CtrlK
BlogDocsLog inGet started
Tessl Logo

human-cli

Reach the actual human you're working for via the `human` CLI (ask/approve/choose/tell) when you need a decision, approval, or notification and no one is watching this terminal right now. Use for background/autonomous/scheduled runs, risky or irreversible actions, and genuine multi-way ambiguity — not for routine questions the current chat user can just answer next turn.

71

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, highly actionable reference with executable examples and a clear exit-code model. The main gaps are a slightly verbose rationale in the 'when to use' and setup sections and no explicit validate→retry feedback loop for the risky operations the skill itself promotes.

Suggestions

Add an explicit validate→fix→retry feedback loop for the risky `approve`/irreversible-action flow (e.g., on denial (exit 10) or timeout (exit 11), state the concrete recovery: stop, surface to logs, or `human wait <id>` to resume).

Trim explanatory prose in 'When to reach for this vs. just asking in chat' and the keyless-demo/sign-up setup edge cases to assumed-knowledge bullets.

Move the detailed flag and exit-code reference into a separate REFERENCE.md and keep SKILL.md as an overview, to tighten the core file and add a one-level-deep reference.

DimensionReasoningScore

Conciseness

Largely lean and tactical with executable snippets and a clean table, but the 'When to reach for this' and 'Before you rely on it' sections include some explanatory prose and setup edge-case detail that could be trimmed slightly.

4 / 5

Actionability

Provides copy-paste-ready commands for every command and flag, a concrete exit-code branching example, and `--json` guidance — fully executable and covers the common cases.

5 / 5

Workflow Clarity

Clear sequenced decision guidance for when-to-use and setup states with error-message-driven next steps, and an exit-code branching example; it lacks an explicit validate→fix→retry feedback loop for the risky/approve operations it describes, so it sits just below 5.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections covering setup, contacts, commands, exit codes, and flags with no nested references; it is a single monolithic file with no bundle files to offload the API/flag reference bulk, leaving minor room to split detailed reference material out.

4 / 5

Total

17

/

20

Passed

Description

92%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 precise, third-person description that names concrete actions and channels and explicitly covers when to use it, with clear negative-trigger guidance to avoid misuse. Minor room for broader synonym coverage in the trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (`ask`, `approve`, `choose`, `tell`) over named channels and names specific use cases (background/autonomous/scheduled runs, risky/irreversible actions), giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what (reach a human via ask/approve/choose/tell over Telegram/Slack/email) and when (background/autonomous/scheduled runs, risky or irreversible actions, genuine multi-way ambiguity) with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural terms (`ask`, `approve`, `notify`, `no one is watching`, `need approval before deploying`) but slightly misses the CLI name as a colloquial phrase and lacks file-extension-style synonyms; not quite the full synonym spread of a 5.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche (reaching a human out-of-band via the `human` CLI) with distinct triggers and an explicit negative trigger ('not for routine questions the current chat user can just answer'), minimizing conflict with ordinary chat skills.

5 / 5

Total

19

/

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.

Validation15 / 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
novuhq/novu
Reviewed

Table of Contents

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.