agency-os

Notion-as-source-of-truth dispatch board for running your work like an AI agency. One Tasks database is the source of truth; tasks flow Suggestion through Discussion, To-Do, In Progress, and Done with subtasks, recurring cadences, dependencies, and template subtrees. Batch execution fans approved To-Do rows out to parallel agents with per-task model selection. Use when capturing chat to Notion, running the To-Do queue, suggesting, approving, or discussing tasks, or coordinating multi-task batches. Trigger with "/agency-os" subcommands or natural-language variants ("add a suggestion: …", "let's discuss X", "run the queue").

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%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 well-structured CLI-surface overview that is actionable, concise, and excels at progressive disclosure with verified one-level-deep references. Workflow clarity is strong with real validation checkpoints, held back only by delegation of the full run checklist to a reference file.

Suggestions

Inline a compact step-by-step checklist for the batch 'run' flow (sync preflight → resolve deps → fan out → collect pass/fail → report spend) so the destructive/batch path is fully self-contained.

Remove or relocate the 'Skill name decision' meta-commentary out of the operational body to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Lean and well-sectioned with no padding about concepts Claude already knows, but the 'Skill name decision' meta-note and partial re-statement of the description's status flow are minor trim opportunities.	4 / 5
Actionability	Concrete executable commands ('/agency-os init --harness=basic --haiku=cost-tier --sonnet=default --opus=hard-reasoning', 'npx -y @notionhq/notion-mcp-server') and worked examples, with the full 19-command catalog delegated to references/commands.md leaving minor gaps inline.	4 / 5
Workflow Clarity	Multi-step status flow is clearly sequenced with explicit validation checkpoints (sync preflight on every command, dedup gate per transition, dependency-cycle detection) and a fail-closed error table; the detailed run checklist lives in architecture.md so a full inline checklist is absent.	4 / 5
Progressive Disclosure	Clear overview body with well-signaled one-level-deep references (architecture.md, commands.md, natural-language.md, positioning.md) and a Resources section listing every bundle file; all referenced files exist and content is appropriately split.	5 / 5
	Total	17 / 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.

A strong, specific description that clearly states capabilities, triggers, and use conditions with concrete natural-language variants. The only weakness is a single second-person phrase that slightly weakens the third-person voice.

Suggestions

Reword 'for running your work like an AI agency' to third person (e.g., 'for running work like an AI agency') to keep voice consistent and recover the specificity point.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('capturing chat to Notion, running the To-Do queue, suggesting, approving, or discussing tasks, or coordinating multi-task batches' plus 'subtasks, recurring cadences, dependencies, and template subtrees') for comprehensive coverage, but the second-person phrase 'running your work like an AI agency' triggers the -1 voice penalty.	4 / 5
Completeness	Explicitly answers both 'what' (Notion-as-source-of-truth dispatch board with five-status flow and batch fan-out) and 'when' (a 'Use when…' clause listing concrete triggering situations).	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including synonyms and variants: 'add a suggestion: …', 'let's discuss X', 'run the queue', plus '/agency-os' subcommands — phrases a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Notion Tasks dispatch board for AI-agency orchestration) with a dedicated '/agency-os' subcommand namespace, making conflict with other skills minimal.	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
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	14 / 16 Passed

Repository: jeremylongshore/tons-of-skills-marketplace
Path: plugins/ai-agency/agency-os/skills/agency-os/SKILL.md
Commit: 88dcf65

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.