create-teammate

Provision a production-ready teammate only after its stable responsibilities, prerequisites, and reusable operating guidance are understood.

Quality

63%

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 ./runtime/harnesses/src/embedded-skills/create-teammate/SKILL.md

Quality

Content

77%

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 well-structured, highly actionable orchestration guide with explicit decision gates and named tool calls, and it avoids explaining concepts Claude already knows. Its main weakness is redundancy across sections and the absence of any progressive-disclosure offloading of reference material.

Suggestions

Consolidate the repeated gating advice (Discovery Gate, Workflow steps 1-2, Teammate Quality Bar, Anti-Patterns) into one canonical section to reduce redundancy and tighten token use.

Move the detailed metadata-field and quality-bar reference material into a references/ file linked from SKILL.md to improve progressive disclosure.

Keep a concise canonical workflow in the body and point to the reference for the expanded rationale and anti-patterns.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's intelligence with no concept tutorials or padding, but the same ideas (don't create from a title, check stable remit, avoid overlap, verify prerequisites, don't ship a crippled setup) are restated across the Discovery Gate, Workflow, Quality Bar, and Anti-Patterns sections, which could be tightened.	2 / 3
Actionability	It names concrete tool calls ("teammates_create", "teammates_list", "teammate_skills_create") with exact metadata fields ("name", "instructions", "capability_profile.summary", "skill_markdown", "sidecar_files", "directories") and a worked example sequence, giving copy-ready actionable guidance for an instruction-only skill.	3 / 3
Workflow Clarity	The 8-step Workflow is clearly sequenced with explicit decision gates and checkpoints ("do not create the teammate yet", "stop and do not create" if not durable, prerequisite check before finalizing), plus feedback loops for the vague-remit case.	3 / 3
Progressive Disclosure	The body is well-organized into labeled sections, but at over 50 lines with no bundle files (references/, scripts/, assets/ absent) all content is inline with no one-level-deep references or navigation, matching the score-2 anchor where content that could be separate remains inline.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 conveys a clear single action and its preconditions in third person, but it lacks an explicit usage trigger and leans on process language rather than natural user phrasing. It is competent but stops short of the rubric's top anchors across all dimensions.

Suggestions

Add an explicit "Use when..." clause stating the natural trigger (e.g., "Use when the workspace needs a new teammate identity or specialist role").

Reframe "Provision a production-ready teammate" toward natural user phrasing like "Create and set up a new teammate" to improve trigger term quality.

List a couple of concrete sub-actions (e.g., create the teammate record, add teammate-local skills, verify prerequisites) to lift specificity toward the score-3 anchor.

Dimension	Reasoning	Score
Specificity	It names a concrete action ("Provision a production-ready teammate") and lists specific gating conditions ("stable responsibilities, prerequisites, and reusable operating guidance"), but describes a single action rather than multiple concrete actions like the score-3 anchor.	2 / 3
Completeness	It states what the skill does ("Provision a production-ready teammate") but has no explicit "Use when..." trigger clause; the "only after...are understood" is a precondition, not a usage trigger, capping completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	"teammate" is a relevant term, but the description uses process language ("Provision", "operating guidance", "prerequisites") rather than natural phrasing a user would say ("create/add a teammate"), and lacks common variations.	2 / 3
Distinctiveness Conflict Risk	The teammate-provisioning niche is reasonably specific, but without explicit triggers and with the abstract framing it could still overlap with related teammate-management skills, so it does not reach the clearly-distinct score-3 anchor.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: holaboss-ai/holaOS
Path: runtime/harnesses/src/embedded-skills/create-teammate/SKILL.md
Commit: f52b580

Reviewed: 6 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.