CtrlK
BlogDocsLog inGet started
Tessl Logo

wiki-qa

Answer repository questions grounded entirely in source code evidence. Use when user asks a question about the codebase, user wants to understand a specific file, function, or component, or user asks "how does X work" or "where is Y defined".

58

Quality

68%

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/wiki-qa/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

61%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a reasonably well-structured but somewhat generic skill for answering codebase questions. Its main strengths are clear formatting guidelines and a concise procedure, but it lacks concrete examples of tool usage, search strategies, or sample Q&A pairs that would make it truly actionable. The duplicate 'When to Use' section and some unnecessary rules ('Think step by step') slightly reduce quality.

Suggestions

Add a concrete example showing a sample question, the search/read tool calls used, and the expected response format with citations

Remove the duplicate 'When to Use' section at the end and the 'Think step by step' rule which Claude doesn't need to be told

Add guidance on which search tools/commands to use (e.g., grep, find, ripgrep) and strategies for narrowing results when initial searches are too broad

DimensionReasoningScore

Conciseness

Mostly efficient with minimal unnecessary explanation. The duplicate 'When to Use' section at the end is wasteful, and the 'Think step by step before answering' rule is unnecessary for Claude. Otherwise lean.

4 / 5

Actionability

Provides a clear procedure and response format guidelines, but lacks concrete examples of searches, specific tool usage commands, or example input/output. The guidance is instructional but not executable in the way code examples would be.

3 / 5

Workflow Clarity

Steps are listed in sequence (detect language, search, read, synthesize) but there are no validation checkpoints. No guidance on what to do if search yields no results mid-workflow, and no feedback loop for verifying answer accuracy against sources.

3 / 5

Progressive Disclosure

For a simple skill under 50 lines with no bundle files, the content is well-organized with clear section headers (When to Use, Procedure, Response Format, Rules). The structure is appropriate for the skill's complexity, though the duplicate 'When to Use' section slightly hurts organization.

4 / 5

Total

14

/

20

Passed

Description

75%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 has strong completeness with explicit 'what' and 'when' clauses including concrete trigger phrases. However, it lacks specificity in the capabilities it offers (just 'answer questions') and has moderate overlap risk with other code-related skills. The trigger terms are good but could include more natural variations of how users ask about code.

Suggestions

Add more specific capabilities like 'traces function call chains, identifies where types/classes are defined, explains component architecture and data flow'

Improve distinctiveness by clarifying what differentiates this from code editing or debugging skills, e.g., 'read-only analysis and explanation of existing code' vs modifying code

DimensionReasoningScore

Specificity

Names the domain (repository/codebase questions) and describes one concrete action ('answer questions grounded in source code evidence'), but doesn't list specific capabilities like tracing call chains, finding definitions, explaining architecture, etc.

3 / 5

Completeness

Clearly answers both 'what' (answer repository questions grounded in source code evidence) and 'when' with explicit trigger phrases ('when user asks a question about the codebase', 'how does X work', 'where is Y defined').

5 / 5

Trigger Term Quality

Includes good natural trigger phrases like 'how does X work', 'where is Y defined', 'codebase', 'file', 'function', 'component'. Missing some common variations like 'class', 'module', 'implementation', 'code review', or 'explain this code'.

4 / 5

Distinctiveness Conflict Risk

Could overlap with other code-related skills such as code editing, code review, or documentation skills. The phrase 'answer repository questions' is somewhat broad and could conflict with skills focused on specific code tasks like refactoring or debugging.

3 / 5

Total

15

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

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.