team-builder-packaging

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

Quality

73%

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 ./.agents/skills/team-builder-packaging/SKILL.md

Quality

Content

62%

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 clear, well-sequenced procedure with concrete file/command references and an explicit verification feedback loop. It loses points for inline tutorial-style explanation in step 9b, incomplete specification of several abstract steps, and the absence of any progressive-disclosure bundle.

Suggestions

Move the runtime-mechanics rationale in step 9b (legacy spellings, derivation behavior) into a separate reference doc and keep only the 'write both keys' directive inline.

Expand the abstract steps ('Encode handoff and return contracts', 'Add PM Soul') with a minimal concrete artifact template or named file so the guidance is copy-paste ready.

Create referenced bundle files (e.g. docs/verify-team-package.md) and link them from the relevant steps so detail lives one level deep.

Dimension	Reasoning	Score
Conciseness	The body is largely procedural with concrete paths and a compact JSON example, but step 9b explains runtime behavior, legacy alternate spellings, and derivation rules that pad the skill with context Claude does not strictly need — matching the 'mostly efficient but could be tightened' anchor; not 3 because of that explanatory prose, not 1 because it avoids concept primers.	2 / 3
Actionability	Concrete artifacts are present (specific docs/scripts paths, an executable manifest.json example, the `scripts/verify-team-package.sh <package-root>` command, and a named output set), but several steps remain abstract directives such as 'Add PM Soul' and 'Encode handoff and return contracts' without specifying the actual artifact contents — matching the 'some concrete guidance but incomplete' anchor; not 3 because key details for several steps are missing.	2 / 3
Workflow Clarity	A clearly numbered 1–11 sequence is paired with an explicit validation checkpoint ('Run scripts/verify-team-package.sh ... If it fails, do not hand off a result; correct the package ...') providing a feedback loop, matching the 'clear sequence with explicit validation steps' anchor; not 2 because validation and recovery are explicit, not implicit.	3 / 3
Progressive Disclosure	No references/, scripts/, or assets/ bundle exists, so there is no actual bundle structure to navigate; the SKILL.md is a single monolithic procedure with the manifest explanation inlined rather than split into a separate file, matching the 'some structure but content that should be separate is inline' anchor; not 3 because there are no one-level-deep signaled references to follow.	2 / 3
	Total	9 / 12 Passed

Description

85%

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, complete, and distinctive with an explicit 'Use when' trigger and a rich enumeration of team-package components. Its main weakness is trigger-term quality: the role names are internal jargon rather than the phrasings users would naturally invoke.

Suggestions

Add natural-language trigger variants users would actually say, e.g. 'Use when building, packaging, or auditing an agent team / multi-agent team package'.

Avoid front-loading internal role names (PM Soul, Policy Gate) in the trigger; surface one or two user-facing terms instead.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete components — 'orchestrator, PM Soul, Memory Curator, Policy Gate, workers, eval, QA, handoffs, and runtime adapters' — which matches the anchor listing multiple specific concrete actions; it is above 2 because the actions are comprehensive rather than partial.	3 / 3
Completeness	It states both what it does ('generating or auditing a multi-role agent team package') and an explicit 'Use when ...' trigger, satisfying the anchor for clearly answering both what AND when with explicit triggers; not below 3 because the trigger is explicit.	3 / 3
Trigger Term Quality	'Use when generating or auditing a multi-role agent team package' includes some relevant keywords but leans on internal jargon (PM Soul, Policy Gate, runtime adapters) that a user would rarely say verbatim, missing common variations like 'build a team' or 'package an agent team' — closest to the anchor with some relevant keywords but missing variations; not 3 because the natural term coverage is thin.	2 / 3
Distinctiveness Conflict Risk	The niche — packaging a multi-role agent team with named roles — is highly specific and unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor; not 2 because it does not broadly overlap with other skill domains.	3 / 3
	Total	11 / 12 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: .agents/skills/team-builder-packaging/SKILL.md
Commit: 2eb39ad

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.