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

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/agentlas-packaging/SKILL.md

Quality

Content

77%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 content is a well-sequenced, actionable packaging procedure with strong validation checkpoints and lean prose. Its chief weakness is progressive disclosure: it points to contract and script files that are not bundled alongside the skill, so the cross-file structure it implies is incomplete.

Suggestions

Bundle the referenced files (e.g., place `contracts/builder-interview-research-gate.md` and `scripts/verify-team-package.sh` in the skill) so the implied reference structure actually exists.

Use clear one-level-deep links (e.g., 'See [builder-interview-research-gate.md](contracts/builder-interview-research-gate.md)') and add a brief reference index so navigation is explicit rather than embedded in prose.

Dimension	Reasoning	Score
Conciseness	The body is a tight, mostly imperative 9-step procedure that assumes Claude's competence and avoids explaining basic concepts; only minor padding (the workforce-search rationale and ontology caveat) could be trimmed.	4 / 5
Actionability	It gives concrete artifacts to author, a specific verification command (`scripts/verify-team-package.sh <package-root>`), a versioned ontology reference, and concrete cardinality constraints per field, with only minor gaps (no sample file contents or command outputs).	4 / 5
Workflow Clarity	The 9 steps are clearly sequenced with explicit validation checkpoints: step 3's research gate, step 8's 'If it fails, correct the package shape before any final handoff', and step 9's pre-release verification provide a clear validate-fix-retry feedback loop for the batch/destructive packaging work.	5 / 5
Progressive Disclosure	The body references several external files (`contracts/builder-interview-research-gate.md`, `scripts/verify-team-package.sh`, ontology graph), but there are no references/, scripts/, or assets/ bundle directories present, so the cross-file structure is not actually materialized and navigation is only partially signaled.	3 / 5
	Total	16 / 20 Passed

Description

76%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 strong: it clearly answers both what it does and when to use it, names a distinct niche, and lists concrete actions and outputs. Its main weakness is trigger-term coverage, which leans on the product-specific term 'Agentlas' rather than broader natural-language synonyms.

Suggestions

Add natural-language synonyms users would actually say (e.g., 'agent', 'skill', 'plugin', 'adapter', 'bundle') so the trigger fires beyond the 'Agentlas' brand name.

Consider naming target file types or extensions (e.g., 'agent packages', 'ZIPs', 'skill bundles') to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('converting, repairing, or packaging') and concrete targets ('local or external agent/team', 'Agentlas architecture'), plus five enumerated delivery outputs, leaving only minor gaps in coverage.	4 / 5
Completeness	It explicitly states what the skill does ('converting, repairing, or packaging ... into Agentlas architecture') and gives an explicit 'Use when ...' clause listing concrete trigger scenarios, satisfying both what and when.	5 / 5
Trigger Term Quality	It includes 'Use when' with relevant triggers (packaging, converting, repairing an agent/team), but relies on the niche term 'Agentlas' and omits common synonyms like 'agent', 'skill', 'plugin', or file extensions users would naturally say.	3 / 5
Distinctiveness Conflict Risk	The narrow domain (packaging into the Agentlas architecture with five named delivery targets) forms a clear niche unlikely to trigger for unrelated skills; conflict risk is minimal.	5 / 5
	Total	17 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: agentlas-ai/Agentlas-OS
Path: skills/agentlas-packaging/SKILL.md
Commit: a7988bb

Reviewed: 4 days 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.