CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentlas-packaging

Use when converting, repairing, or packaging an existing local or external agent/team into Agentlas architecture for local install, Agentlas import, Codex plugin use, Claude adapter use, or open-source release.

Quality

74%

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 ./codex/plugins/agentlas-core-engine-meta-agent/runtime-support/skills/agentlas-packaging/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 lean, well-sequenced procedure with a genuine validation feedback loop, and the workforce résumé constraints are unusually precise. Its weaknesses are incomplete executable guidance for the contract files the procedure demands, and references to bundle files that are missing from the skill as shipped.

Suggestions

Add the missing bundle files (contracts/builder-interview-research-gate.md, scripts/verify-team-package.sh) or remove/inline the references — step 3 and step 8 cannot be executed as written.

Provide minimal templates or field schemas for the 13 contract files in step 4 (or move them to a reference file), so an executor knows what to author rather than just where.

Merge the vague step 9 ('Run package verification and public-safety checks before release') into step 8's concrete verify script invocation, and name the specific public-safety checks (secrets scan, path scan) instead of leaving them abstract.

DimensionReasoningScore

Conciseness

The body is a lean checklist with no padding and no explanation of concepts Claude already knows; step 5's density is unfamiliar domain knowledge that earns its place. It falls short of anchor 5 only because step 9 overlaps step 8 and the ontology contract version string could live in a reference.

4 / 5

Actionability

There is one copy-paste command ('scripts/verify-team-package.sh <package-root>') plus precise file lists and field constraints (roles 0-4, communities 1-5, skills 3-12), but many steps are high-level directives with no how-to — 'Inspect the existing source', 'Preserve useful behavior', 'Run package verification and public-safety checks' without naming the checks — and no templates or examples for the 13 required contract files. This matches anchor 3 (some concrete guidance but incomplete) rather than anchor 4's mostly-executable guidance.

3 / 5

Workflow Clarity

A clear 9-step sequence with an explicit validation feedback loop (step 8: run the verify script, fix failures, only then hand off), so the missing-validation cap does not apply. It falls short of anchor 5 because step 9 is vague and redundant with step 8, and mid-process steps 5-7 (résumé authoring, secret removal) have no checkpoints.

4 / 5

Progressive Disclosure

Sections (Procedure, Output) are well organized and references are one level deep, but the two load-bearing referenced files — 'contracts/builder-interview-research-gate.md' and 'scripts/verify-team-package.sh' — do not exist in the bundle (no references/, scripts/, or assets/ directories are present), so navigation to them is broken. This places it at anchor 3: structure present, but referenced material is not actually available.

3 / 5

Total

14

/

20

Passed

Description

73%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 solid description with an explicit trigger clause, good niche-specific keyword coverage, and very low conflict risk thanks to the unique Agentlas branding. Its main weakness is that the capability statement is thin: the verbs converting/repairing/packaging are near-synonyms and the description never states what the skill actually produces.

Suggestions

Replace the near-synonymous verbs with distinct concrete actions, e.g. 'Converts an agent's prompt and tools into Agentlas contracts, repairs a broken package's contract files, and adds runtime adapters for local install, Agentlas import, or release.'

State the concrete outputs (contract files like AGENTS.md, .agentlas/ manifests, runtime adapters) so the 'what' stands independently of the 'Use when' clause.

DimensionReasoningScore

Specificity

The description names the domain ('packaging an existing local or external agent/team into Agentlas architecture') and actions ('converting, repairing, or packaging'), but the three verbs are near-synonyms and it never enumerates the concrete work products, matching anchor 3 rather than the multi-action coverage of anchor 4.

3 / 5

Completeness

It has an explicit 'Use when…' trigger clause with concrete trigger contexts, satisfying the trigger-guidance requirement, but the 'what' is folded into the when-clause rather than independently stated, so it does not fully match anchor 5's clearly separated what-and-while structure.

4 / 5

Trigger Term Quality

Good natural keyword coverage including 'converting', 'repairing', 'packaging', 'agent/team', 'Agentlas import', 'Codex plugin', 'Claude adapter', and 'open-source release'; a few natural synonyms like 'bundle' or 'port' are missing, so it sits between anchors 3 and 5 but noticeably above the midpoint.

4 / 5

Distinctiveness Conflict Risk

'Agentlas architecture' is a unique proper noun and the trigger conditions (local install, Agentlas import, Codex plugin use) are specific to this niche, giving a clear niche with distinct triggers and minimal conflict risk with generic packaging or code skills.

5 / 5

Total

16

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

agentlas-ai/Agentlas-OS

Path

codex/plugins/agentlas-core-engine-meta-agent/runtime-support/skills/agentlas-packaging/SKILL.md

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.