claude-code-headless

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

1.09x

Quality

74%

Does it follow best practices?

Impact

95%

1.09x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xdarkmatter/claude-mods/claude-code-headless/SKILL.md

Quality

Content

78%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 an efficient, highly actionable CLI reference with clear sequences and an error-handling checkpoint. Its main weakness is progressive disclosure: three reference files are advertised but not present in the bundle.

Suggestions

Create the advertised `./references/cli-options.md`, `output-formats.md`, and `integration-patterns.md` files, or remove the dangling references and inline the essential material.

Add an explicit validate-fix-retry loop for the CI/CD pattern (e.g., re-run on `.is_error` with adjusted tools) to reach the top workflow-clarity anchor.

Trim the duplicated resume example between Quick Start and Common Patterns to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is lean: compact flag tables and copy-paste commands with almost no concept explanation, assuming Claude's competence; only minor redundancy (resume appears in both Quick Start and Common Patterns) keeps it just below the leanest anchor.	4 / 5
Actionability	Examples are fully executable and copy-paste ready across the common cases — basic execution, JSON parsing, resume/multi-turn, tool restrictions, CI/CD, and an error-handling block that checks `.is_error`.	5 / 5
Workflow Clarity	Multi-turn automation and the Error Handling section give clear sequences with an explicit validation checkpoint (check `.is_error`, exit on failure); it stops short of the full validate-fix-retry checklist that defines the 5 anchor.	4 / 5
Progressive Disclosure	Sections are well organized and additional detail is signaled via "Additional Resources" pointing to `./references/*.md`, but those referenced files do not exist in the bundle, so navigation is undermined by broken one-level-deep references.	3 / 5
	Total	16 / 20 Passed

Description

70%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 is concise, third-person, and explicitly pairs a clear capability statement with concrete trigger terms, giving it strong completeness and trigger quality. It is slightly limited in specificity by naming only one core action.

Suggestions

Expand the "what" with 1-2 more concrete actions (e.g., parse JSON output, resume multi-turn sessions) to lift specificity toward the comprehensive anchor.

Add a couple of natural phrasings users might say (e.g., "non-interactive", "automate Claude Code") to round out trigger synonyms.

Dimension	Reasoning	Score
Specificity	"Run Claude Code programmatically without interactive UI" names the domain and one concrete action (headless programmatic execution) but does not enumerate multiple specific capabilities, matching the anchor that lists domain plus 1-2 concrete actions.	3 / 5
Completeness	It states a clear "what" (run Claude Code programmatically without UI) and an explicit "when" via the "Triggers on:" clause with concrete triggers, but the "what" is thinner than the comprehensive multi-action anchor at 5.	4 / 5
Trigger Term Quality	"Triggers on: headless, CLI automation, --print, output-format, stream-json, CI/CD, scripting" provides good coverage of natural terms users would say, though a few synonyms or phrasings are missing relative to the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Headless/CLI-automation is a clear niche with distinct triggers and minimal conflict risk, though it sits alongside related claude-code skills, leaving minor overlap rather than the fully isolated niche of the 5 anchor.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NeverSight/skills_feed
Path: data/skills-md/0xdarkmatter/claude-mods/claude-code-headless/SKILL.md
Commit: 2f57aec

Reviewed: about 22 hours ago

Table of Contents

Discovery Implementation Validation

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.