CtrlK
BlogDocsLog inGet started
Tessl Logo

wiki-researcher

You are an expert software engineer and systems analyst. Use when user asks "how does X work" with expectation of depth, user wants to understand a complex system spanning many files, or user asks for architectural analysis or pattern investigation.

57

Quality

66%

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-researcher/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 research protocol with concrete citation/confidence standards and a clear iteration sequence. Its main weakness is redundancy: a duplicated 'When to Use' section and a vague closing line add tokens without value.

Suggestions

Remove the duplicate 'When to Use' section (lines 69-70) and its filler closing sentence; the first 'When to Use' already covers triggers.

Add a short example of a complete finding (statement + evidence + implication + confidence + open question) to make the per-finding protocol unambiguous.

Consider moving the evidence-standard table to a reference file if the skill grows, to keep SKILL.md a lean overview.

DimensionReasoningScore

Conciseness

Mostly efficient with bold imperatives and a compact evidence table, but the duplicate 'When to Use' section and the filler closing line ('This skill is applicable to execute the workflow or actions described in the overview.') are unnecessary and could be trimmed.

3 / 5

Actionability

Gives concrete, executable guidance for a research skill: a citation format ('(file_path:line_number)'), a 5-lens iteration process, an evidence-standard table, and explicit HIGH/MEDIUM/LOW confidence ratings, with only minor gaps (no example finding output).

4 / 5

Workflow Clarity

The 5-iteration process is clearly sequenced and explicitly builds on prior findings, with a per-finding 5-step protocol; confidence rating acts as a self-check. No validation checkpoints are needed for read-only research, so the destructive-ops cap does not apply.

4 / 5

Progressive Disclosure

No bundle files exist and the skill is a single well-organized file with clear sections (When to Use, Core Invariants, Process, Rules); the redundant trailing 'When to Use' section is a minor organization gap keeping it below 5.

4 / 5

Total

15

/

20

Passed

Description

66%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 has an explicit and concrete 'Use when' clause with natural trigger phrases, which is its main strength. It is held back by a persona-based 'what' that is less specific than a list of concrete actions and a broad framing that raises overlap risk with general coding skills.

Suggestions

Lead with concrete actions (e.g. 'Traces code paths, maps data flow, and produces architectural analyses of complex codebases') instead of a persona label.

Add a few more natural synonyms users say (e.g. 'explain how X works', 'trace', 'walk me through', 'codebase walkthrough') to broaden trigger coverage.

Tighten the niche so it is distinguishable from general coding assistance (e.g. emphasize depth/multi-file tracing over editing).

DimensionReasoningScore

Specificity

Names the domain ('expert software engineer and systems analyst') and a couple of concrete actions ('understand a complex system spanning many files', 'architectural analysis or pattern investigation'), but coverage is not comprehensive and the lead is a persona rather than a list of actions.

3 / 5

Completeness

Both 'what' (deeply understand codebases/systems) and 'when' (explicit 'Use when user asks...' with concrete trigger phrases) are present; the 'what' is framed as a persona rather than crisp actions, keeping it just below a 5.

4 / 5

Trigger Term Quality

Includes natural user phrases like "how does X work", "architectural analysis", and "pattern investigation" that a user would actually say, though a few synonyms (e.g. 'explain', 'trace', 'codebase walkthrough') are missing.

4 / 5

Distinctiveness Conflict Risk

The triggers ('how does X work', architectural analysis) are somewhat distinctive, but the 'expert software engineer and systems analyst' framing is broad and could overlap with general coding/explanation skills.

3 / 5

Total

14

/

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.

Validation15 / 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
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.