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.

65

Quality

79%

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 ./.agents/skills/public-plugin-packaging/SKILL.md

The canonical home for this skill is public-plugin-packaging in agentlas-ai/Agentlas-OS

SKILL.md
Quality
Evals
Security

Quality

Content

80%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.

A concise, well-structured checklist skill with clear validation conditions and good organization. Its main weakness is workflow clarity: it is a flat checklist rather than a sequenced workflow with explicit ordering and a fix-and-retry feedback loop.

Suggestions

Add an ordered sequence to the checklist so the verify/public_safety_check steps run in a defined order after packaging, with an explicit 'if a check fails: fix and re-run' feedback loop.

Include the actual one-line install command and the verify/public-safety invocation commands so the guidance is copy-paste executable rather than just naming the scripts.

Clarify what 'passes' means for each script (expected exit code or output) so validation results are unambiguous.

DimensionReasoningScore

Conciseness

A lean flat checklist with clear section headers, no padding, and no over-explanation of concepts Claude already knows; every line earns its place.

5 / 5

Actionability

Lists concrete, verifiable file-path targets and named scripts (install.sh, verify-package.sh, public_safety_check.sh), but states they "support"/"pass" without giving the actual commands to run, so it is not fully copy-paste ready.

4 / 5

Workflow Clarity

Functions as a verification checklist with explicit validation checkpoints (the "passes" conditions), but lacks any sequenced ordering and has no error-recovery feedback loop, fitting the anchor where checkpoints are present but sequence is implicit.

3 / 5

Progressive Disclosure

Under 50 lines, no bundle files needed, and well-organized into clearly signaled sections (Checklist, Public Boundary), satisfying the simple-skill exception for top marks.

5 / 5

Total

17

/

20

Passed

Description

78%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.

A strong, trigger-led description that names a distinct niche and several concrete release contexts. It would reach the top level by spelling out the concrete packaging actions rather than relying on the generic verb "packaging".

DimensionReasoningScore

Specificity

Names the packaging domain plus four concrete release/distribution targets ("public GitHub release", "Codex plugin submission", "Claude adapter distribution", "one-line terminal installation"), but these are destinations rather than a comprehensive set of distinct actions performed.

4 / 5

Completeness

Explicitly answers both "when" (the four release contexts) and "what" (packaging an Agentlas agent repo), but the "what" is a single generic verb rather than a list of concrete operations, keeping it just below the anchor 5 example.

4 / 5

Trigger Term Quality

Opens with a natural "Use when packaging..." trigger and covers several concrete trigger phrases, but misses common synonyms a user might actually say like "publish" or "ship".

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (Agentlas multi-platform agent repo packaging) with distinct, specific triggers and minimal overlap risk with other skills.

5 / 5

Total

17

/

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

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.