CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

envelope-team

Design and generate .envelope.json AI agent team definitions — the open standard for multi-agent teams with hierarchy, access policies, human-in-the-loop gates, and cron schedules.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/envelope-team/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 strong, schema-focused body: a complete worked example, precise field reference, and a validation command make it immediately actionable, while it stays lean by teaching only the Envelope standard Claude would not know. Sequence and validation are both present, though not woven into a single ordered procedure with a feedback loop. The main structural refinement would be splitting the schema reference into a bundle file as the skill grows.

DimensionReasoningScore

Conciseness

The body is dense with Envelope-specific knowledge Claude cannot know (field tables, model assignments, the hierarchy rule) and explains no general concepts. Minor over-explanation remains: 'What This Skill Does' restates the frontmatter description and the two usage sections overlap the worked example, keeping it below the lean anchor 5.

4 / 5

Actionability

Fully executable throughout: a complete copy-paste-ready example JSON, exact field tables with required flags, concrete accessPolicy and gates snippets, specific model IDs, and the runnable command 'npx @openenvelope/schema validate ./team.envelope.json'. The common cases (basic team, gated team, restricted access) are covered with real code, matching anchor 5.

5 / 5

Workflow Clarity

'What This Skill Does' sequences the process (takes description, designs hierarchy, generates schema-valid file) and Tips supplies an explicit pre-deploy validation command. Below anchor 5 because validation is not embedded as a numbered step with an error-recovery loop; above anchor 3 because the checkpoint is explicit with a concrete command rather than implicit.

4 / 5

Progressive Disclosure

Clean section structure (When to Use, How to Use, Example, Schema Reference, Tips, Links) with no nested references and everything needed inline for a bundle-free skill. Not anchor 5: at roughly 170 lines the Schema Reference tables are bulk reference material that could sit in a one-level-deep reference file, so the under-50-line exception does not apply.

4 / 5

Total

17

/

20

Passed

Description

66%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 specific, distinctive description that clearly states what the skill produces, anchored by the niche .envelope.json standard. Its main weakness is the absence of any 'Use when...' trigger clause, which caps completeness at 3 and leaves a few natural trigger terms uncovered. Adding explicit when-guidance would move it from good to excellent.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to build, design, or generate an Envelope team or create a .envelope.json file.'

Include natural user verbs and synonyms ('build', 'create', 'agent team', 'multi-agent workflow') so trigger-term coverage reaches the anchor-5 bar.

Optionally state when not to use it (e.g. general agent orchestration outside the Envelope standard) to sharpen distinctiveness.

DimensionReasoningScore

Specificity

'Design and generate .envelope.json AI agent team definitions' names two concrete actions on a specific artifact, and the trailing clause enumerates feature areas ('hierarchy, access policies, human-in-the-loop gates, and cron schedules'). Above anchor 3 because coverage extends beyond 1-2 bare actions into the feature set; below anchor 5 because only two verbs describe what Claude actually does.

4 / 5

Completeness

The 'what' is explicit and concrete ('Design and generate .envelope.json AI agent team definitions'), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Anchor 4 is unreachable without explicit when-guidance, while anchor 2 does not fit because the what is clear.

3 / 5

Trigger Term Quality

Natural phrases a user would actually say are present: 'AI agent team', 'multi-agent teams', '.envelope.json', 'human-in-the-loop'. Not anchor 5 because common user verbs like 'build' or 'create' and synonyms like 'agent workflow' are missing; well above anchor 3 because multiple specific domain keywords appear.

4 / 5

Distinctiveness Conflict Risk

'the open standard for multi-agent teams' and the '.envelope.json' format carve a distinct niche with minimal conflict risk for anyone mentioning the format. Not anchor 5 because 'multi-agent teams' alone overlaps generic agent-orchestration skills and no trigger clause sharpens the boundary; clearly above anchor 3's broad-overlap example.

4 / 5

Total

15

/

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

davepoon/buildwithclaude

Path

plugins/all-skills/skills/envelope-team/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.