CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

team-agent-orchestration

Run team-based orchestration for agent squads: work items with owners and scope, agent Kanban state, branch isolation, control pane visibility, and merge gates. Use when coordinating multiple agents in parallel across branches or worktrees — multi-agent fan-out, agent Kanban, squad coordination, or merging agent output into one product.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured, efficient instruction skill: concrete card schema and Kanban criteria make the operating model actionable, and the failure-modes section adds genuine value. Weaknesses are mild — a redundant opening paragraph, high-level execution-mode steps without commands, and validation expressed as criteria rather than explicit feedback loops.

Suggestions

Drop or compress the opening paragraph that repeats the frontmatter description, and let the body start at 'When To Activate'.

Add one worked example of a single orchestration pass (board shaping through merge) to make the high-level flow steps concrete.

Make validation feedback loops explicit, e.g., 'if the merge gate fails, return the card to Blocked with the failing check recorded' rather than stating gates only as exit criteria.

DimensionReasoningScore

Conciseness

The body is list- and table-driven with no explanations of concepts Claude already knows, but the opening paragraph restates the frontmatter description almost verbatim, and phrases like "Merge readiness by gate, not vibes" could be tightened — efficient with minor trim opportunities rather than fully lean.

4 / 5

Actionability

Concrete artifacts are provided — a copy-paste JSON card schema, a Kanban table with per-column exit criteria, and a named failure-mode checklist — but the flow steps remain high-level ("Shape the board", "Pick execution mode") without specific commands or a worked example, leaving minor gaps for an otherwise actionable instruction skill.

4 / 5

Workflow Clarity

The 7-step orchestration flow is clearly sequenced with an explicit review order ("tests first, then diff review, then security/risk checks, then content/product polish") and merge gates with exit criteria, but validation is expressed as criteria rather than explicit validate-fix-retry commands, leaving minor checkpoint gaps.

4 / 5

Progressive Disclosure

Self-contained ~100-line body with well-organized, clearly headed sections and no nested or buried references; it is slightly over the size where inline-only structure would earn top marks, and sections like the card schema or control-pane requirements could arguably live in reference files.

4 / 5

Total

16

/

20

Passed

Description

83%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 strong description: third-person, concise, with an explicit 'Use when' clause and concrete natural-language triggers that clearly delimit a niche. The main gap is that capabilities are named as feature nouns rather than specific actions, and a few common trigger synonyms are absent.

Suggestions

Phrase the capability list with concrete action verbs (e.g., 'assign work items with owners and merge gates', 'track agent state on a Kanban board') rather than feature nouns.

Add a few missing natural trigger variations users would say, such as 'agent team', 'parallelize agents', or 'merge agent output'.

DimensionReasoningScore

Specificity

"work items with owners and scope, agent Kanban state, branch isolation, control pane visibility, and merge gates" enumerates several concrete capabilities in a clearly named domain ("Run team-based orchestration for agent squads"), though the items are feature nouns rather than the comprehensive action-verb list of the top anchor.

4 / 5

Completeness

It explicitly answers both questions: the "what" is the enumerated orchestration capabilities, and an explicit "Use when coordinating multiple agents in parallel across branches or worktrees" clause with concrete trigger phrases answers the "when".

5 / 5

Trigger Term Quality

"multi-agent fan-out, agent Kanban, squad coordination, or merging agent output into one product" plus "branches or worktrees" gives good natural-phrase coverage a user would actually say, though common variations like "agent team" or "parallelize agents" are missing.

4 / 5

Distinctiveness Conflict Risk

Distinct niche triggers ("agent Kanban", "squad coordination", "multi-agent fan-out", "worktrees") separate it from generic skills, but it could mildly overlap with general multi-agent or workflow-orchestration skills.

4 / 5

Total

17

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

affaan-m/ECC

Path

skills/team-agent-orchestration/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.