setup

Scaffold a complete knowledge system. Detects platform, conducts conversation, derives configuration, generates everything. Validates against 15 kernel primitives. Triggers on "/setup", "/setup --advanced", "set up my knowledge system", "create my vault".

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/setup/SKILL.md

Quality

Content

58%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and clearly sequenced with strong validation checkpoints, but it is far too verbose — much of the prescribed onboarding text, manual pages, and template scaffolding should be moved into referenced files to respect the context budget. Progressive disclosure is partially realized but undermined by inline bulk.

Suggestions

Move the seven prescribed manual pages (Step 5g) and the full ops/derivation.md / derivation-manifest.md templates into referenced generator files, keeping only the structural contract and field list in SKILL.md.

Extract the large onboarding screen text blocks (Phase 1.5) into a reference file referenced by path, since they are prescribed verbatim content rather than reasoning Claude needs in context.

Collapse the signal-pattern and anti-signal tables (Phase 2) into a reference doc and keep only the extraction rules and confidence threshold in the body.

Dimension	Reasoning	Score
Conciseness	At ~1700 lines the body is extremely verbose; large prescribed text blocks (onboarding screens, full template frontmatter, 7 manual pages, extensive signal tables) restate material that could live in referenced files and pad the SKILL.md far beyond a lean overview.	1 / 3
Actionability	Provides concrete, executable guidance throughout: exact bash commands (git init, qmd commands), full YAML/JSON templates, literal hook JSON, and copy-paste-ready markdown scaffolds with explicit field requirements.	3 / 3
Workflow Clarity	Phases 1–6 are explicitly sequenced with a 15-step generation order, and validation is built in (kernel validation checks, pipeline smoke test, coherence three-pass check with explicit feedback loops) before proceeding.	3 / 3
Progressive Disclosure	It references external files (kernel.yaml, interaction-constraints.md, generators/, skill-sources/) at one level deep, but inlines enormous amounts of content (manual pages, templates, manifest YAML) that should themselves be separate files, leaving structure uneven.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, third-person description that names concrete actions and provides explicit trigger terms covering both slash-command and natural-language invocations. It cleanly answers what the skill does and when to use it with minimal fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Detects platform, conducts conversation, derives configuration, generates everything. Validates against 15 kernel primitives' — each maps to a specific task rather than vague language.	3 / 3
Completeness	Clearly answers both 'what' (scaffold/detect/converse/derive/generate/validate) and 'when' via an explicit 'Triggers on' clause with concrete examples.	3 / 3
Trigger Term Quality	Good natural coverage with literal trigger terms a user would type: '/setup', '/setup --advanced', 'set up my knowledge system', 'create my vault', covering both command and prose invocations.	3 / 3
Distinctiveness Conflict Risk	A clear niche — building a knowledge-system/vault with a derivation engine — with specific command triggers unlikely to overlap with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

75%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1714 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: agenticnotetaking/arscontexta
Path: skills/setup/SKILL.md
Commit: 2acfd5c

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.