Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

fp-errors

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

Quality

62%

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

56%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 thorough, highly actionable fp-ts pattern catalog with strong before/after examples, but it is far too verbose for a skill: it re-teaches concepts Claude already knows, duplicates examples, and inlines everything instead of splitting into reference files. Trimming motivational blocks and moving the quick reference and advanced scenarios into references/ would substantially improve token efficiency and structure.

Suggestions

Cut the 'Before' try/catch-hell blocks and Left/Right mnemonic explanations — Claude already knows why exceptions are untyped — and keep only the Either/TaskEither patterns themselves.

Move the Quick Reference table and the 'Real Scenarios' section into references/ files (e.g. references/quick-reference.md, references/scenarios.md), keeping SKILL.md as a concise overview pointing to them.

Deduplicate the processUserOrder and form-validation examples (each pattern is demonstrated twice) and declare all imports per snippet so examples are fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The ~840-line body includes long motivational 'Before: try/catch hell' blocks, Left/Right mnemonics ('think "right" as in "correct"'), and duplicated examples (processUserOrder and form validation each shown twice), plus fp-ts basics Claude already knows — matching 'noticeably verbose; several padded sections' rather than the mostly-efficient anchor at 3.	2 / 5
Actionability	Nearly all guidance is concrete, executable TypeScript with usage examples and expected outputs (e.g. the parseInput and fetchWithErrorHandling scenarios), but minor gaps remain: snippets rely on undefined helpers (db.find, fetchPosts, deleteUser) and some later snippets use O/A imports never declared — 'mostly executable with minor gaps' rather than fully copy-paste ready.	4 / 5
Workflow Clarity	The pattern catalog is clearly sequenced (problem → Either basics → chaining → validation → async → conversions → real scenarios) with a when-to-use Quick Reference table and a 5-point summary; it is a reference skill with no destructive workflow requiring validation checkpoints, but there is no explicit guidance for choosing among the patterns, keeping it at 4.	4 / 5
Progressive Disclosure	Sections are well-organized with headers and a quick-reference table, but it is an 840-line monolith with zero bundle files — the Quick Reference, the real-scenario walkthroughs, and the TaskEither deep-dive clearly belong in separate reference files, matching 'some structure but content that should be separate is inline'.	3 / 5
	Total	13 / 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 communicates the core idea and the specific tools (Either/TaskEither) in a punchy, concise way, but it lacks any 'when to use' trigger guidance and omits ecosystem keywords like fp-ts and TypeScript that users would naturally mention. Adding an explicit 'Use when...' clause with those keywords would lift both completeness and trigger quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user mentions fp-ts, Either, TaskEither, functional error handling in TypeScript, or wants to replace try/catch with typed errors.'

Include the ecosystem keywords 'fp-ts' and 'TypeScript' so the description matches how users actually reference this library.

Expand the 'what' with 1-2 more concrete capabilities (e.g. 'collect validation errors' or 'wrap async operations with TaskEither') to improve specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain and concrete mechanisms — 'handle errors as values using Either and TaskEither' — but presents essentially one action ('stop throwing' restated as 'handle errors as values'), matching the '1-2 concrete actions, not comprehensive' anchor rather than the several-actions anchor at 4.	3 / 5
Completeness	It has a clear 'what' (handle errors as values with Either/TaskEither) but no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Terms like 'throwing', 'errors as values', 'Either', and 'TaskEither' are natural for users in this niche, but common variations users would actually say — 'fp-ts', 'TypeScript', 'functional programming', 'try/catch', 'Result type' — are absent, matching the 'relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Either and TaskEither' are distinctive constructs that carve out a clear fp-ts niche, but the generic 'handle errors' framing could still overlap with broader error-handling or TypeScript skills, so it sits at 'mostly distinct; minor overlap risk' rather than 5.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/fp-errors/SKILL.md
Revision: 64adc55

Reviewed: 14 days ago

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.

fp-errors

Table of Contents

Is this your skill?