CtrlK
BlogDocsLog inGet started
Tessl Logo
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

80%

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

Fix and improve this skill with Tessl

tessl review fix ./skills-seed/admin/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 actionable operational guide with exact endpoints, response shapes, and error-handling paths, and a well-validated destructive-workflow sequence (offboarding). Its costs are length-driven: repeated rules across sections and a monolithic single-file structure with no reference files despite several self-contained sub-topics.

Suggestions

State the portal-only rule once (e.g., in "Admin grants") and reference it elsewhere instead of restating it in "Admin API limits", "External users", and "Failure modes".

Move the Slack installation guide and the connector-source checks into reference files (e.g., references/slack-installation.md, references/connector-sources.md) and keep one-line pointers in SKILL.md so the main file stays an overview.

Convert the Slack-installation and connector sections' conditional prose (configured/managed/invalid_environment/installAvailable branches) into explicit decision steps or a short checklist to match the sequencing quality of the offboarding workflow.

DimensionReasoningScore

Conciseness

The body is dense with deployment-specific operational facts and never explains concepts Claude already knows, but it is noticeably repetitive — the portal-only grant rule appears in four places ("Admin API limits", "External users", "Admin grants", "Failure modes") and the DM/Open audience requirement is restated across "Admin API limits" and "Scheduling admin-reading work" — fitting anchor 3's "mostly efficient but could be tightened".

3 / 5

Actionability

Guidance is fully executable: a copy-paste curl shape ("curl -fsS -H "x-agent-capability: $AGENT_API_TOKEN" "$AGENT_API_URL/v1/admin/…""), concrete endpoints with expected response fields ("a serviceCredentials entry with enabled: true, hasSecret: true, delivery: "env"…", "setup.tokenUrl, setup.submitUrl, and setup.installUrl"), and verbatim 403/409 error strings with per-error handling — matching anchor 5.

5 / 5

Workflow Clarity

The destructive offboarding workflow has explicit validation (preview without apply, show the admin and get a yes, apply, then review leftovers, with safe re-runs) and the global "confirm before any mutation / report afterwards" rule plus GET-first-then-PUT act as checkpoints, matching anchor 4 rather than 5 only because the Slack-installation and connector sections present conditional logic as dense prose instead of sequenced steps.

4 / 5

Progressive Disclosure

Section headers are clear and consistent, but this is a ~330-line single file with no bundle files at all; self-contained topics like the Slack installation guide and connector-source checks are inlined where separate reference files would keep SKILL.md an overview — anchor 3's "some structure but content that should be separate is inline".

3 / 5

Total

15

/

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 highly distinct, explicitly triggered description that clearly answers both what the skill does and when to use it. Its main weaknesses are second-person phrasing ("accepts your token when the user you're talking to") and action verbs that stay generic ("inspect or change") while the concrete specificity lives in a long parenthetical noun list.

Suggestions

Rewrite in third person to remove the second-person constructions ("accepts your token when the user you're talking to") — e.g., "Accepts the agent's token when the requesting user is an org admin…" — which also removes the rubric's specificity penalty.

Convert the parenthetical resource list into distinct concrete actions (e.g., "list scopes, read and update any scope's config/SOUL/memory, review transcripts and captured prompts, manage the user roster and external users, pull audit/error/egress logs") so the actions, not just the nouns, are specific.

Add a few natural synonym triggers such as "administrator", "organization-wide", or "user management" to broaden keyword coverage.

DimensionReasoningScore

Specificity

The description enumerates many concrete coverage areas ("scope directory, per-scope config & SOUL, any scope's memory, transcripts & captured prompts, files, user roster & external users, audit/errors/egress") but the actions themselves are only "Act for" / "inspect or change", matching anchor 4 rather than 5; the rubric's 1-point penalty for second-person voice ("accepts your token when the user you're talking to") reduces it to 3.

3 / 5

Completeness

Both parts are explicit: the "what" ("Act for an org admin — the admin API (scope directory, … audit/errors/egress)") and a concrete "Use when…" clause ("when an admin asks you to inspect or change anything org-wide or in another scope, or anyone asks whether they're an admin"), matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Natural terms like "org admin", "org-wide", "roster", "audit", and "whether they're an admin" are present and would be said by real users, but common synonyms ("administrator", "organization-wide", "user management") are missing — anchor 4, not the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (org-admin API operations) with distinct triggers tied to admin status and org-wide/cross-scope requests, so it is unlikely to fire for the wrong skill — matching anchor 5's "clear niche with distinct triggers; minimal conflict risk".

5 / 5

Total

17

/

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

relative_links

Relative link issues: 2 possibly missing (installUrl, setup.submitUrl)

Warning

Total

15

/

16

Passed

Repository

yc-software/qm

Path

skills-seed/admin/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.