CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

team-builder-packaging

Use when generating or auditing a multi-role agent team package with orchestrator, workers, handoffs, Memory Ticket outputs, and runtime adapters (PM Soul, Memory Curator, Policy Gate, eval and QA are OS-resident).

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/team-builder-packaging/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 compact, well-sequenced procedure with a genuine end-of-work validation loop and appropriately self-contained structure. Its main gap is actionability: several core steps (handoff/return contracts, runtime adapters, the interview-research contract) point at artifacts without giving their shape, forcing the reader to guess.

Suggestions

Add a minimal template or example for the handoff and return contracts in step 8, since 'Encode handoff and return contracts' currently gives no structure to follow.

Specify what 'Emit runtime adapters and package verification' (step 10) concretely produces — file names, format, or a short example — matching the specificity already present for manifest.json.

Clarify what 'contracts/builder-interview-research-gate.md' contains or inline its essential rules, so step 2 is executable without an unavailable external file.

DimensionReasoningScore

Conciseness

The body is imperative and lean with no explanations of concepts Claude already knows; only step 9b's prose about older key spellings and the 'entry' caveat could be tightened, so it sits between anchors 3 and 4, noticeably above the midpoint.

4 / 5

Actionability

Concrete elements exist (the 'scripts/verify-team-package.sh <package-root>' command, the manifest entrypoints/roster JSON snippet, and explicit doc file paths), but key steps like 'Encode handoff and return contracts' and 'Emit runtime adapters and package verification' give no template, example, or file shape, leaving executable guidance incomplete.

3 / 5

Workflow Clarity

A clear numbered sequence ends with an explicit validation gate and feedback loop ('If it fails, do not hand off a result; correct the package...'), but validation exists only at the end, correction guidance is high-level, and the awkward 9b numbering signals minor drift.

4 / 5

Progressive Disclosure

The skill is a ~50-line self-contained body with well-organized Procedure and Output sections and no bundle files; paths it references (docs/, contracts/, scripts/) belong to the generated package, not this bundle, so per the simple-skill guideline well-organized sections alone earn the top score.

5 / 5

Total

16

/

20

Passed

Description

71%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 specific, distinctive description with an explicit trigger clause that clearly separates it from generic skills. Its main weaknesses are the fused what/when structure, missing natural synonyms for the action verbs, and an internal-jargon parenthetical that adds no trigger value.

Suggestions

State the what separately from the when, e.g. 'Generates and audits multi-role agent team packages... Use when building, creating, or reviewing an agent team, multi-agent crew, or orchestrator/worker roster.'

Add natural trigger synonyms users would actually say ('build', 'create', 'review', 'multi-agent') to broaden keyword coverage.

Trim or relocate the '(PM Soul, Memory Curator, Policy Gate, eval and QA are OS-resident)' parenthetical, which is internal jargon that neither describes a capability nor serves as a trigger.

DimensionReasoningScore

Specificity

Names the domain ('multi-role agent team package') and enumerates concrete components ('orchestrator, workers, handoffs, Memory Ticket outputs, and runtime adapters'), but only two action verbs ('generating or auditing') are explicitly stated, leaving minor gaps in coverage.

4 / 5

Completeness

An explicit 'Use when generating or auditing...' trigger is present, and the what is recoverable from the same clause, but the what is fused into the when rather than separately stated with concrete trigger phrases, so it falls short of the anchor 5 example.

4 / 5

Trigger Term Quality

'agent team', 'orchestrator', 'workers', 'handoffs', 'generating', 'auditing' are relevant keywords, but common natural variations ('build', 'create', 'multi-agent', 'crew') are missing and the parenthetical ('PM Soul, Memory Curator, Policy Gate, eval and QA are OS-resident') is internal jargon no user would say.

3 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche (multi-role agent team packaging with Memory Ticket outputs and runtime adapters) with distinctive trigger terms; minimal risk of firing for an unrelated skill.

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 possibly missing (scripts/verify-team-package.sh)

Warning

Total

15

/

16

Passed

Repository

agentlas-ai/Agentlas-OS

Path

skills/team-builder-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.