CtrlK
BlogDocsLog inGet started
Tessl Logo

cli-anything

Use when the user wants Codex to build, refine, test, or validate a CLI-Anything harness for a GUI application or source repository. Adapts the CLI-Anything methodology to Codex without changing the generated Python harness format.

74

1.75x
Quality

62%

Does it follow best practices?

Impact

91%

1.75x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./codex-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

66%

SQLite Automation Harness

Build mode harness structure and packaging

Criteria
Without context
With context

Top-level structure

25%

100%

Markdown entrypoint

0%

100%

Package subdirectories

0%

100%

Backend wrapper

50%

100%

Click CLI used

0%

100%

One-shot subcommands

12%

100%

REPL default

100%

100%

JSON output flag

62%

100%

Session state / undo-redo

100%

100%

Namespace packages in setup.py

0%

100%

No top-level cli_anything __init__.py

0%

100%

console_scripts entry point

25%

100%

Report: files and validation

100%

100%

Report: risks or limitations

0%

100%

93%

-2%

Extending a ffmpeg CLI Harness

Refine mode: gap analysis and command preservation

Criteria
Without context
With context

convert command preserved

100%

100%

info command preserved

100%

100%

New commands added

100%

100%

High-impact additions

100%

100%

Backend reuse

100%

80%

Report: existing inventory

100%

100%

Report: gap rationale

100%

100%

Report: files changed

100%

100%

Report: validation

100%

100%

Report: risks or limitations

0%

0%

80%

53%

Test Suite for a Pandoc CLI Harness

Test mode: test planning and file organization

Criteria
Without context
With context

TEST.md exists

0%

0%

TEST.md before implementation

0%

0%

test_core.py exists

0%

100%

test_full_e2e.py exists

0%

100%

Unit tests in test_core.py

0%

100%

Subprocess in test_full_e2e.py

0%

100%

E2e tests cover backend

0%

100%

No large test files

100%

71%

test-report.md exists

100%

100%

report: test results

100%

100%

Repository
HKUDS/CLI-Anything
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.