agent-manager-skill

Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

Quality

69%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/agent-manager-skill/SKILL.md

Quality

Content

72%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 compact, command-focused skill body with executable examples and clean organization that respects the token budget. Its main weaknesses are the absence of a sequenced workflow with validation checkpoints (required for batch agent management) and minor execution gaps such as unexplained agent IDs and setup paths.

Suggestions

Sequence the commands into an explicit workflow (clone → configure agents/ → doctor → start → monitor → assign) with a validation step such as running 'doctor' or checking 'list' output before assigning tasks.

Explain the agent ID convention (e.g. EMP_0001) and where the agents/ directory must live relative to the cloned repo, plus the clone destination needed for the command paths to resolve.

Trim the boilerplate Limitations lines to one concrete guardrail, or replace them with skill-specific caveats (e.g. tmux session limits, log rotation).

Dimension	Reasoning	Score
Conciseness	The body is lean with no explanations of concepts Claude already knows and concrete commands stated directly, but the Limitations section is boilerplate filler ('Do not treat the output as a substitute for environment-specific validation...'). This matches anchor 4 — efficient with minor instances that could be trimmed — rather than 5 where every token earns its place.	4 / 5
Actionability	Provides copy-paste-ready commands ('python3 agent-manager/scripts/main.py doctor', 'start EMP_0001', 'monitor --follow', 'assign' with heredoc) covering the main cases. It is not 5 because of minor gaps: no clone destination or install step linking the git clone to the command paths, and no explanation of agent IDs like EMP_0001 or the agents/ directory layout.	4 / 5
Workflow Clarity	Commands are catalogued rather than sequenced — there is no install → configure → start → monitor flow with checkpoints. Because this skill manages batch operations over multiple agents (including stopping them) with no validation steps beyond an unexplained 'doctor' command, the rubric caps workflow clarity at 3.	3 / 5
Progressive Disclosure	The skill is under 50 lines, self-contained, and organized into clear sections (When to Use, Prerequisites, Common commands, Notes, Limitations) with the only external pointer ('see the repo for examples') appropriately signaled. The rubric's simple-skill guideline allows a score of 5 with just well-organized sections and no external references needed.	5 / 5
	Total	16 / 20 Passed

Description

66%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 concise, fairly specific description with concrete action verbs, but it omits any explicit 'Use when...' trigger guidance, which caps its completeness and weakens its usefulness for skill selection. Keyword coverage is good though missing common synonyms like 'parallel' or 'background' agents.

Suggestions

Add an explicit trigger clause, e.g. 'Use when running multiple CLI agents in parallel, managing agents in tmux sessions, or scheduling recurring agent work with cron.'

Include natural synonyms such as 'parallel agents', 'background agents', and 'tail agent logs' to broaden trigger-term coverage.

Mention the log/monitoring capability explicitly (e.g. 'tail their output') since it is a primary function only implied by 'monitor'.

Dimension	Reasoning	Score
Specificity	The description names the domain ('multiple local CLI agents via tmux sessions') and several concrete actions ('start/stop/monitor/assign', 'cron-friendly scheduling'), matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because coverage verbs like log tailing, parallel runs, or agent listing are absent.	4 / 5
Completeness	The 'what' is clear (manage agents via tmux with start/stop/monitor/assign plus cron scheduling), but there is no 'Use when...' clause or any equivalent explicit trigger guidance, which the rubric guideline caps at 3. It is not 2 because the 'what' is concrete and specific rather than vague.	3 / 5
Trigger Term Quality	Natural terms users would say are present — 'tmux sessions', 'CLI agents', 'monitor', 'cron-friendly scheduling' — giving good keyword coverage. It is not 5 because common variations like 'run agents in parallel', 'background agents', or 'agent logs' are missing.	4 / 5
Distinctiveness Conflict Risk	The niche is clear — tmux-managed local CLI agents with cron scheduling — so overlap risk is minor, matching 'mostly distinct'. It is not 5 because the trigger surface (agents, monitoring, scheduling) could still overlap with generic multi-agent orchestration skills.	4 / 5
	Total	15 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/agentic-awesome-skills
Path: skills/agent-manager-skill/SKILL.md
Commit: 7b534bc

Reviewed: 5 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.