CtrlK
BlogDocsLog inGet started
Tessl Logo

reference-builder

Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference materials.

44

Quality

45%

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/reference-builder/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

31%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 long, generic template describing what good reference docs look like rather than giving actionable, executable guidance for producing them, with no real tools or concrete examples and a broken external reference. It reads as filler rather than skill-specific instruction.

Suggestions

Replace abstract category lists with concrete, executable guidance: specific commands, tools, or copy-paste-ready templates for generating references from real source code.

Move the large entry-format template and per-type reference material into separate reference files and fix the broken 'resources/implementation-playbook.md' link (create the file or correct the path).

Add explicit validation checkpoints to the Reference Building Process (e.g., a concrete verify command and a fix-and-retry loop) and trim the generic best-practice bullets that restate what Claude already knows.

DimensionReasoningScore

Conciseness

The ~180-line body is padded with generic documentation best-practice lists ('Document every parameter, method, and configuration option', 'Complete method signatures with all parameters') that restate concepts Claude already knows, matching 'noticeably verbose; several unnecessary explanations or padded sections'; it is not severe enough for level 1 because it stays on-topic.

2 / 5

Actionability

Guidance is almost entirely abstract — the 'Entry Format' is a fill-in placeholder template and the 'Reference Building Process' lists high-level phases (Inventory, Extraction, Enhancement...) with no commands, tools, or executable steps; this matches 'minimal concrete guidance; high-level hints but missing the specific steps to execute'.

2 / 5

Workflow Clarity

A 6-step 'Reference Building Process' sequence is present including a named 'Validation' step, but the checkpoints are vague ('Verify accuracy and completeness') with no concrete verification commands or error-recovery feedback loops, matching 'steps listed but validation gaps; checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

All bulk reference-template material is inlined in one ~180-line SKILL.md rather than split into separate files, and the sole external pointer 'resources/implementation-playbook.md' is a dangling reference to a non-existent directory, matching 'content that clearly belongs in separate files is inlined; or references are buried'.

2 / 5

Total

9

/

20

Passed

Description

58%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 states what the skill does and lists several concrete actions, but it omits any explicit 'when to use' trigger guidance, which caps completeness and limits trigger-term quality. It is otherwise specific and reasonably distinct.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., 'Use when the user asks for API reference docs, parameter/configuration guides, or searchable technical references').

Include natural synonyms users actually say — 'docs', 'reference docs', 'API reference' — and relevant file extensions to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'Generates comprehensive parameter listings, configuration guides, and searchable reference materials' alongside 'API documentation' — matching the 'lists several specific actions; minor gaps' anchor, falling short of level 5 only because 'exhaustive'/'comprehensive' are mild padding rather than additional distinct actions.

4 / 5

Completeness

The 'what' is clearly stated (creates references/API docs and generates listings/guides), but there is no 'Use when...' clause or equivalent trigger guidance; per the rubric this caps completeness at 3.

3 / 5

Trigger Term Quality

Terms like 'API documentation', 'parameter listings', and 'configuration guides' are relevant but lean technical; common natural synonyms users would actually say ('docs', 'reference docs', 'API reference', file extensions) are missing, matching the 'some relevant keywords but missing common variations or synonyms' anchor.

3 / 5

Distinctiveness Conflict Risk

'Technical references and API documentation' with 'parameter listings' and 'configuration guides' carves a fairly distinct reference-doc niche with only minor overlap against general documentation skills, matching the 'mostly distinct; minor overlap risk' anchor.

4 / 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.