CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agent-manager-skill

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

61

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is agent-manager-skill in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

80%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 lean, actionable command reference with clean organization, but it lacks a sequenced first-run workflow and contains a path inconsistency between the clone step and the commands. Spelling out the agent-configuration step and the role of 'doctor' as a pre-flight check would make it fully executable end-to-end.

Suggestions

Sequence the commands into a first-run workflow: clone → configure an agent under agents/ → run doctor → start EMP_0001 → assign → monitor, so users know the order and where agent IDs come from.

Fix the path inconsistency: the clone creates 'agent-manager-skill/' but every command references 'agent-manager/scripts/main.py'.

Explain 'doctor' as a pre-flight validation step and show a minimal agent config example instead of deferring entirely to "see the repo for examples".

DimensionReasoningScore

Conciseness

Lean and efficient: no concept explanations, short purposeful sections (When to Use, Prerequisites, Common commands, Notes), and every command example earns its place. Nothing explains what Claude already knows, matching the 'every token earns its place' anchor.

5 / 5

Actionability

Provides concrete, copy-pasteable commands (doctor, list, start, monitor --follow, assign with heredoc) covering common cases. Not a 5 because the command path 'agent-manager/scripts/main.py' does not match the cloned 'agent-manager-skill' directory, and agent IDs/configuration are deferred to "see the repo".

4 / 5

Workflow Clarity

Commands are presented as a catalog rather than a sequenced workflow — there is no install → configure agent → doctor → start → assign → monitor flow, and no validation checkpoints (the role of 'doctor' is never explained). Managing multiple agents is a batch operation, so per the rubric's cap, workflow clarity cannot exceed 3. Not a 2 because the When-to-Use list plus the command set gives a rough implicit order.

3 / 5

Progressive Disclosure

The skill is under 50 lines with well-organized sections and no need for external reference files, so per the rubric's simple-skill note it earns a 5 on organization alone. No bundle files (references/scripts/assets) exist, so nothing is deferred or nested.

5 / 5

Total

17

/

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 specific, action-oriented description with a clear niche, undermined by the complete absence of a 'when to use' trigger clause. Adding an explicit 'Use when...' sentence with natural trigger phrases would raise both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when you need to run multiple CLI agents in parallel, assign tasks to agents, or schedule recurring agent work."

Replace "cron-friendly scheduling" with a concrete action such as "schedule recurring agent runs via cron" so every listed capability is a crisp action.

Add common synonyms users would naturally say ("parallel agents", "background agents", "agent sessions") to broaden trigger coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions — "start/stop/monitor/assign" — in the tmux-based agent-management domain. Not a 5 because "cron-friendly scheduling" is a vague capability modifier rather than a crisp action, and capabilities shown in the body (log tailing) are absent.

4 / 5

Completeness

The 'what' is clear (manage multiple local CLI agents via tmux: start/stop/monitor/assign, with scheduling), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3. It is not a 2 because the 'what' half is concrete and specific.

3 / 5

Trigger Term Quality

Contains natural terms users would say ("manage", "start/stop", "monitor", "assign", "agents", "scheduling", "tmux"), but misses common variations such as "run agents in parallel", "background agents", or "agent sessions". Fits the 'good keyword coverage; a few natural terms missing' anchor rather than the 5's comprehensive synonym coverage, and is well above the 3's sparse keywords.

4 / 5

Distinctiveness Conflict Risk

The tmux-based multi-CLI-agent management niche with cron scheduling is fairly distinct. Minor overlap risk remains with generic agent-orchestration or tmux/session-management skills, so it fits 'mostly distinct' rather than the 5's 'clear niche with minimal conflict risk'.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/agent-manager-skill/SKILL.md

Revision

64adc55

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill