skill-architect

Architect and audit portable agent skills for retrieval, predictability, progressive disclosure, evals, and repository gates. Use when the user asks to "create a skill", "author a skill", "improve a skill", "review a skill", "refactor a skill", "compare skill rubrics", "distill a skill from sessions", "reconcile skill plans", or "teach skill authoring"; when paths include `skills/<name>/SKILL.md`, `references/*.md`, helper scripts, evals, lockfiles, security manifests, or vendor adapters; or when mentions include skill-creator, Skill Development, skills.sh, trigger descriptions, completion criteria, leading words, or model/user invocation.

Quality

89%

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

Quality

Content

85%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-architected, action-oriented meta-skill with clear sequenced workflows, explicit validation feedback loops, and exemplary one-level-deep progressive disclosure backed by real bundle files. The main improvement opportunity is trimming duplication between the command-modes table and the Mode rules list.

Suggestions

Collapse the 'Mode rules' bullet list into the command-modes table (or vice versa) to remove the duplicated enumeration of the nine modes and tighten conciseness.

Trim the overlap between 'Why this skill exists' and 'Operating mode', both of which restate the vendor-neutral synthesis point.

For routing-level guidance ('route to a dedicated code-review skill'), add a one-line concrete trigger or handoff condition so the instruction is executable rather than abstract.

Dimension	Reasoning	Score
Conciseness	Efficient, operational prose that does not re-explain basics Claude already knows, but has minor over-explanation: the nine modes appear both in the command-modes table and again as 'Mode rules', and 'Operating mode' overlaps the 'Why this skill exists' table.	4 / 5
Actionability	Provides concrete executable guidance — a modes table with outputs, linked helper scripts, and real validation commands ('npm run check:skill-standard', 'node bin/hash-check.mjs') — with minor gaps where guidance stays at routing level rather than executable steps.	4 / 5
Workflow Clarity	Multi-step workflows are clearly sequenced (7-step operating order, 6-step architecture workflow) with explicit validation checkpoints ('Verify mechanically', 'Run repo checks') and a validate->fix->retry feedback loop via fix_skill.py.	5 / 5
Progressive Disclosure	SKILL.md stays a routing overview; detailed material is one level deep in references/ (5 real linked files) and assets/scripts/ (4 real linked scripts), each with a 'Load when' navigation table — easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

95%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 is strong: third-person imperative voice, explicit 'Use when' clause, comprehensive trigger coverage with synonyms and path/mention patterns, and a clear distinct niche. Minor specificity gap only in that the broad mode set is summarized rather than enumerated.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Architect and audit portable agent skills for retrieval, predictability, progressive disclosure, evals, and repository gates') with only minor coverage gaps around what each mode concretely produces.	4 / 5
Completeness	Explicitly answers both 'what' (architect/audit portable agent skills) and 'when' ('Use when the user asks to...') with concrete trigger phrases and path/mention conditions.	5 / 5
Trigger Term Quality	Comprehensive natural-language triggers including synonyms ('create a skill', 'author a skill', 'improve a skill', 'review a skill', 'refactor a skill'), path patterns, and mention terms users would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (skill authoring/review/governance) with distinct triggers and path/mention signals; minimal conflict risk with unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 3 missing, 9 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: t4sh/skills4sh
Path: skills/skill-architect/SKILL.md
Commit: 3858600

Reviewed: 4 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.