CtrlK
BlogDocsLog inGet started
Tessl Logo

x-team

Use when the user asks for parallel team-style execution of multiple features in one project — orchestrates a team lead + N dev workers, one feature per worktree, each gated on x-qa E2E tests, with blocker escalation to human via SendMessage. Hard requires `plugin.omc` (TeamCreate/SendMessage primitives) and `.x-skills/x-qa/profile.json` (E2E gate).

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced orchestration skill with concrete payloads and strong validation/feedback loops throughout its batch workflow. Its gaps are conciseness (verbose error quotations and policy clauses) and progressive disclosure (a broken gotchas.md link and orphaned bundle files).

Suggestions

Add the missing gotchas.md file or remove the two 'See gotchas.md' references so navigation has no dead-ends.

Link the orphaned references (auto-merge-policy, blocker-escalation, feature-branch-mapping) and scripts (feature-map-read/update, tests/smoke) from the relevant phases so all bundle files are discoverable.

Tighten the long block-quoted error messages and the 'Persist Lessons' parenthetical policy into shorter pointers to the x-shared docs.

DimensionReasoningScore

Conciseness

The body is mostly lean and operational with no concept padding, but long block-quoted error messages and dense memory-policy clauses (e.g. the 'Persist Lessons' parentheticals) could be tightened without losing meaning.

2 / 3

Actionability

Provides concrete, executable artifacts throughout — JSON payloads for TeamCreate/TaskCreate/TaskUpdate/SendMessage/TeamDelete, bash invocations with arguments, and precise detection commands like `jq -e '[.entry_points[].launch.uses_isolate_profile] | any'`.

3 / 3

Workflow Clarity

An explicit 8-phase sequence (Bootstrap → Decompose → TeamCreate → Provision → TaskCreate → Spawn → Monitor → Shutdown → Summary) with validation checkpoints — prerequisite refusal gates, worktree-failure abort, idempotence guard, and blocker feedback loops — and checklists for a complex batch process.

3 / 3

Progressive Disclosure

Core references (decomposition-rules, monitor-loop, worker-preamble) are well-signaled one level deep, but gotchas.md is referenced twice and does not exist, and three reference files plus several scripts are orphaned (never navigable from the body), so discovery is incomplete.

2 / 3

Total

10

/

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.

A specific, complete, and distinctive description with an explicit 'Use when' trigger and concrete capabilities. Its main weakness is trigger-term quality: the natural-language trigger is narrow and the bulk relies on technical jargon rather than the varied phrases a user would naturally say.

Suggestions

Broaden the trigger clause to cover natural user phrasings like 'run these features in parallel', 'split work across workers', or 'parallelize feature development'.

Move the prerequisite jargon (plugin.omc, profile.json path) to the body and keep the description focused on capabilities and when-to-use terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'orchestrates a team lead + N dev workers, one feature per worktree, each gated on x-qa E2E tests, with blocker escalation to human via SendMessage' — rather than vague language.

3 / 3

Completeness

Explicitly answers both what (orchestrates team lead + workers per worktree with E2E gating and blocker escalation) and when ('Use when the user asks for parallel team-style execution of multiple features').

3 / 3

Trigger Term Quality

The 'Use when the user asks for parallel team-style execution of multiple features in one project' clause is a natural trigger, but coverage of common phrasings is narrow and the rest is jargon-heavy (worktree, x-qa, SendMessage, plugin.omc) rather than natural user terms.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear, narrow niche (parallel multi-feature team orchestration with worktrees and E2E gating) with distinct triggers and hard prerequisites unlikely to collide with other skills.

3 / 3

Total

11

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
quangtran88/x-skills
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.