CtrlK
BlogDocsLog inGet started
Tessl Logo

teamskill-creator

Creates, converts, or modifies Teamskills — the multi-role extension of the Skills standard (specialized roles + workflow + bind constraints). Use when the user wants to author a multi-role agent team, convert a single-agent skill into one, or refactor an existing team. Do NOT use for single-agent Skills — use create-skill instead.

66

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 findings from the security scan

SKILL.md
Quality
Evals
Security

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 body is a well-sequenced, validation-rich authoring workflow with strong workflow clarity, but its progressive-disclosure design is undermined by missing bundle files and its actionability/conciseness slip because concrete examples and skeletons are pointed at files that do not exist and the community-search guidance is repeated.

Suggestions

Ship the missing `reference/` and `templates/` directories — the body links to pattern-selection.md, role-design.md, conversion-guide.md, compliance-checklist.md, community-search.md, and five templates, but none exist; these dead links break navigation and cap progressive_disclosure.

Inline at least one complete worked example (e.g., a full `roles/<id>.md` or a minimal end-to-end teamskill) directly in SKILL.md, since the concrete skeletons and examples are currently deferred to non-existent reference/template files.

Consolidate the post-generation community-enrichment section: the 'default recommend / generic≠covered' rule is restated in the anti-pattern box, the high-signal scenarios, and the decision rules — fold these into a single statement to tighten the body.

DimensionReasoningScore

Conciseness

Most content is novel spec detail that earns its place, but the post-generation community-enrichment section restates the 'recommend by default / generic≠covered' rule three times (anti-pattern box, high-signal scenarios, decision rules), so it is mostly efficient but could be tightened — not the lean 'every token earns its place' anchor.

2 / 3

Actionability

Inline guidance is concrete (named sections, naming rules, the runnable `python scripts/validate_teamskill.py` command, the MODIFY impact matrix), but the promised skeletons/examples are deferred to `templates/*.template` and `reference/role-design.md` files that do not exist, leaving key copy-paste details incomplete.

2 / 3

Workflow Clarity

A clear Stage 0–6 sequence across three modes with explicit validation checkpoints ('run until exit 0', 'Stage 6 is mandatory regardless of edit size'), feedback loops (validate→fix→re-run), and checklists (Stage 1b, common pitfalls, impact matrix), matching the explicit-validation-steps anchor.

3 / 3

Progressive Disclosure

The overview is well organized with clearly signaled one-level-deep references and a 'When to read' Files table, but scored against the actual bundle: the `reference/` and `templates/` directories are missing, so 10 of 11 referenced paths are dead links and navigation does not resolve — structure is present but non-functional, the anchor-2 case rather than the working anchor-3 case.

2 / 3

Total

9

/

12

Passed

Description

100%

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 a tight WHAT/WHEN/NOT triple that names concrete actions, gives explicit triggers, and explicitly excludes the single-agent case. It uses third-person/imperative voice consistent with the rubric's own good examples, with no fluff or synonym enumeration.

DimensionReasoningScore

Specificity

Lists three concrete actions — 'Creates, converts, or modifies Teamskills' — and specifies the artifact kind (specialized roles + workflow + bind constraints), matching the multi-action anchor rather than the vague or partial ones.

3 / 3

Completeness

Explicitly answers both what ('Creates, converts, or modifies Teamskills...') and when ('Use when the user wants to author...'), plus a NOT clause, satisfying the explicit-trigger anchor; not capped at 2 because the 'Use when' guidance is present.

3 / 3

Trigger Term Quality

The 'Use when' clause surfaces natural user phrasings — 'author a multi-role agent team', 'convert a single-agent skill into one', 'refactor an existing team' — covering the create/convert/modify variants a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The exclusion 'Do NOT use for single-agent Skills — use create-skill instead' carves a clear niche and actively prevents conflict with the sibling single-agent skill, fitting the distinct-triggers anchor.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 25 missing

Warning

Total

14

/

16

Passed

Repository
XiaoLuoLYG/GOD
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.