CtrlK
BlogDocsLog inGet started
Tessl Logo

matrix-server-management

Use for standalone Matrix admin requests (register users, create rooms, manage membership, upload files). Also use when you need to send a file to the admin via Matrix media upload. Do NOT use for Worker/project creation — those handle Matrix operations internally.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 lean, high-signal skill body: environment specifics and genuinely non-obvious gotchas up front, with all curl detail appropriately delegated to a single well-organized reference file. The only minor improvement would be inlining one minimal register/room-creation example so the most common case needs no file hop.

DimensionReasoningScore

Conciseness

Every token is non-obvious operational knowledge Claude cannot be assumed to know: "Workers IGNORE messages without m.mentions", "trusted_private_chat only invites members", "Matrix accounts cannot be deleted via API", plus the env-var URL and user-ID format. No padding, no explaining what Matrix is. Not 4: there is nothing that could be trimmed without losing signal.

5 / 5

Actionability

Concrete, specific guidance — "POST /join", "m.mentions.user_ids with the full Matrix user ID (MSC3952)", the ${AGENTTEAMS_MATRIX_URL} base, and the user-ID format — with full executable curl examples one click away in references/api-reference.md (verified to contain complete register/room/message/upload commands). Not 5: the body itself contains no copy-paste-ready command, so the reader must hop to the reference even for the most common case; not 3: the guidance is precise and immediately actionable, far beyond high-level hints.

4 / 5

Workflow Clarity

A simple skill handled cleanly: the single routing rule ("Any Matrix API call → references/api-reference.md") is unambiguous, and the gotchas encode the required per-operation checkpoints — you MUST include m.mentions.user_ids, you must ensure each invited user accepts with POST /join, IDs must match exactly or failures are silent. Not 4: the validation-critical steps are explicitly stated rather than merely implied; the destructive/batch cap of 3 does not apply since these are non-destructive standalone API calls.

5 / 5

Progressive Disclosure

Textbook split: a ~17-line SKILL.md overview (env vars, gotchas) with all API detail correctly placed in references/api-reference.md, which exists, is one level deep, and is clearly signaled via the Operation Reference table. Not 4: navigation is unambiguous and nothing that belongs in a separate file is inlined.

5 / 5

Total

19

/

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 list, explicit 'Use for/when' triggers, and an explicit exclusion clause that separates it from sibling skills. The only weakness is a few missing natural synonyms (invite, homeserver) that keeps trigger-term coverage just short of comprehensive.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — "register users, create rooms, manage membership, upload files" plus the media-upload flow — matching the comprehensive-coverage anchor. Not 4: there is no minor gap; the actions enumerated map cleanly onto the skill's actual operations (as confirmed by the body's Operation Reference).

5 / 5

Completeness

Explicitly answers both: what ("register users, create rooms, manage membership, upload files") and when ("Use for standalone Matrix admin requests... Also use when you need to send a file to the admin via Matrix media upload"), with a concrete trigger phrase. It also adds an explicit negative trigger ("Do NOT use for Worker/project creation"), strengthening the 'when' beyond the anchor's bar. Not 4: the 'when' is already explicit and specific, not merely present-but-improvable.

5 / 5

Trigger Term Quality

Good natural keyword coverage — "register users", "create rooms", "manage membership", "upload files", "send a file", "Matrix media upload" — phrases users would naturally say. Not 5: it misses common synonyms a user might use, e.g. "invite users", "homeserver", or "Synapse", so a few natural trigger terms are absent. Not 3: coverage is well beyond the 'some relevant keywords' bar.

4 / 5

Distinctiveness Conflict Risk

Claims a clear niche — "standalone Matrix admin requests" — and explicitly disambiguates the closest conflict: "Do NOT use for Worker/project creation — those handle Matrix operations internally." That explicit boundary makes wrong-skill triggering unlikely. Not 4: overlap risk is not merely minor; it is proactively called out.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
agentscope-ai/AgentTeams
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.