typescript-security
Validate input, secure auth tokens, and prevent injection attacks in TypeScript. Use when validating input, handling auth tokens, sanitizing data, or managing secrets and sensitive configuration.
62
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/typescript/typescript-security/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly communicates specific security-related capabilities in TypeScript, includes natural trigger terms users would use, and provides explicit 'Use when' guidance. It covers both the 'what' and 'when' effectively while maintaining a distinct niche that minimizes conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Validate input', 'secure auth tokens', and 'prevent injection attacks', all within a named technology (TypeScript). | 3 / 3 |
Completeness | Clearly answers both 'what' (validate input, secure auth tokens, prevent injection attacks in TypeScript) and 'when' with an explicit 'Use when...' clause listing multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'validating input', 'auth tokens', 'sanitizing data', 'injection attacks', 'secrets', 'sensitive configuration'. These cover common variations of security-related queries. | 3 / 3 |
Distinctiveness Conflict Risk | Targets a clear niche of security-focused TypeScript tasks (input validation, auth tokens, injection prevention, secrets management). This is distinct enough from general TypeScript coding skills or other domain-specific skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a competent security checklist that covers important topics (input validation, injection prevention, auth, anti-patterns) with specific library recommendations and some inline code snippets. Its main weaknesses are the lack of complete executable examples (most guidance is directive rather than copy-paste ready) and the absence of a clear sequenced workflow for implementing security measures. The duplicate reference link and excessive bold formatting add minor noise.
Suggestions
Add at least one complete, executable code example for a core pattern (e.g., a full Zod schema validation at an Express endpoint with error handling), rather than relying solely on inline snippets.
Remove the duplicate REFERENCE.md link — keep it only at the bottom in the References section to reduce noise.
Consider adding a brief sequenced workflow for the most common use case (e.g., 1. Define Zod schema → 2. Add safeParse at route handler → 3. Run getDiagnostics → 4. Verify 400 response on invalid input) to improve workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but has some redundancy — the reference to REFERENCE.md appears twice (once near the top and once at the bottom), and some bolding is excessive. The anti-patterns section is valuable but slightly verbose with parenthetical explanations Claude would already know (e.g., explaining what eval does). | 2 / 3 |
Actionability | Provides specific library names, function calls, and inline code snippets (e.g., pool.query with parameterized syntax, execFileSync with args array), but lacks complete executable code examples. Most guidance is at the 'use X for Y' level rather than copy-paste ready blocks. | 2 / 3 |
Workflow Clarity | The verification step mentions calling getDiagnostics after writing validation schemas, which is a good checkpoint. However, there's no clear sequenced workflow — the content reads as a checklist of security concerns rather than a step-by-step process. For a security skill that involves input validation at boundaries (a multi-step concern), the lack of an explicit validate-then-proceed flow is a gap. | 2 / 3 |
Progressive Disclosure | References to REFERENCE.md are clearly signaled and appear to be one level deep, which is good. However, the reference is duplicated (top and bottom), and since no bundle files were provided, we cannot verify the referenced file exists or contains the promised content. The main content itself could benefit from better separation — the anti-patterns section is substantial and could potentially be its own reference file. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- HoangNguyen0403/agent-skills-standard
- Commit
3df717f
- 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.