CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

google-workspace

Read and act on the user's Gmail, Google Calendar, and Google Tasks through their own Google connection.

Quality

77%

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/google-workspace/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

The body is an operational, highly executable reference: exact commands and endpoints, explicit pagination and validation loops, and approval gates on all writes, with environment-specific details that justify nearly every token. Its only weaknesses are minor tightening opportunities and a dense Gmail section that could be offloaded to a reference file.

DimensionReasoningScore

Conciseness

Nearly every passage conveys environment-specific knowledge Claude cannot know (vault tokens, UTC sandbox clock, composio proxy routing, nextPageToken behavior, MIME mirror rules), fitting anchor 4's "efficient; minor instances of over-explanation" — e.g. the recurring-digest state detail and the styled-HTML rationale could be trimmed slightly. It does not reach 5 because a few passages elaborate beyond the directive itself.

4 / 5

Actionability

The body provides copy-paste-ready curl commands with exact endpoints, headers, and query parameters for Calendar, Tasks reads and writes, plus a concrete gmail.py subcommand surface (search/read/thread/draft/reply/update-draft/send-draft) covering the common cases, matching anchor 5.

5 / 5

Workflow Clarity

Sequences are explicit with validation checkpoints and feedback loops: timezone lookup before day-bounds computation, "keep fetching" on nextPageToken, thread-fetch before flagging a reply need with a failure fallback ("report the item as unverified"), read-back-and-verify of drafts for mojibake, and approval gates before every write, matching anchor 5.

5 / 5

Progressive Disclosure

Scored against the actual bundle: the single referenced path (scripts/gmail.py) exists and is clearly signaled one level deep, and sections (Connection, Gmail, Calendar reads, Tasks, Writes) are easy to navigate — anchor 4's "good structure; most content appropriately placed". It falls short of 5 because the ~50 lines of Gmail etiquette rules (digest state, bulk-mail demotion, body-file formatting) are inlined and could be split into a reference file.

4 / 5

Total

18

/

20

Passed

Description

57%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.

The description is clear, third-person, and highly distinct thanks to naming the exact Google products, but it is generic on actions ("act on") and entirely missing an explicit use-when trigger clause with natural synonyms like "email" or "schedule". It answers "what" well and "when" not at all.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions email, Gmail, their calendar or schedule, meetings, tasks, or to-do lists" to raise completeness.

Replace the generic "act on" with concrete actions such as "send and draft email, reply, manage labels, query and create calendar events, and manage tasks" to raise specificity.

Include natural synonyms ("email", "schedule", "to-dos") alongside the product names so the skill triggers for users who don't say "Gmail" or "Google Calendar" verbatim.

DimensionReasoningScore

Specificity

Names three concrete domains ("Gmail, Google Calendar, and Google Tasks") and one concrete action ("Read"), but "act on" is generic, matching anchor 3 (domain plus 1-2 concrete actions) rather than anchor 4's several specific actions.

3 / 5

Completeness

The "what" is clear ("Read and act on the user's Gmail, Google Calendar, and Google Tasks through their own Google connection") but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

"Gmail", "Google Calendar", and "Google Tasks" are natural product names users say, but common synonyms like "email", "schedule", "meetings", and "to-do list" are missing, fitting anchor 3 (relevant keywords missing common variations).

3 / 5

Distinctiveness Conflict Risk

Naming the three specific Google products carves a clear niche with distinct triggers and minimal overlap risk with other skills, matching anchor 5.

5 / 5

Total

14

/

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

yc-software/qm

Path

skills-seed/google-workspace/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.