Tessl • The management layer for AI agent skills

SkillPublic

admin

Act for an org admin — the admin API (scope directory, per-scope config & SOUL, any scope's memory, transcripts & captured prompts, files, user roster & external users, audit/errors/egress) accepts your token when the user you're talking to is an org admin and started this turn themselves. Use when an admin asks you to inspect or change anything org-wide or in another scope, or anyone asks whether they're an admin.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%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.

An exceptionally dense and actionable operational guide: exact commands, request/response shapes, validation checkpoints before every mutation, and an explicit error-recovery section. Its one structural weakness is that everything lives in SKILL.md itself — the onboarding-specific flows would benefit from being split into one-level-deep reference files.

Suggestions

Move the connector-source check and the Slack installation guide into reference files (e.g., references/connectors.md, references/slack-install.md) and keep short summaries with clear links in SKILL.md, so onboarding detail loads only when needed.

Add a brief table-of-contents or scope note at the top so the admin API reference and the onboarding checks are discoverable separately.

Tighten the prose in the Slack and connector sections — several multi-sentence paragraphs (e.g., the checklist rendering rules) can be compressed to bullet rules without losing constraints.

Dimension	Reasoning	Score
Conciseness	Nearly every sentence carries non-obvious operational detail (routes, grant rules, literal error strings) with no padding about concepts Claude already knows, but the Slack-installation and connector-source sections run as long prose that could be tightened. Efficient with minor instances of over-explanation, not the lean top anchor.	4 / 5
Actionability	Fully executable guidance throughout: a copy-paste curl shape ("curl -fsS -H 'x-agent-capability: $AGENT_API_TOKEN' \"$AGENT_API_URL/v1/admin/...\""), exact routes with expected response shapes (e.g., "GET /v1/admin/whoami → {\"isAdmin\":true,...}"), concrete JSON bodies ("POST /v1/admin/external-users {\"email\":\"ana@partner.com\",\"expiresAt\":\"2026-12-31\"}"), and literal 403/409 error strings with per-error handling.	5 / 5
Workflow Clarity	Destructive and batch operations are explicitly guarded ("confirm before any mutation", "GET first, then PUT the corrected value", "report afterwards exactly what changed", "Confirm with the admin before inviting or revoking"), the cron-grant flow is a numbered 5-step sequence ending in a verification step, and the "Failure modes" section provides error-recovery feedback loops — so the destructive-op cap does not apply.	5 / 5
Progressive Disclosure	The body has clear section headers and a working internal anchor link, but the entire ~280-line guide is inline with no bundle files at all; the Slack-installation (~50 lines) and connector-source (~40 lines) onboarding flows clearly belong in one-level-deep reference files. This matches anchor 3 (good structure, but content that should be separate is inline) rather than anchor 4, where most content is appropriately split across files.	3 / 5
	Total	17 / 20 Passed

Description

82%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, information-dense description that explicitly covers both what the skill does and when to use it, with a well-enumerated capability list and distinctive triggers. Its main flaws are second-person voice and action verbs that stay at a generic "inspect or change" level rather than naming the concrete operations.

Suggestions

Rewrite in third person (e.g., "accepts the agent's token when the acting user is an org admin") to avoid the rubric's second-person specificity penalty.

Vary the action verbs beyond "inspect or change" — e.g., "govern per-scope config and SOUL, read any scope's memory and transcripts, invite and revoke external users, review audit/errors/egress".

Add one or two more natural user phrases as triggers, such as "am I an admin" or "promote/revoke an admin", to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete capability areas ("scope directory, per-scope config & SOUL, any scope's memory, transcripts & captured prompts, files, user roster & external users, audit/errors/egress") but the actual verbs stay generic ("inspect or change anything"), and it is written in second person ("accepts your token when the user you're talking to"), which the rubric penalizes by reducing specificity by 1 (base 4).	3 / 5
Completeness	It explicitly answers both "what" (act for an org admin via the enumerated admin API surface) and "when" ("Use when an admin asks you to inspect or change anything org-wide or in another scope, or anyone asks whether they're an admin") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good natural keywords — "org admin", "org-wide", "in another scope", "whether they're an admin" — that users would plausibly say, but a few natural variations (e.g., promote/revoke grants, audit log, inviting external collaborators) are missing, so it sits between anchors 3 and 5 without comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	A clear niche (the org-admin API plane with scope-level authorization rules) with distinct triggers ("org-wide", "in another scope", "whether they're an admin") and minimal overlap with adjacent skills; not the lower anchors, which describe generic multi-skill domains.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: yc-software/qm
Path: skills-seed/admin/SKILL.md
Revision: 88c380f

Reviewed: 7 days ago

Discovery Implementation Validation

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.

admin

Table of Contents

Is this your skill?