CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-native-cli

Design spec with 98 rules for building CLI tools that AI agents can safely use. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description.

57

Quality

66%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/ai-native-cli/SKILL.md

The canonical home for this skill is ai-native-cli in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured, actionable spec with concrete examples and a clear phased workflow, but it restates the same rules across multiple sections, adding noticeable redundancy. Progressive disclosure is good despite being a single file.

Suggestions

Consolidate the rule restatements: keep the detailed Certification Requirements as the canonical source and have the Checklist/Best Practices/Pitfalls reference it rather than re-listing rules.

Add explicit validation checkpoints between phases (e.g. 'Verify all core rules pass before starting Phase 2') to strengthen workflow clarity.

Consider moving the full 98-rule catalog into a references/ file and keeping SKILL.md as an overview with the philosophy, layer model, and quick-start examples.

DimensionReasoningScore

Conciseness

The same rules are restated across Certification Requirements, the Reserved Flags table, the Quick Implementation Checklist, Best Practices, and Common Pitfalls; the core is a dense reference rather than concept padding, but the redundancy could be tightened.

3 / 5

Actionability

Concrete, copy-pasteable patterns appear throughout (error JSON with code/message/suggestion, CLI invocations, exit-code table, agent/ directory tree, reserved-flags table), with only minor gaps toward fully executable coverage.

4 / 5

Workflow Clarity

A clear phased sequence (Phase 1->2->3 certification, Step 1/2/3 in How It Works) with an implementation checklist is present; it lacks explicit validation checkpoints between phases, though the destructive/batch cap does not apply to this design-spec skill.

4 / 5

Progressive Disclosure

No bundle files exist and the single SKILL.md is well-sectioned with clear headers, tables, and examples; the 98-rule catalog could arguably be split into a separate reference file, leaving minor organization gaps.

4 / 5

Total

15

/

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.

The description clearly states what the skill covers and enumerates specific capability areas with good trigger terms, but it omits any explicit 'Use when...' guidance, capping completeness. It is a solid, mostly distinctive description with one clear gap.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building or retrofitting CLI tools that AI agents will invoke, or when auditing a CLI for agent-safety compliance.'

Include natural synonyms users might say, such as 'command-line interface' or 'CLI automation', to broaden trigger coverage.

Reframe coverage domains as concrete actions (e.g. 'Define JSON output schemas, structure error responses, set exit codes') to lift specificity toward 5.

DimensionReasoningScore

Specificity

Lists several specific coverage areas ('structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description'), but these are coverage domains rather than a comprehensive set of concrete actions, so it sits above anchor 3 yet below anchor 5.

4 / 5

Completeness

The 'what' is clear ('Design spec with 98 rules for building CLI tools that AI agents can safely use') but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms like 'building CLI tools', 'AI agents', 'JSON output', and 'exit codes' give good keyword coverage, though common variations such as 'command line' or 'CLI automation' are missing.

4 / 5

Distinctiveness Conflict Risk

The niche 'CLI tools that AI agents can safely use' is mostly distinct with only minor overlap risk against general CLI-design skills, especially given a related @cli-best-practices skill exists.

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.

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
administrakt0r/AI-Agents-Safe-Coding-Skills
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.