CtrlK
BlogDocsLog inGet started
Tessl Logo

public-plugin-packaging

Use when packaging an Agentlas agent repo for public GitHub release, Codex plugin submission, Claude adapter distribution, or one-line terminal installation.

75

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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 tight, concrete packaging-verification checklist with no wasted tokens and clear sectioning. Its main weakness is workflow clarity: the checks are unsequenced and lack explicit failure-recovery feedback loops for a batch verification operation.

Suggestions

Convert the checklist into a numbered sequence with an explicit validation feedback loop, e.g. 'If scripts/verify-package.sh fails, review the error, fix the offending artifact, and re-run before proceeding.'

Group the existence checks by phase (e.g. manifest files, command files, agent/skill files, scripts) so the order of verification is unambiguous.

Add a short note on what to do when a required file is missing (create from the referenced template vs. abort) to close the verification gap.

DimensionReasoningScore

Conciseness

Every line is a lean, concrete check (e.g. '`codex/marketplace.json` exists.', '`scripts/verify-package.sh` passes.') with no padding and no explanation of concepts Claude already knows, matching the most token-efficient anchor.

3 / 3

Actionability

Each item names an exact, verifiable artifact path, and three name runnable scripts (install.sh, verify-package.sh, public_safety_check.sh), giving concrete actionable guidance rather than vague direction.

3 / 3

Workflow Clarity

The checklist lists clear requirements but presents them as a flat set rather than a sequenced process, and it lacks explicit validation feedback loops (e.g. 'if verify-package.sh fails, fix and re-run') for a batch verification context, capping it at 2 per the rubric's feedback-loop note.

2 / 3

Progressive Disclosure

At roughly 20 lines with two well-organized sections (Checklist, Public Boundary) and no need for external references, it meets the rubric's allowance for simple skills under 50 lines scoring 3 on well-organized structure.

3 / 3

Total

11

/

12

Passed

Description

100%

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-triggered, and explicitly states both what the skill does and when to use it across five concrete distribution targets. It is well above the bad-example floor with no vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete packaging targets — 'public Codex plugin registration, Claude Code installation, GitHub release, one-line terminal install, or open-source distribution' — matching the anchor for listing multiple specific concrete actions.

3 / 3

Completeness

Explicit 'Use when packaging this meta-agent for...' trigger answers both what (packaging this meta-agent) and when (the listed distribution scenarios), matching the highest anchor with explicit triggers.

3 / 3

Trigger Term Quality

Includes natural terms a plugin author would actually say — 'Codex plugin registration', 'Claude Code installation', 'GitHub release', 'one-line terminal install', 'open-source distribution' — giving good coverage of natural phrasings.

3 / 3

Distinctiveness Conflict Risk

Scoped to a very specific niche — meta-agent plugin packaging for named distribution channels — making it clearly distinguishable and unlikely to trigger for unrelated skills.

3 / 3

Total

12

/

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

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
agentlas-ai/Agentlas-OS
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.