google-docs
Create and modify Google Docs documents. Read content, insert tables, apply heading styles, and manage formatting. Use when asked to edit a gdoc, write a Google document, update a doc, or format document content.
Install with Tessl CLI
npx tessl i github:odyssey4me/agent-skills --skill google-docs93
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 98%
↑ 4.08xAgent success when using this skill
Validation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that follows best practices. It uses third person voice, lists specific capabilities, includes a clear 'Use when...' clause with natural trigger terms including the colloquial 'gdoc', and is clearly distinguishable from other document-related skills by its Google Docs focus.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Read content, insert tables, apply heading styles, and manage formatting.' These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Create and modify Google Docs documents. Read content, insert tables, apply heading styles, and manage formatting') AND when ('Use when asked to edit a gdoc, write a Google document, update a doc, or format document content'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'gdoc', 'Google document', 'doc', 'format document content'. Good coverage of common variations including the informal 'gdoc'. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on Google Docs with distinct triggers like 'gdoc' and 'Google document'. Unlikely to conflict with generic document or other file type skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with executable commands and good progressive disclosure through external references. The main weaknesses are some verbosity in command documentation and missing validation checkpoints in multi-step workflows, particularly around destructive operations like content deletion.
Suggestions
Add explicit validation steps in workflows (e.g., 'Read document back to verify changes' after content modifications)
Consolidate redundant sections - 'Setup Verification' and 'check' command documentation overlap significantly
Add a validation step before destructive operations like content delete (e.g., 'First run documents read to identify correct indices')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy (e.g., repeating OAuth setup information, verbose command documentation with full example outputs). Some sections like 'Setup Verification' and 'check' command overlap significantly. | 2 / 3 |
Actionability | Provides fully executable bash commands with concrete examples, specific flags, and expected outputs. Commands are copy-paste ready with clear argument documentation. | 3 / 3 |
Workflow Clarity | Multi-step examples are provided but lack explicit validation checkpoints. The 'Create and populate a document' workflow doesn't verify success between steps. The warning about content delete indices is good but no validation step is provided before destructive operations. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections, external references for OAuth setup and API documentation are one level deep and clearly signaled. Quick start is concise with detailed command reference following. | 3 / 3 |
Total | 10 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.