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

80%

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 ./claude/plugins/agentlas-core-engine-meta-agent/runtime-support/skills/team-builder-packaging/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 tight, executable procedure with concrete file paths, a manifest example, and a genuine validation feedback loop gating completion. Its only notable weakness is that the verify script and interview/research contract it instructs the agent to run are not shipped in the bundle, which slightly undermines both actionability and navigation.

DimensionReasoningScore

Conciseness

The body is lean and procedural with terse steps, and the longer step 9b earns its length by documenting non-obvious runtime gotchas (older key spellings, 'entry' being the package entrypoint not the team manager). It is not a 5 because a few explanatory sentences ('a package that omits it is published, charged for as a team, and can never be called') could be tightened.

4 / 5

Actionability

The guidance is mostly executable: concrete file paths, a copy-ready manifest.json snippet, a concrete verify command ('scripts/verify-team-package.sh <package-root>'), and an explicit output field list. It stops short of 5 because the referenced resources (scripts/verify-team-package.sh, contracts/builder-interview-research-gate.md) are not present in any bundle directory, leaving a gap between instruction and available tooling.

4 / 5

Workflow Clarity

The procedure is a clearly numbered sequence with an explicit validation gate and feedback loop: 'Run scripts/verify-team-package.sh ... If it fails, do not hand off a result; correct the package by adding an orchestrator/HQ ... or by collapsing it to a valid single-agent package.' This matches the level-5 anchor of clear sequencing with explicit validation and error-recovery guidance.

5 / 5

Progressive Disclosure

At under 50 lines with clean Procedure/Output sections the body is well organized and appropriately sized for a single SKILL.md. It is not a 5 because it references bundle-style paths (contracts/builder-interview-research-gate.md, scripts/verify-team-package.sh) that do not exist in the bundle, and the '9b' sub-numbering slightly muddies navigation.

4 / 5

Total

17

/

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.

The description is specific and highly distinctive for a niche packaging task, with an explicit 'Use when' trigger. Its main weaknesses are fused what/when phrasing and trigger vocabulary dominated by internal jargon (PM Soul, OS-resident) rather than natural user phrases, which limits when users would organically invoke it.

Suggestions

Add natural trigger phrases users would actually say, such as 'multi-agent team', 'build an agent roster', or 'team package', alongside the existing jargon terms.

Separate the capability statement from the trigger: lead with what the skill does ('Packages a multi-role agent team with orchestrator, workers, and handoff contracts'), then the 'Use when...' clause.

Move internal jargon like 'PM Soul' and 'OS-resident' out of the trigger sentence or gloss it briefly so the description stays scannable for outsiders.

DimensionReasoningScore

Specificity

The description names two concrete actions ("generating or auditing") and a list of specific package artifacts ("orchestrator, workers, handoffs, Memory Ticket outputs, and runtime adapters"), giving several specific elements with minor gaps. It is not a 5 because the action coverage is thin (only two verbs) and much of the specificity comes from internal jargon rather than comprehensive concrete capabilities.

4 / 5

Completeness

An explicit "Use when" clause is present and the what is stated (generating/auditing multi-role agent team packages with named components), so both what and when are answered. It falls short of 5 because the what and when are fused into a single trigger sentence with no separate capability statement, and the when could be more explicit about concrete triggering scenarios.

4 / 5

Trigger Term Quality

Some relevant keywords are present ("agent team", "orchestrator", "handoffs", "auditing") but common natural variations like "multi-agent", "build a team", or "team package" are missing, and terms like "PM Soul", "Memory Curator", and "OS-resident" are internal jargon a user would never say. It fits the 'some relevant keywords but missing common variations' anchor rather than the level-4 'good keyword coverage' anchor.

3 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche with highly specific artifact names ("Memory Ticket outputs", "PM Soul", "Policy Gate", "runtime adapters") that no other skill would share, so conflict risk is minimal. Anti-drift check: the level-4 anchor ('minor overlap risk with closely related skills') is a worse fit than the level-5 'clear niche with distinct triggers' anchor.

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

claude/plugins/agentlas-core-engine-meta-agent/runtime-support/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.