agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

Quality

80%

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/agentic-os/SKILL.md

Quality

Content

71%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 highly actionable architectural skill with excellent concrete templates across every layer, weakened by monolithic inlining of material that belongs in separate reference files and some redundant presentation of the directory structure.

Suggestions

Split the full templates (CLAUDE.md kernel, agent file, LaunchAgent/systemd/pm2 configs) into files under references/ and link to them one level deep, leaving concise examples inline in SKILL.md.

Collapse the duplicate architecture presentation: keep either the ASCII tree or the responsibilities table, not both, to tighten conciseness.

Add an explicit validation checkpoint to the routing/multi-agent handoff workflow (e.g., verify the target agent file exists and tools are configured before delegating, with a retry-on-miss feedback loop).

Dimension	Reasoning	Score
Conciseness	The ~380-line body is mostly efficient and assumes Claude's competence, but the architecture overview duplicates the directory tree as both an ASCII diagram and a table, and the opening prose ('Treat Claude Code as a persistent runtime...') restates what the structure already shows.	3 / 5
Actionability	Copy-paste-ready templates cover the common cases: a full CLAUDE.md kernel, an agent definition file, a slash command, LaunchAgent plist, systemd unit/timer, pm2 config, and JSON state schemas are all concrete and executable.	5 / 5
Workflow Clarity	Routing rules and the daily-sync command are clearly numbered and sequenced, and the closing best-practices checklist acts as a verification gate; however, the multi-agent handoff and routing workflows lack explicit validation checkpoints for failed handoffs.	4 / 5
Progressive Disclosure	Sections are well-organized, but no bundle files exist and large copy-paste templates (full kernel, agent, command, plist, systemd, pm2) that would benefit from being one level deep in references are fully inlined, with no signaled references to navigate to.	3 / 5
	Total	15 / 20 Passed

Description

88%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.

A strong, third-person description that clearly states both capabilities and activation triggers with concrete component coverage. Main gap is that the most distinctive user-facing trigger phrases ('agentic OS', 'personal OS') live only in the body, not the description.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete components — 'kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases' — giving comprehensive coverage of what the skill builds.	5 / 5
Completeness	It explicitly answers both what ('Build persistent multi-agent operating systems... Covers...') and when ('Use when building a persistent multi-agent system...'), with concrete trigger phrasing.	5 / 5
Trigger Term Quality	'Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling' offers good natural coverage, but common user phrases like 'agentic OS' or 'personal OS' (which appear in the body) are absent from the description itself.	4 / 5
Distinctiveness Conflict Risk	The 'persistent multi-agent operating system on Claude Code' niche is fairly distinct, but 'multi-agent' framing has minor overlap risk with general agent-coordination skills.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/agentic-os/SKILL.md
Commit: 06c5e11

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.