gog-chat

Google Chat operations through gog.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

87%

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

The body is a tight, highly actionable CLI wrapper with well-organized sections and a clean single-level reference, scoring well on conciseness, actionability, and progressive disclosure. Its main gap is workflow clarity: destructive operations lack an explicit validate-fix-retry feedback loop.

Suggestions

Add an explicit write/delete workflow with a validation checkpoint, e.g. run `gog schema chat <command> --json` to confirm the contract, use `--dry-run`, then execute and verify the result; on error, fix and retry.

Provide one concrete end-to-end example (e.g. sending a message) showing the safe-start → schema-check → execute → verify sequence.

Dimension	Reasoning	Score
Conciseness	The body is lean (~35 lines), assumes Claude's competence, explains no basic concepts, and uses a compact command table; every token earns its place. Not level 2 because there is no unnecessary explanation or padding to tighten.	3 / 3
Actionability	It provides concrete, executable commands (e.g. "gog auth list --check --json --no-input", "gog schema chat --json", "gog --readonly --account user@example.com chat --help") plus specific flag guidance and a command table; copy-paste ready. Not level 2 because guidance is complete and executable rather than pseudocode or abstract.	3 / 3
Workflow Clarity	A safe-start sequence and safety checkpoints exist ("--dry-run before supported writes", "Confirm the exact account, object, and mutation before any write or delete"), but there is no explicit error-recovery feedback loop (run, check, fix, retry) for destructive operations, so the rubric caps destructive-workflow clarity at 2. Not level 1 because steps and some checkpoints are present, not level 3 because validation feedback loops are missing.	2 / 3
Progressive Disclosure	The skill is under 50 lines with well-organized sections (Safe start, Commands) and a single clearly-signaled one-level reference ("Read `../gog/SKILL.md` first"); no nested references. Per the simple-skill note, this scores 3. Not level 2 because organization and signaling are clean.	3 / 3
	Total	11 / 12 Passed

Description

57%

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 concise and names a distinct, specific domain and tool, but it is generic about actions and provides no explicit trigger guidance. Adding concrete capabilities and a "Use when..." clause would raise completeness and trigger-term quality.

Suggestions

Enumerate concrete actions, e.g. "Send and read Google Chat messages, manage spaces, threads, and DMs through gog."

Add an explicit trigger clause such as "Use when the user asks to send, search, or manage Google Chat messages, spaces, or threads."

Include natural keyword variations (messages, spaces, threads, DMs) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Google Chat operations through gog" names a concrete domain (Google Chat) and a concrete tool (gog), but "operations" is generic and lists no specific actions (e.g. send messages, create spaces); not level 3 because no concrete actions are enumerated, not level 1 because the domain and tool are explicit rather than abstract.	2 / 3
Completeness	It states what the skill does (Google Chat operations through gog) but lacks any "Use when..." or equivalent trigger guidance, so per the rubric completeness is capped at 2; not level 1 because the "what" is present, not level 3 because the "when" is entirely missing.	2 / 3
Trigger Term Quality	"Google Chat" is a natural term users would say, but the description omits common variations such as messages, spaces, threads, or DMs; not level 3 due to thin coverage, not level 1 because a real natural keyword is present.	2 / 3
Distinctiveness Conflict Risk	"Google Chat" is a clear, narrow niche that is unlikely to trigger for unrelated skills; not level 2 because the domain is specific enough to avoid broad overlap with other skills.	3 / 3
	Total	9 / 12 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-chat/SKILL.md
Commit: 1dbd820

Reviewed: 1 day 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.