 'functional error handling', 'railway-oriented programming'.

Replace the imperative/tagline tone ('Stop throwing everywhere') with concrete action descriptions in third person, e.g., 'Refactors exception-based error handling into Either and TaskEither patterns for type-safe, composable error flows.'

Dimension	Reasoning	Score
Specificity	Names the domain (error handling) and mentions specific concepts (Either, TaskEither, errors as values), but doesn't list concrete actions like 'refactor try/catch blocks' or 'convert Promise chains to TaskEither pipelines'.	3 / 5
Completeness	The 'what' is weakly implied (handle errors as values using Either/TaskEither) but there is no explicit 'when' clause. The description reads more like a tagline or pitch than a skill selection guide. Missing a 'Use when...' clause caps this at 3, and the vague 'what' brings it to 2.	2 / 5
Trigger Term Quality	Includes some relevant keywords like 'Either', 'TaskEither', 'errors as values', and 'throwing', but misses natural user phrases like 'fp-ts', 'functional error handling', 'try/catch', 'Result type', 'monadic error handling', or 'railway-oriented programming'.	3 / 5
Distinctiveness Conflict Risk	The mention of Either and TaskEither specifically narrows this to functional programming error handling patterns, making it fairly distinct from general error handling or other coding skills. Minor overlap risk with general FP skills or broader error handling skills.	4 / 5
	Total	12 / 20 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (860 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/fp-errors/SKILL.md
Commit: 57c135b

Reviewed: 4 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.