gog-forms

Google Forms operations through gog.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/gog-forms/SKILL.md

Quality

Content

80%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.

A tight, command-first reference that assumes competence and defers syntax discovery to `--help` and `gog schema` — excellent token efficiency and structure. Its main gap is operational safety depth: destructive commands lack an explicit post-write verification step or error-recovery loop, capping workflow clarity.

Suggestions

Add a post-write verification step (e.g., re-run `gog forms get` after `update` or `delete-question` to confirm the mutation landed) to create a real feedback loop for destructive operations.

Include one short worked example of a common case (e.g., `gog forms create --title ...` then `add-question`) so the most frequent operations need no extra discovery round-trip.

Briefly state what to do when a `--dry-run` or write fails (inspect the error, fix the flag/object, retry) to round out the workflow.

Dimension	Reasoning	Score
Conciseness	The body is ~45 lean lines with zero concept explanations (it never explains what Google Forms is), delegating flags to `--help`. Every command and bullet earns its place, matching "Lean and efficient; assumes Claude's competence".	5 / 5
Actionability	The "Safe start" block gives copy-paste-ready commands (e.g., `gog auth list --check --json --no-input`) and the command table plus "Run `gog forms <command> --help`" is executable guidance. It is not a 5 because common cases like `create` or `add-question` get only a one-line table purpose with no worked example; not a 3 because what is given is fully executable, not pseudocode.	4 / 5
Workflow Clarity	A sequence exists (read parent skill → auth check → `--readonly`/`--dry-run` → "Confirm the exact account, object, and mutation before any write or delete"), but despite destructive commands (`delete-question`, `publish`) there is no post-write validation or fix-and-retry feedback loop, so the destructive-operation cap applies. It is not a 2 because pre-write checkpoints (`--dry-run`, explicit confirmation) are clearly present.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no bundle files, well-organized sections ("Safe start", "Commands"), a single clearly-signaled one-level reference ("Read `../gog/SKILL.md` first"), and defers detail to runtime `--help`/`gog schema` rather than inlining it — matching the simple-skill exception for a 5.	5 / 5
	Total	17 / 20 Passed

Description

48%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 admirably concise and names a specific domain and tool, but it is skeletal: no concrete operations, no trigger terms beyond the product name, and no "Use when..." guidance. It reads as a generated stub rather than a self-contained trigger description.

Suggestions

Add a "Use when..." clause (e.g., "Use when creating or editing Google Forms, adding questions, or reading form responses") to raise completeness.

List 2-3 concrete operations (create forms, add/move questions, publish, fetch responses) so the "what" is more than a domain label.

Include natural user synonyms such as "survey" and "quiz" alongside "Google Forms" to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	"Google Forms operations" names the domain but lists no concrete actions (no create, publish, or response-reading mentioned), matching the anchor "Names the domain but actions are minimal or generic". It is not a 3 because not even 1-2 concrete actions are stated.	2 / 5
Completeness	The description has a clear "what" ("Google Forms operations through gog") but no "when"/"Use when..." clause, which per the judging guidelines caps completeness at 3. It is not a 2 because the "what" is clearly stated, and not a 4 because there is no "when" at all.	3 / 5
Trigger Term Quality	"Google Forms" is a natural term users would say, but it is the only one; "gog" is tool jargon and common variations like "survey", "quiz", or "form responses" are missing, matching "Some relevant keywords but missing common variations or synonyms". It falls below anchor 4's "Good keyword coverage; a few natural terms missing".	3 / 5
Distinctiveness Conflict Risk	"Google Forms operations through gog" carves a specific Google-product niche with the tool named, so overlap risk is minor — mostly with sibling gog skills or generic "form" requests. It is not a 5 because there are no distinct trigger phrases to fully disambiguate from related skills.	4 / 5
	Total	12 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: openclaw/gogcli
Path: .agents/skills/gog-forms/SKILL.md
Commit: 414e2ff

Reviewed: 3 days ago

Table of Contents

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.