CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

69%

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-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

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.

A well-structured instruction-only skill: the 5-iteration process, evidence standard table, and per-finding protocol give concrete, actionable guidance with clear sequencing and built-in confidence checkpoints. Its main flaws are a verbatim duplicated 'When to Use' section, a placeholder closing sentence, and the absence of an explicit verification step or output format for the final synthesis.

Suggestions

Delete the second 'When to Use' section and the filler line 'This skill is applicable to execute the workflow or actions described in the overview.'

Add an explicit verification checkpoint before iteration 5 (e.g., re-read the cited code to confirm each HIGH-confidence claim before synthesizing).

Specify the expected output of the final synthesis iteration (e.g., a summary diagram plus a findings table with confidence ratings).

DimensionReasoningScore

Conciseness

The body is directive with no explanation of concepts Claude already knows ('TRACE ACTUAL CODE PATHS', the evidence-requirements table), but it is not fully lean: the 'When to Use' section appears twice verbatim and the closing line 'This skill is applicable to execute the workflow or actions described in the overview.' is pure filler. Fits anchor 4 (efficient, minor instances that could be trimmed) rather than 5 because of the duplication and placeholder text, and rather than 3 because the padding is a small fraction of the whole.

4 / 5

Actionability

Concrete, specific guidance throughout: a 5-lens iteration plan, a per-finding protocol ('State the finding', 'Show the evidence — file paths, code references, call chains'), defined confidence levels (HIGH 'read code', MEDIUM 'read some, inferred rest', LOW 'inferred from structure'), a claim-to-evidence table, and an explicit citation format '(file_path:line_number)'. Falls short of 5 because the final output format and expected depth per iteration are never specified; exceeds 3 because the guidance is specific and executable rather than pseudocode-level.

4 / 5

Workflow Clarity

Clear sequence: 5 numbered iterations that 'build on all prior findings', each with a defined lens, plus a per-finding checklist; confidence ratings and 'Flag what you HAVEN'T explored' act as checkpoints. Not 5 because there is no explicit verification/feedback step (e.g., re-reading cited code to confirm a claim before synthesis). The cap-3 rule for destructive/batch operations does not apply — this is a read-only research skill.

4 / 5

Progressive Disclosure

Single-file skill (~63 body lines) with no bundle directories (references/, scripts/, assets/ do not exist) and no file references in the body; sections are well organized with headers, a table, and numbered lists. Scored 4 rather than 5 because of the duplicated 'When to Use' section and the vacuous placeholder closing section, which are minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

51%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 strong, explicit trigger guidance with natural phrases ('how does X work', 'architectural analysis'), but it never states what the skill actually does — it opens with a second-person persona claim ('You are an expert software engineer and systems analyst') instead of third-person action verbs. The when-clause is well written; the what-clause is missing, which drags down specificity and completeness.

Suggestions

Rewrite in third person and lead with concrete actions, e.g.: 'Traces actual code paths across a codebase and explains how complex systems work, grounding every claim in cited evidence. Use when the user asks "how does X work" with expectation of depth, wants to understand a complex system spanning many files, or asks for architectural analysis or pattern investigation.'

Replace the persona opener ('You are an expert software engineer and systems analyst') with what the skill does: trace call chains, map data flow, rate confidence of findings.

Add common trigger synonyms such as 'explain the codebase', 'walk me through', or 'trace the flow' to broaden natural-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ('expert software engineer and systems analyst') but states no concrete actions the skill performs — base 2 per the anchor 'names the domain but actions are minimal or generic'; reduced by 1 because it opens in second person ('You are an expert software engineer and systems analyst') instead of third person. Not 2 because the second-person penalty applies; not higher because nowhere does it list what the skill actually does (e.g., tracing code paths, mapping architecture).

1 / 5

Completeness

The 'when' is explicit and concrete ('Use when user asks "how does X work" with expectation of depth... or user asks for architectural analysis or pattern investigation'), but the 'what' is only a persona statement ('You are an expert software engineer and systems analyst') with no explicit actions. This sits between anchor 2 ('only when is present without what') and anchor 4 (both what and when, when more specific) — the persona conveys a domain but not what the skill does, so it lands at the midpoint rather than noticeably above it.

3 / 5

Trigger Term Quality

Includes natural phrases users would actually say: 'how does X work', 'architectural analysis', 'pattern investigation', and 'understand a complex system spanning many files'. Falls at anchor 4 (good coverage, a few natural terms missing) rather than 5 because common synonyms like 'explain the codebase', 'walk me through', or 'trace the flow' are absent, and rather than 3 because the included triggers are natural and varied.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche — deep, multi-file system understanding — with fairly distinct triggers ('how does X work' with expectation of depth, 'complex system spanning many files', 'architectural analysis'). Anchor 4 (mostly distinct, minor overlap risk) fits: it could still overlap with general code-exploration or code-review skills triggered by 'pattern investigation', so not 5.

4 / 5

Total

12

/

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/skills/wiki-researcher/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.