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.

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 known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/agentic-os/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 body is highly actionable with concrete, copy-paste templates and clearly sequenced workflows, but it is a monolithic single file that exceeds the token budget a SKILL.md overview should carry. Splitting templates and automation configs into reference files would improve both conciseness and progressive disclosure.

Suggestions

Move the larger template blocks (kernel CLAUDE.md, agent definitions, LaunchAgent/systemd/pm2 configs) into reference files under references/ and link to them one level deep, keeping SKILL.md as an overview.

Tighten the intro and section prose to reduce the ~380-line footprint and earn a higher conciseness score.

After extracting references, re-check that every inline link points to a real bundle file so progressive disclosure scores against an actual bundle structure.

Dimension	Reasoning	Score
Conciseness	The ~380-line body is mostly concrete with little beginner-concept padding, but it is long for a SKILL.md and includes prose that could be tightened. It is above score 1 because it avoids explaining concepts Claude already knows, but below score 3 because the overall length does not earn every token its place.	2 / 3
Actionability	It provides copy-paste-ready templates: a full CLAUDE.md kernel, agent definition files, slash-command files, macOS LaunchAgent XML, systemd service/timer units, a pm2 ecosystem config, and JSON state schemas. These are concrete and executable rather than pseudocode, matching the score-3 anchor.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced — the five-step routing rules, the numbered daily-sync workflow, and the multi-agent collaboration pattern — and a Best Practices checklist plus an auto-reflection feedback loop provide checkpoints. It is above score 2 because sequencing and a feedback loop are explicit rather than implicit.	3 / 3
Progressive Disclosure	No bundle files exist in references/, scripts/, or assets/, and the entire architecture guide, all templates, and all automation configs live inline in one ~380-line SKILL.md. It is well-organized so it is not score 1, but content that should be split into one-level-deep reference files is inline, matching the score-2 anchor.	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 about what the skill builds, but it lacks an explicit 'Use when...' trigger clause and the natural user-facing trigger terms that would help it fire at the right moment. Adding a trigger phrase would lift completeness and trigger-term quality.

Suggestions

Append a 'Use when...' clause with natural trigger terms a user would say, e.g. 'Use when building an agentic OS, personal OS, multi-agent workflow, or persistent agent coordination on Claude Code.'

Surface the natural phrases from the body ('agentic OS', 'personal OS', 'agent coordinator', 'persistent agent') into the description so trigger-term quality reaches full coverage.

Keep the existing concrete capability list — it is the strongest part of the description and should be preserved.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete capabilities — 'kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management' — anchored by the concrete action 'Build persistent multi-agent operating systems on Claude Code'. This matches the score-3 anchor of listing multiple specific concrete actions; it is not the vague single-action phrasing of score 2.	3 / 3
Completeness	It clearly answers 'what' the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, so per the guidelines completeness is capped at 2. It is not score 1 because the 'what' is explicit and substantive.	2 / 3
Trigger Term Quality	It contains some relevant terms ('multi-agent', 'Claude Code') but omits the natural phrases a user would actually say ('agentic OS', 'personal OS', 'agent coordinator'), which appear only in the body, not the description. It is above score 1 because relevant keywords are present, but below score 3 because common natural variations are missing.	2 / 3
Distinctiveness Conflict Risk	'Persistent multi-agent operating systems on Claude Code ... without external databases' defines a clear niche unlikely to trigger for the wrong skill. It is above score 2 because the combination of kernel/agents/commands/memory is distinctive rather than a generic overlap.	3 / 3
	Total	10 / 12 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
Commit: 754b8dd

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.