CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

team-builder

Interactive picker that discovers available agent personas via the claude agents command and agents/ markdown globs, groups them into domains, has the user select up to five, dispatches them in parallel on one task, and synthesizes agreements and conflicts into a unified report. Use when composing a team of agents, browsing available agent personas, or running several specialist agents in parallel.

Quality

91%

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

88%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, highly actionable skill with a clear sequenced workflow and explicit error-handling checkpoints. Its two weak spots are modest redundancy (the flat-layout domain rule stated twice) and a monolithic single-file layout that could move examples and layout specs into reference files.

Suggestions

State the flat-layout prefix rule once (in Configuration or Step 1) instead of duplicating it in Prerequisites and Step 1, and keep only one directory-tree example.

Move the full example dialog (~34 lines) into references/example-session.md and link to it, keeping a short two-line excerpt inline.

Consider extracting the domain-grouping algorithm details (prefix qualification, General fallback) into a reference file so the main body reads as a lean workflow overview.

DimensionReasoningScore

Conciseness

The body is efficient with no explanations of concepts Claude already knows, but the flat-layout prefix rule ('A prefix counts as a domain when 2+ files share it... splits at the first `-`') is stated twice — in Prerequisites and again nearly verbatim in Step 1 — and both directory trees plus a full example dialog could be trimmed. Minor over-explanation, matching the 4 anchor rather than the lean 5.

4 / 5

Actionability

Fully executable guidance: exact command ('claude agents'), per-source parse rules, copy-paste user-facing prompts ('You selected N agents (max 5). Pick which to keep...'), and exact Agent tool parameters ('subagent_type: "general-purpose"', prompt template). Matches the copy-paste-ready 5 anchor.

5 / 5

Workflow Clarity

A clear 5-step sequence with explicit checkpoints and feedback loops: zero-agents abort with a verbatim message, >5-agent narrowing prompt, per-agent failure handling with inline note and continuation, and single-agent synthesis skip. Checkpoints are explicit, exceeding the 4 anchor.

5 / 5

Progressive Disclosure

Well-organized sections with clear headers and no nested references, but everything is inlined in a ~160-line file — the full example dialog and layout specifications are candidates for a references/ file. Good structure with minor organization gaps fits the 4 anchor; the 5 assumes content is appropriately split across files.

4 / 5

Total

18

/

20

Passed

Description

92%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: concrete action verbs throughout, an explicit and multi-phrase trigger clause, and a clearly distinct niche. The only weakness is mild — trigger coverage could add common synonyms like 'agent team' or 'multi-agent'.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'discovers available agent personas via the claude agents command and agents/ markdown globs', 'groups them into domains', 'has the user select up to five', 'dispatches them in parallel', and 'synthesizes agreements and conflicts' — giving comprehensive, concrete coverage rather than the minor-gaps profile of a 4.

5 / 5

Completeness

It explicitly answers both 'what' (full action pipeline from discovery to synthesized report) and 'when' with an explicit 'Use when composing a team of agents, browsing available agent personas, or running several specialist agents in parallel' clause containing concrete trigger phrases — a direct match for the 5 anchor.

5 / 5

Trigger Term Quality

Natural phrases like 'composing a team of agents', 'browsing available agent personas', and 'running several specialist agents in parallel' are present, but common synonyms users would say ('agent team', 'multi-agent', 'pick agents') are missing — good coverage, not comprehensive.

4 / 5

Distinctiveness Conflict Risk

The interactive team-picker niche is clearly distinct with dedicated triggers ('composing a team of agents', 'browsing available agent personas'); only slight overlap with generic parallel-subagent requests, fitting 'minimal conflict risk' better than the 4 anchor.

5 / 5

Total

19

/

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-builder/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.