CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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".

Quality

74%

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-claude/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

60%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 content is well-structured with a clear procedure and concrete output format, and it appropriately avoids external files for a skill this size. It is held back by a redundant filler section, a vague search step without concrete guidance, and the absence of any citation-verification checkpoint.

Suggestions

Delete the second "## When to Use" section ("This skill is applicable to execute the workflow or actions described in the overview.") and remove "Think step by step before answering" — both are padding that adds no instruction.

Make the search step concrete: specify tooling and patterns, e.g. "Use grep/ripgrep for definitions (`rg 'def <name>'`) and usages, then read the matched files".

Add a verification checkpoint before answering, e.g. "Confirm every cited file path and line number exists in the read files; drop citations you cannot verify".

DimensionReasoningScore

Conciseness

The body is short but contains avoidable padding: a duplicated "## When to Use" section whose second occurrence is filler ("This skill is applicable to execute the workflow or actions described in the overview"), and "Think step by step before answering" restates default behavior.

3 / 5

Actionability

Concrete elements exist (citation format "(src/path/file.ts:42)", the Key Files table requirement), but the core step "Search the codebase for relevant files" lacks any concrete command or search pattern, leaving key details missing.

3 / 5

Workflow Clarity

The four-step procedure (detect language, search, read, synthesize) is clearly sequenced with a fallback for insufficient information, but no explicit checkpoint such as verifying each citation points to real file content.

4 / 5

Progressive Disclosure

For an under-50-line skill needing no external files, sections are well-organized (When to Use, Procedure, Response Format, Rules); the duplicated "When to Use" section is the only notable organization flaw.

4 / 5

Total

14

/

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 strong description that answers both what and when with explicit, naturally phrased triggers in third person. Its main limitation is specificity: it names a single capability rather than enumerating the concrete actions involved, which also leaves slight overlap with adjacent code-exploration skills.

DimensionReasoningScore

Specificity

"Answer repository questions grounded entirely in source code evidence" names the domain and one main concrete action, but does not enumerate multiple specific actions (search, read, cite), matching the 1-2-concrete-actions anchor.

3 / 5

Completeness

It clearly states what it does ("Answer repository questions grounded entirely in source code evidence") and explicitly when to use it with concrete quoted trigger phrases ("how does X work", "where is Y defined"), matching the top anchor.

5 / 5

Trigger Term Quality

Natural user phrases like "question about the codebase", "how does X work", and "where is Y defined" give good keyword coverage, though common synonyms such as "explain" or "trace" are missing.

4 / 5

Distinctiveness Conflict Risk

The evidence-grounded codebase Q&A niche is mostly distinct with specific triggers, but there is minor overlap risk with general code-exploration or code-review skills.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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/wiki-qa/SKILL.md

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.