Name: sharp-edges
Rating: 60.8 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

sharp-edges

Quality

72%

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/sharp-edges/SKILL.md

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

Quality

Content

70%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 a well-structured, actionable analysis methodology with a strong sequenced workflow and validation loop. Its weaknesses are noticeable padding (the rationalizations table and repeated detection-pattern lists) and a progressive-disclosure promise that is broken because none of the referenced files actually exist in the bundle.

Suggestions

Ship the referenced files under references/ (crypto-apis.md, config-patterns.md, auth-patterns.md, case-studies.md, lang-*.md, language-specific.md) or remove the dead references from the body.

Trim or relocate the 'Rationalizations to Reject' table and consolidate the repeated per-category 'Detection patterns' lists to reduce tokens spent on persuasion Claude does not need.

Move the long language-specific footgun tables entirely into the referenced language files so the SKILL.md overview stays lean.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain guidance, but it carries padding that Claude does not need: the argumentative 'Rationalizations to Reject' table, repeated 'Detection patterns' lists, and rhetorical 'Questions to ask' sections could be tightened.	3 / 5
Actionability	Concrete detection patterns (parameters like 'algorithm', 'mode', 'cipher'), real code examples in PHP/Python/Go/YAML contrasting safe vs unsafe usage, and specific probing questions give mostly executable guidance with minor gaps.	4 / 5
Workflow Clarity	A clear four-phase workflow (Surface Identification, Edge Case Probing, Threat Modeling, Validate Findings) with explicit validation in Phase 4 (reproduce misuse, verify exploitability), a feedback loop ('return to Phase 2'), and a final Quality Checklist.	5 / 5
Progressive Disclosure	The References section is well organized (by category and by language, one level deep), but the bundle contains no references/ directory, so all ~15 referenced files (crypto-apis.md, config-patterns.md, lang-*.md, etc.) are dead links and navigation is broken.	3 / 5
	Total	15 / 20 Passed

Description

75%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 clearly states what the skill does and when to use it with concrete, third-person trigger phrasing. Its main defect is that the YAML value is malformed and truncated mid-sentence at "'secure by...", leaving the final trigger clause incomplete.

Suggestions

Close the description string and finish the truncated clause (e.g. "...or evaluating whether code follows 'secure by default' principles.") so the value is valid YAML and the 'when' guidance is complete.

Add a few natural synonyms users might say ('footguns', 'insecure defaults', 'pit of success', 'misuse-resistant APIs') to broaden trigger coverage.

Distinguish the skill from generic security/code review by naming the design-review angle explicitly (e.g. 'design-time review of API and configuration ergonomics').

Dimension	Reasoning	Score
Specificity	Names the security-design domain and lists several concrete targets ('error-prone APIs, dangerous configurations, and footgun designs'), though they are variations on one identifying action rather than a comprehensive set of distinct capabilities.	4 / 5
Completeness	Explicitly answers both 'what' (identifies error-prone APIs/configs/footgun designs) and 'when' (a 'Use when...' clause with concrete triggers), but the 'when' is cut off mid-phrase at "'secure by...", so it is not fully complete.	4 / 5
Trigger Term Quality	Includes natural phrases a user would say ('reviewing API designs, configuration schemas, cryptographic library ergonomics') with good coverage, though synonyms like 'footguns', 'insecure defaults', or 'misuse' are thin.	4 / 5
Distinctiveness Conflict Risk	The sharp-edges / secure-by-default design niche is fairly distinct with specific triggers, with only minor overlap risk against a general security-review or code-review skill.	4 / 5
	Total	16 / 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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
description_field	'description' is very short (11 chars), consider making it more detailed	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 16 missing	Warning

	Total	13 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/sharp-edges/SKILL.md
Commit: 57c135b

Reviewed: 20 hours 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.