haskell-pro

Expert Haskell engineer specializing in advanced type systems, pure functional design, and high-reliability software. Use PROACTIVELY for type-level programming, concurrency, and architecture guidance.

Quality

66%

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/haskell-pro/SKILL.md

Quality

Content

53%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 compact, well-sectioned Haskell guidance skill that names the right tools and principles but stays at the level of abstract advice with no executable examples, concrete workflows, or validation steps. The generic 'Use/Do not use/Instructions' boilerplate adds length without value.

Suggestions

Replace the generic 'Use/Do not use/Instructions' boilerplate with Haskell-specific triggers and concrete first steps, or remove it entirely.

Add at least one runnable GHCi example or a concrete Cabal/Stack snippet to lift actionability above high-level principles.

Turn the 'Approach' list into a sequenced workflow with an explicit validation step (e.g. 'compile with -Wall', 'run QuickCheck properties') so multi-step work has checkpoints.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but the 'Use this skill when'/'Do not use this skill when' and 'Instructions' sections are generic boilerplate ('Working on haskell pro tasks or workflows', 'Apply relevant best practices and validate outcomes') that earns no token value, matching the 'mostly efficient but some unnecessary content' anchor.	3 / 5
Actionability	Named libraries (STM, async, Aeson, Megaparsec, Cabal/Stack, QuickCheck/Hspec) and an Approach list give some concrete guidance, but there is no executable code, no commands, and no worked examples — guidance remains high-level principles, so it sits at 'some concrete guidance but incomplete' rather than 4.	3 / 5
Workflow Clarity	The 'Approach' section offers a 7-step sequence, but the steps are design principles rather than an ordered process, and there are no validation checkpoints or feedback loops; the generic 'validate outcomes' instruction is implicit, matching the 3 anchor 'steps listed but validation gaps'.	3 / 5
Progressive Disclosure	At under 50 lines with no bundle files, the well-organized sections (Focus Areas, Approach, Output) give good structure and easy navigation, but the weak generic 'Instructions' block and lack of any signaled references keep it just below the clean 5 anchor.	4 / 5
	Total	13 / 20 Passed

Description

78%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.

A solid, third-person description that states both capabilities and explicit use triggers for a well-defined Haskell niche. The main weakness is that triggers are framed as directives ('Use PROACTIVELY for') rather than as natural phrases a user would say.

Suggestions

Reframe the 'when' clause around user-said triggers, e.g. 'Use when the user asks about Haskell type-level programming, STM/concurrency, or pure functional architecture'.

Add a few natural synonyms/extensions (e.g. 'GHC', 'typeclasses', 'Cabal/Stack') to broaden trigger coverage.

Prefer concrete verbs over capability nouns (e.g. 'Design type-safe domain models, tune performance, structure Cabal/Stack projects') to lift specificity.

Dimension	Reasoning	Score
Specificity	Quotes 'advanced type systems, pure functional design, and high-reliability software' and 'type-level programming, concurrency, and architecture guidance' — several concrete capability areas are named, though they read as domains rather than discrete actions like extract/fill/merge, so a 5 is not warranted.	4 / 5
Completeness	It answers 'what' ('Expert Haskell engineer specializing in...') and 'when' ('Use PROACTIVELY for type-level programming, concurrency, and architecture guidance'), but the 'when' is a directive rather than concrete user-said trigger phrases, capping it below 5.	4 / 5
Trigger Term Quality	Natural terms 'Haskell', 'type-level programming', 'concurrency', and 'architecture' are present and would be said by users, but common synonyms and variants are missing, so it sits above the 3 anchor but below comprehensive 5 coverage.	4 / 5
Distinctiveness Conflict Risk	The Haskell niche with triggers like 'type-level programming' and 'concurrency' is clearly distinct from other skills with minimal overlap risk, matching the 5 anchor's 'clear niche with distinct triggers'.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/haskell-pro/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.