CtrlK
BlogDocsLog inGet started
Tessl Logo

fp-taskeither-ref

Quick reference for TaskEither. Use when user needs async error handling, API calls, or Promise-based operations that can fail.

62

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/fp-taskeither-ref/SKILL.md

The canonical home for this skill is fp-taskeither-ref in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A tight, well-organized, code-forward reference card that gives executable fp-ts patterns for the common TaskEither cases and lands at a solid 4 across every dimension. The remaining gaps are small: a touch of motivational narrative in the comparison section and a few undefined helper names in the pattern examples.

Suggestions

Make the 'Common Patterns' examples self-contained by either defining the helper functions (fetchPosts, toNetworkError, defaultUser) inline or noting they are placeholders, so the snippets are fully copy-paste-runnable.

Trim the 'vs async/await' narrative comments to a single motivating line, keeping the section code-forward to push conciseness toward 5.

If the card grows further, move the 'Common Patterns' block into a references/ file linked from the top, which would let progressive_disclosure reach 5 without bloating the main body.

DimensionReasoningScore

Conciseness

The body is code-forward with terse single-line comments ("Async success", "Transform success value") and a one-line definition; the 'vs async/await' section's narrative ("errors hidden", "Error info lost", "errors typed and composable") is mild over-explanation a maximally lean reference could trim, so it sits at 'efficient; minor instances of over-explanation' rather than the 5-anchor's 'every token earns its place'.

4 / 5

Actionability

Examples use the real fp-ts API (TE.right, TE.map, TE.flatMap, TE.tryCatch, pipe, sequenceT, TE.match) and cover common cases (fetch wrapping, chaining, parallel, recovery); the minor gap is that helpers like fetchPosts, fetchComments, toNetworkError, and defaultUser are referenced but not defined, so it is 'mostly executable' rather than fully copy-paste-runnable.

4 / 5

Workflow Clarity

Organized into a logical Create -> Transform -> Execute -> Common Patterns -> comparison progression with an unambiguous single purpose and no destructive/batch operations (so the validation cap does not apply); it does not reach 5 because a reference card has no explicit validation/feedback-loop checkpoints, and at ~95 lines it is outside the under-50-line simple-skill exception that would auto-grant 5.

4 / 5

Progressive Disclosure

No bundle files exist and none are referenced; the content is a self-contained quick-reference card split into clear, well-labeled sections with no buried or nested references, matching 'good structure; most content appropriately placed'; it stops short of 5 because the body exceeds 50 lines, so the under-50-line simple-skill exception for an auto-5 does not cleanly apply.

4 / 5

Total

16

/

20

Passed

Description

73%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 pairs a 'what' with an explicit 'Use when' trigger clause and uses natural keywords, but it under-specifies the skill's concrete capabilities — calling itself merely a 'quick reference' without naming the actions it covers. Strengthening the 'what' with specific operations would lift its weakest dimension.

Suggestions

Name concrete capabilities in the 'what' clause, e.g. 'Create, transform, chain, and execute TaskEither values for async operations that can fail' — this would move specificity from 2 toward 4-5.

Add a domain-specific trigger synonym such as 'fp-ts' or 'functional error handling' so the skill surfaces for users who name the library rather than the pattern.

Tighten distinctiveness by scoping the 'when' clause to the typed-error / functional-programming context (e.g. 'Use when you need typed, composable errors for async operations in fp-ts') to reduce overlap with generic async error-handling skills.

DimensionReasoningScore

Specificity

Names the domain ("TaskEither") but the only stated action is "Quick reference for TaskEither"; it does not enumerate concrete capabilities like create/transform/chain/execute, so it matches 'names the domain but actions are minimal or generic' rather than the 3-anchor which requires 1-2 concrete actions.

2 / 5

Completeness

Explicitly answers both: 'what' ("Quick reference for TaskEither") and 'when' ("Use when user needs async error handling, API calls, or Promise-based operations that can fail") with concrete trigger phrases, matching the 5-anchor; the 'Use when' clause is present so the missing-trigger cap does not apply.

5 / 5

Trigger Term Quality

Includes three natural phrases a user would say — "async error handling", "API calls", "Promise-based operations that can fail" — giving good keyword coverage; it sits above the 3-anchor (some keywords, missing variations) but misses synonyms like 'fp-ts', 'monad', 'retry', or 'chain async' that would reach 5.

4 / 5

Distinctiveness Conflict Risk

TaskEither is a specific fp-ts niche giving a clear identity, but the triggers "async error handling" and "API calls" are broad enough to risk minor overlap with general error-handling or retry skills, placing it at 'mostly distinct; minor overlap risk' rather than the 5-anchor's minimal conflict risk.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.