gog-keep

Google Keep operations through gog.

Quality

74%

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-keep/SKILL.md

Quality

Content

86%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 a model of lean, command-first skill writing: safe-start commands, a tight command table, explicit safety rules for writes, and syntax delegated to --help/schema rather than guessed. The only meaningful gap is the absence of even one example invocation of a keep subcommand and any post-write verification step.

Suggestions

Add one concrete example per common operation, e.g. `gog --account user@example.com keep create --title "..." --json`, so agents have a copy-paste starting point.

Include a post-write verification step (re-run `gog keep get` or check the JSON output) to close the error-recovery loop for write/delete operations.

Clarify that `search` is client-side over `list` output (the table notes it, but a one-line note on when to use `search` vs `list` would remove ambiguity).

Dimension	Reasoning	Score
Conciseness	The ~40-line body contains no concept explanation and no padding: every line is a command, a flag rule, or a pointer ('Read `../gog/SKILL.md` first', 'Run `gog keep <command> --help`', 'Do not guess command syntax'). Matches 'Lean and efficient; every token earns its place'.	5 / 5
Actionability	The safe-start block gives three copy-paste-ready commands (`gog auth list --check --json --no-input`, `gog schema keep --json`, `gog --readonly --account user@example.com keep --help`) and the commands table is concrete, but no example invocation of an actual keep operation (create/search/delete) is shown — syntax is delegated to --help and schema. Mostly executable with minor gaps, so 4 rather than 5.	4 / 5
Workflow Clarity	There is a clear sequenced start (auth check → schema → help) with validation checkpoints for risky operations: '--dry-run before supported writes' and 'Confirm the exact account, object, and mutation before any write or delete'. This clears the destructive-operation cap; it is a 4 rather than 5 because there is no post-write verification or error-recovery loop (e.g., re-check the note after a write).	4 / 5
Progressive Disclosure	The skill is under 50 lines with no bundle files (no references/, scripts/, or assets/ directories exist), and per the rubric's simple-skill exception a short, well-sectioned body scores 5. The single external pointer ('Read `../gog/SKILL.md` first') is clearly signaled and one level deep.	5 / 5
	Total	18 / 20 Passed

Description

52%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 concise and names a distinct niche (Google Keep via the gog CLI), but it says nothing about what operations are supported or when the skill should be invoked. Adding a short list of operations and a 'Use when...' trigger clause would lift both specificity and completeness.

Suggestions

Add concrete operations to the description, e.g. 'Create, search, list, get, and delete Google Keep notes; download attachments.'

Append an explicit trigger clause such as 'Use when the user mentions Google Keep, notes, checklists, or asks to manage notes via gog.'

Include natural synonyms (notes, lists, reminders) to improve trigger-term coverage beyond the single product name.

Dimension	Reasoning	Score
Specificity	"Google Keep operations through gog" names the domain but lists no concrete actions (no create/search/delete of notes mentioned), matching the anchor 'Names the domain but actions are minimal or generic' exemplified by 'Processes PDF files'. Not a 3 because no specific operation is stated at all; not a 1 because the domain is clearly named rather than pure abstract language.	2 / 5
Completeness	The 'what' is present (Google Keep operations) but there is no 'when' / 'Use when...' clause, which per the judging guidelines caps completeness at 3. Not a 2 because the 'what' is clearly stated rather than vague; not a 4 because 'when' is entirely absent, not just under-specified.	3 / 5
Trigger Term Quality	"Google Keep" is a natural term users would say, but the description omits common variations and synonyms such as notes, note-taking, lists, reminders, or checklists. Fits 'Some relevant keywords but missing common variations or synonyms'; not a 4 because coverage is limited to a single product name plus the internal tool name 'gog'.	3 / 5
Distinctiveness Conflict Risk	"Google Keep" names a clear niche product with distinct triggers, and scoping operations 'through gog' ties it to a specific tool, so conflict risk with other skills is minimal. Matches 'Clear niche with distinct triggers; minimal conflict risk'.	5 / 5
	Total	13 / 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-keep/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.