architect

Research-backed evolution advice for your knowledge system. Analyzes health reports, friction patterns, and derivation history to propose specific changes with research justification. Never auto-implements — proposals require your approval.

Quality

72%

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/architect/SKILL.md

Quality

Content

77%

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

The skill is highly actionable with a clear, well-checkpointed seven-phase workflow, but it is verbose and ships as a single monolithic file with no progressive-disclosure bundle. Trimming philosophical prose and splitting large reference material into separate files would raise conciseness and progressive disclosure.

Suggestions

Move the Phase 5 research-reference table and the Phase 6 recommendation template into separate reference files under references/, keeping SKILL.md as a concise overview that links to them.

Cut the Philosophy section's exposition to one or two lines; remove redundant restatements like 'The goal is to connect EVERY recommendation to specific research' that repeat what the phase instructions already specify.

Tighten the Edge Cases and Quality Standards sections into a compact checklist to reduce token overhead while preserving the actionable rules.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands and tables, but it is padded with philosophical exposition ('Evidence beats intuition. Research beats habit.', the 25% budget rationale) and repeated emphasis that could be trimmed to respect the token budget.	2 / 3
Actionability	Provides fully executable bash commands, exact file paths, copy-paste-ready recommendation and changelog templates, and explicit quality gates — matching the 'copy-paste ready' anchor.	3 / 3
Workflow Clarity	The seven phases are clearly sequenced with explicit validation checkpoints (post-change validation in Phase 7, quality gates in Phase 6) and feedback loops (On Rejection, re-validate on failure), matching the clear-sequence-with-checkpoints anchor.	3 / 3
Progressive Disclosure	The body is monolithic (~570 lines) with all phases inline and no bundle files present (no references/, scripts/, or assets/); the one-level-deep plugin reference table is well-signaled, but content that could be split (templates, research map) remains inline.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 is specific and distinctive, but it omits an explicit 'Use when...' trigger clause and relies partly on domain jargon, capping completeness and trigger quality. Adding natural trigger phrases would raise both dimensions.

Suggestions

Append an explicit 'Use when...' clause stating when to invoke the skill (e.g., 'Use when you want to evolve or audit your knowledge system's structure, or when you mention health reports, friction, or derivation drift').

Replace or gloss the jargon term 'derivation history' with phrasing a user would naturally say, such as 'design-intent history' or 'original system design'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Analyzes health reports, friction patterns, and derivation history to propose specific changes with research justification' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly answers 'what' but lacks an explicit 'Use when...' trigger clause — the 'when' is only implied by 'Never auto-implements', which per guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Has some relevant natural terms ('evolution advice', 'health reports', 'friction patterns') but leans on specialized jargon ('derivation history') and misses common user phrasings, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (research-backed system-evolution advisor that never auto-implements and requires approval) with distinct triggers unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (569 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

	Total	13 / 16 Passed

Repository: agenticnotetaking/arscontexta
Path: skills/architect/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.