Name: haskell-pro
Rating: 45.6 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

haskell-pro

Expert Haskell engineer specializing in advanced type systems, pure

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/haskell-pro/SKILL.md

The canonical home for this skill is haskell-pro in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

42%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 body is well-structured and names the right Haskell topics and libraries, but it provides no runnable code and leans on generic boilerplate. The single reference to detailed examples points to a file that does not exist, weakening progressive disclosure.

Suggestions

Add runnable, copy-paste Haskell examples (GADT/newtype modeling, STM concurrency, Megaparsec/Aeson parsing, QuickCheck properties) to fulfill the Output promises and raise actionability.

Fix the broken reference: 'resources/implementation-playbook.md' does not exist — either create the file under the correct bundle directory or remove the pointer.

Replace the generic 'Instructions' bullets with Haskell-specific guidance and tighten the circular 'Use this skill when / Do not use' sections.

Dimension	Reasoning	Score
Conciseness	The body is mostly terse bullet lists, but the generic 'Instructions' ('Clarify goals...', 'Apply relevant best practices and validate outcomes') and circular 'Use this skill when / Working on haskell pro tasks' sections are filler that could be tightened, matching the score-3 anchor 'Mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	The Approach steps are abstract design principles ('Use expressive types...', 'Prefer pure functions') with no executable Haskell code, despite the Output section promising GADT/Megaparsec/QuickCheck examples, fitting the score-2 anchor 'Minimal concrete guidance; high-level hints but missing the specific steps to execute'.	2 / 5
Workflow Clarity	The numbered Approach list provides a rough sequence of design principles but no validation checkpoints or feedback loops, matching the score-3 anchor 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	Sections (Focus Areas, Approach, Output) give reasonable structure and one reference to detailed examples, but the referenced 'resources/implementation-playbook.md' does not exist (no bundle files are present and the path is 'resources/' not 'references/'), so the reference is broken, matching the score-3 anchor 'references present but not clearly signaled'.	3 / 5
	Total	11 / 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 establishes a clear Haskell niche but is truncated mid-sentence ('pure') and omits any explicit 'Use when' trigger guidance, capping completeness. Specificity and trigger-term quality are moderate because capabilities are framed as a persona rather than concrete actions.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger situations (e.g. designing GADTs/type families, STM concurrency, Cabal/Stack builds).

Complete the truncated description so it does not end mid-word at 'pure'.

Reframe the persona ('Expert Haskell engineer') as concrete actions ('Designs advanced type systems, writes total functions, tunes performance') to lift specificity.

Dimension	Reasoning	Score
Specificity	Quotes 'Expert Haskell engineer specializing in advanced type systems, pure' name the domain and two concrete specialization areas, but phrase them as a persona rather than concrete actions, matching the score-3 anchor 'Names domain and 1-2 concrete actions'.	3 / 5
Completeness	The description gives a clear 'what' ('Expert Haskell engineer specializing in...') but contains no 'Use when...' or equivalent trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	'Haskell' is the natural keyword a user would say, and 'advanced type systems' is moderately natural, but common variations or synonyms are absent, fitting the score-3 anchor 'Some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	Haskell with advanced type systems is a clear niche with low overlap risk against non-Haskell skills, matching the score-4 anchor 'Mostly distinct; minor overlap risk with closely related skills'; not a 5 because the truncated description lacks distinct explicit triggers.	4 / 5
	Total	13 / 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
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
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/haskell-pro/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.