CtrlK
BlogDocsLog inGet started
Tessl Logo

google-docs

Connector-first Google Docs creation and editing in local Codex plugin sessions, with direct native create and batchUpdate workflows for simple docs, DOCX-first import for polished deliverables, target-document checks, smart chip and building-block reconstruction, connector-readback verification, and reference routing for formatting, citations, tables, and write-safety.

64

Quality

76%

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/google-drive/skills/google-docs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured, actionable, and exemplifies progressive disclosure with explicit workflows and validation checkpoints; its main weakness is verbosity from repeated guardrails and overlapping guidance sections.

Suggestions

Dedupe the recurring 'If a simple verified workflow is viable, use it. Do not drift into speculative alternate paths.' directive — state it once and reference it.

Consolidate overlapping framing in 'Capability Position' and 'Canonical Workflow Bias' with 'Default Routing' to remove redundancy.

Tighten the Release-Blocker Checklist by merging near-duplicate style-matching items to reduce token weight.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows and stays operational, but is padded with repeated guardrails — 'If a simple verified workflow is viable, use it. Do not drift into speculative alternate paths.' recurs three times — and overlapping sections (Capability Position, Canonical Workflow Bias) that could be tightened.

2 / 3

Actionability

Gives concrete, executable specifics inline — 'mcp__codex_apps__google_drive._create_file' with 'mime_type: "application/vnd.google-apps.document"', 'mcp__codex_apps__google_drive_import_document' with 'upload_mode: "native_google_docs"', 'write_control.requiredRevisionId', and chip element types 'dateElement', 'person', 'richLink' — and routes to named reference files.

3 / 3

Workflow Clarity

The Direct-Request Workflow is a clear 10-step sequence with explicit validation checkpoints (re-read after substantial writes, verify/normalize before handoff), plus a Release-Blocker Checklist and feedback loop ('If any check fails, the task is not complete.').

3 / 3

Progressive Disclosure

The SKILL.md is a routing overview pointing to 15 verified one-level-deep reference files, organized by a Task To Reference Map table with clearly signaled backtick paths; content is appropriately split out of the overview.

3 / 3

Total

11

/

12

Passed

Description

67%Weight 40%Scale 1-3

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 highly specific and distinct, but leans on internal terminology over natural user triggers and omits an explicit 'when to use' clause, leaving it without clear invocation guidance.

Suggestions

Append a 'Use when...' clause with natural triggers (e.g., 'Use when the user asks to create, edit, or import a Google Doc in a Codex local-plugin session').

Replace or supplement jargon like 'connector-readback verification' and 'building-block reconstruction' with plain terms a user would actually say ('verify the doc', 'recreate smart chips').

Add common phrasings such as 'make a Google Doc', 'Google Docs document', or 'Docs link' to broaden trigger coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'direct native create and batchUpdate workflows', 'DOCX-first import', 'smart chip and building-block reconstruction', 'connector-readback verification' — rather than vague language.

3 / 3

Completeness

Strongly answers 'what' with a detailed capability list, but offers no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

Contains 'Google Docs' and 'DOCX' but buries them under internal jargon ('Codex plugin sessions', 'connector-readback verification', 'batchUpdate workflows', 'building-block reconstruction') that users would not naturally say, and omits common variations like 'make a Google Doc'.

2 / 3

Distinctiveness Conflict Risk

The niche — Google Docs creation/editing inside Codex local-plugin sessions — is clearly scoped and unlikely to trigger for unrelated skills.

3 / 3

Total

10

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 suspicious

Warning

Total

15

/

16

Passed

Repository
openai/plugins
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.