CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-code-headless

Run Claude Code programmatically without interactive UI. Triggers on: headless, CLI automation, --print, output-format, stream-json, CI/CD, scripting.

92

1.09x
Quality

Does it follow best practices?

Impact

95%

1.09x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

92%

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 error-handling checkpoint. Its main weakness is progressive disclosure: it points to three reference files that are not present in the bundle.

Suggestions

Create the referenced ./references/ files (cli-options.md, output-formats.md, integration-patterns.md) or remove the dangling references so navigation is not broken.

Move the full CLI options and output-format detail tables into those reference files to keep SKILL.md a true overview, or commit to keeping everything inline and drop the 'Additional Resources' references.

De-duplicate the session-resume pattern between Quick Start and Multi-turn automation to tighten token usage.

DimensionReasoningScore

Conciseness

The body is lean: dense flag tables, copy-paste code, and minimal prose, with no explanation of concepts Claude already knows; the only minor redundancy is the resume pattern reappearing across sections.

3 / 3

Actionability

Examples are fully executable bash commands with real flags, concrete output-format JSON, and specific tool-restriction/CI patterns — copy-paste ready.

3 / 3

Workflow Clarity

Multi-turn automation is clearly sequenced and the Error Handling section provides an explicit validation checkpoint (check is_error, exit 1); operations here are not destructive/batch so no fix-retry loop is required.

3 / 3

Progressive Disclosure

Sections are well-organized and reference files are clearly signaled in 'Additional Resources', but the referenced paths (./references/cli-options.md, output-formats.md, integration-patterns.md) do not exist, so navigation fails and detail that could be split stays inline.

2 / 3

Total

11

/

12

Passed

Description

90%

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 concise, third-person description that states a concrete capability and supplies explicit trigger guidance covering both natural and technical terms. It is slightly thin on the breadth of actions described, but otherwise strong.

DimensionReasoningScore

Specificity

It names a concrete capability ('Run Claude Code programmatically without interactive UI') but states only that single action; the rest are triggers, not additional actions, so it is not comprehensive.

2 / 3

Completeness

It answers 'what' (run Claude Code programmatically without UI) and 'when' via an explicit 'Triggers on:' clause equivalent to a 'Use when...' trigger, satisfying the completeness cap lift.

3 / 3

Trigger Term Quality

'Triggers on: headless, CLI automation, --print, output-format, stream-json, CI/CD, scripting' covers natural terms a user would say (headless, CI/CD, scripting) alongside the relevant flag names.

3 / 3

Distinctiveness Conflict Risk

The headless/CLI-automation niche with specific flag-based triggers is clearly distinct from other skills and unlikely to fire for the wrong skill.

3 / 3

Total

11

/

12

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
NeverSight/skills_feed
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.