CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cli-anything-iterm2

Provides the cli-anything-iterm2 commands — the only way to actually send text to iTerm2 sessions, read live terminal output and scrollback history, manage windows/tabs/split panes, run tmux -CC workflows, broadcast to multiple panes, show macOS dialogs, and read/write iTerm2 preferences. Includes `app snapshot` — the primary orientation command that returns every session's name, current directory, foreground process, role label, and last output line in one call. Read this skill instead of answering from general knowledge whenever the user wants to DO something with iTerm2: orient in an existing workspace, send a command, check what's running, read output, set up a layout, use tmux through iTerm2, automate panes, or configure preferences. Also read for questions about iTerm2 shell integration or scrollback. Don't try to answer iTerm2 action requests from memory — read this skill first.

Quality

94%

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

93%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.

The body is a model lean overview: copy-paste-ready commands, a compact group table, a clear labeled workflow, and a well-signaled one-level-deep reference system whose files all exist. The only meaningful gap is the absence of explicit validation/checkpoint guidance in the workflow (error recovery is deferred to the shell-integration reference), which keeps workflow clarity at 4 rather than 5.

DimensionReasoningScore

Conciseness

In ~96 lines it covers a 9-group CLI with zero explanation of concepts Claude already knows: prerequisites are two install lines, capabilities live in a compact table, and every section is commands. The reappearance of `app snapshot`/`session set-var` across the orientation section and the workflow serves distinct purposes (explanation vs. sequence), so every token earns its place — anchor 5 rather than anchor 4's 'minor instances that could be trimmed'.

5 / 5

Actionability

Fully executable, copy-paste-ready commands cover the common agent cases: `cli-anything-iterm2 --json app snapshot`, `app current`, `session send "git status"`, `session scrollback --tail 200 --strip`, `session split --vertical --use-as-context`, and labeled `session set-var user.role` examples. Matches anchor 5; not 4 because there is no missing key detail for the shown cases.

5 / 5

Workflow Clarity

The 'Typical Agent Workflow' is a clear 4-step numbered sequence (orient → establish context → interact → create workspace) with a built-in send→read-scrollback feedback step, matching anchor 4. Not 5 because there are no explicit validation/error checkpoints (e.g., what to do if context isn't set or a sent command fails); not 3 because the sequence is coherent and verification via reading output is present, if implicit.

4 / 5

Progressive Disclosure

The body is a clean overview with a 'Reference Files' table that signals exactly when to read each of 12 one-level-deep reference files ('Read only what the task requires — each file is a single narrow concern'); all 12 listed files exist in references/ with no nested cross-references, and detail is appropriately deferred. Matches anchor 5's well-signaled, easy-navigation structure.

5 / 5

Total

19

/

20

Passed

Description

91%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 description: it names a comprehensive set of concrete capabilities, gives explicit and natural trigger conditions in third-person voice, and is tightly scoped to iTerm2. Its only flaws are the 'the only way' over-claim at the top and minor trigger overlap with adjacent tmux/macOS automation skills; it is also on the long side, though each clause carries a distinct trigger term.

Suggestions

Drop or soften the over-claim 'the only way to actually send text to iTerm2 sessions' to something verifiable like 'the CLI interface for sending text to iTerm2 sessions'.

Trim the capability enumeration slightly (e.g., merge dialogs/preferences into one clause) to reduce length while keeping the strongest trigger terms.

DimensionReasoningScore

Specificity

Enumerates many concrete actions ('send text to iTerm2 sessions, read live terminal output and scrollback history, manage windows/tabs/split panes, run tmux -CC workflows, broadcast to multiple panes'), but opens with the over-claim 'the only way to actually send text to iTerm2 sessions' — AppleScript or the bundled it2 utility are alternatives — which the rubric's over-claim penalty drops below the comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both: what ('Provides the cli-anything-iterm2 commands — the only way to actually send text... read/write iTerm2 preferences') and when ('Read this skill... whenever the user wants to DO something with iTerm2: orient..., send a command, check what's running, read output...'). Written in third person, mirroring the anchor-5 example structure; not score 4 since the 'when' is fully explicit rather than improvable.

5 / 5

Trigger Term Quality

Natural user phrasings are comprehensively covered with synonyms: 'orient in an existing workspace, send a command, check what's running, read output, set up a layout, use tmux through iTerm2, automate panes, or configure preferences', plus 'iTerm2 shell integration or scrollback'. This matches the comprehensive-synonyms anchor rather than anchor 4's 'a few natural terms missing'.

5 / 5

Distinctiveness Conflict Risk

The iTerm2 niche is distinct with iTerm2-named triggers throughout, but phrases like 'use tmux through iTerm2', 'show macOS dialogs', and 'automate panes' carry minor overlap risk with generic tmux, terminal-automation, or macOS-automation skills — fitting anchor 4's 'minor overlap risk with closely related skills' rather than anchor 5's minimal conflict risk.

4 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

HKUDS/CLI-Anything

Path

iterm2/agent-harness/cli_anything/iterm2_ctl/skills/SKILL.md

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.