CtrlK
BlogDocsLog inGet started
Tessl Logo

wiki-researcher

Conducts multi-turn iterative deep research on specific topics within a codebase with zero tolerance for shallow analysis. Use when the user wants an in-depth investigation, needs to understand how something works across multiple files, or asks for comprehensive analysis of a specific system or pattern.

64

Quality

80%

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/deep-wiki/skills/wiki-researcher/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 methodology with concrete commands, explicit citation/evidence standards, and a clearly sequenced 5-iteration workflow. Its main weaknesses are minor redundancy between the depth-invariant sections and the absence of any progressive-disclosure split despite exceeding the simple-skill line count.

Suggestions

Consolidate 'Depth Before Breadth' and 'Zero Tolerance for Shallow Research' into a single invariants block to remove the restated 'go deep, don't guess' redundancy.

Add one fully-resolved example citation (both linked and local forms) so the citation format is copy-paste ready rather than only templated.

Since the body exceeds 50 lines, consider moving the evidence-standard table and per-iteration detail into a references file linked from a concise overview to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is lean, using directives, tables, and lists without explaining concepts Claude already knows; minor redundancy between 'Depth Before Breadth' and 'Zero Tolerance for Shallow Research' (both restate 'go deep, don't guess') keeps it just below a 5.

4 / 5

Actionability

Gives concrete commands ('git remote get-url origin', 'git rev-parse --abbrev-ref HEAD'), explicit citation formats, a defined 5-iteration process, and a HIGH/MEDIUM/LOW confidence scheme; minor gaps (no full example linked citation, Mermaid dark-mode colors unspecified) hold it at 4.

4 / 5

Workflow Clarity

Clear sequence with a 'MUST DO FIRST' gate ('Do NOT proceed until source repo context is resolved') and five building iterations with checkpoints; this is a research skill so the destructive/batch cap does not apply, but minor validation/loop-back gaps remain.

4 / 5

Progressive Disclosure

No bundle files exist; the body is a single self-contained doc with well-organized section headers and no buried or nested references, but at ~75 lines with no one-level-deep detail-file pointers it sits just below the well-organized-and-short 5 anchor.

4 / 5

Total

16

/

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.

The description clearly answers both what the skill does and when to use it, with natural trigger phrases and a distinct deep-research niche. Its main weakness is that the named actions are abstract variations of 'research' rather than concrete, differentiated operations.

DimensionReasoningScore

Specificity

Names the domain and several actions ('multi-turn iterative deep research', 'in-depth investigation', 'understand how something works across multiple files', 'comprehensive analysis'), but these are variations of 'research' rather than distinct concrete operations, so coverage is not comprehensive.

3 / 5

Completeness

Explicitly states what it does ('Conducts multi-turn iterative deep research…') and gives an explicit 'Use when…' clause with concrete trigger phrases, clearly answering both what and when.

5 / 5

Trigger Term Quality

Includes natural user phrases ('in-depth investigation', 'understand how something works across multiple files', 'comprehensive analysis of a specific system or pattern'); a few synonyms (e.g. 'trace', 'architectural analysis') are missing, keeping it just short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche (multi-turn, zero-tolerance-for-shallow codebase research) with specific triggers, but 'understand how something works across multiple files' has minor overlap risk with general codebase-explainer 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

relative_links

Relative link issues: 2 missing, 2 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
freightCognition/linehaulai-claude-marketplace
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.