CtrlK
BlogDocsLog inGet started
Tessl Logo

gog-contacts

Google Contacts operations through gog.

55

Quality

69%

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 ./.agents/skills/gog-contacts/SKILL.md
SKILL.md
Quality
Evals
Security

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 an exemplary lean CLI-wrapper skill: executable safe-start commands, explicit safety gates before any write, a compact command inventory, and clean delegation of flag detail to --help and the machine-readable schema. The only meaningful gap is the absence of a concrete example for write commands and any post-write verification or error-recovery guidance.

DimensionReasoningScore

Conciseness

The body is ~35 lines with zero concept explanations or padding: a one-line purpose, a delegated pointer for shared rules, an executable safe-start block, a compact command table, and pointers to --help and the schema contract. Every token earns its place, matching anchor 5.

5 / 5

Actionability

The safe-start block is fully executable and copy-paste ready (auth check, schema fetch, a read-only search example), and the body directs to `gog contacts <command> --help` and `gog schema contacts <command> --json` for exact syntax. It stops short of anchor 5 because no example invocation exists for any write command (create/update/delete/batch), leaving the most common mutation cases without a concrete example.

4 / 5

Workflow Clarity

Despite destructive and batch operations being present, the required validation checkpoints exist ('--dry-run before supported writes', 'Confirm the exact account, object, and mutation before any write or delete', '--readonly', and an auth/schema check before any operation), so the batch/destructive cap at 3 does not apply. It remains at anchor 4 rather than 5 because there is no post-write verification step or error-recovery loop (what to do when a command fails).

4 / 5

Progressive Disclosure

The skill is under 50 lines, cleanly sectioned (Safe start, Commands), and correctly delegates bulk detail: shared auth/safety rules to the one-level-deep `../gog/SKILL.md` reference and per-command flag contracts to `gog schema contacts <command> --json` instead of inlining an API reference. Per the simple-skill guideline, this scores 5 with well-organized sections and no unnecessary external reference files.

5 / 5

Total

18

/

20

Passed

Description

40%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 identifies a clear niche (Google Contacts via the gog CLI) but is too terse to function well as a trigger. It specifies no concrete operations and contains no 'Use when...' guidance, so the skill risks not being surfaced when users ask about contact management. A single sentence enumerating the key operations and the natural trigger phrases would move it into good territory.

Suggestions

Add a 'Use when...' trigger clause, e.g. 'Use when the user mentions contacts, Google Contacts, address book, or asks to create, find, dedupe, or export contacts.'

Enumerate concrete operations instead of the generic word 'operations': create, update, delete, search, dedupe/merge, and export contacts as vCard.

Include natural synonyms and tool-context terms users would say ('contacts', 'address book', 'People API') so the skill surfaces from varied phrasings.

DimensionReasoningScore

Specificity

The description names the domain ("Google Contacts") but the only action word is the generic "operations" — no concrete verbs like create, search, update, or delete. This matches anchor 2 ('Names the domain but actions are minimal or generic') and falls short of anchor 3, which requires 1-2 concrete actions.

2 / 5

Completeness

There is no "Use when..." trigger clause at all, and the 'what' is itself vague ("operations" conveys no specific capability). This matches anchor 2 ('Has a vague what and no when') rather than anchor 3, whose example lists concrete capabilities even without a when-clause.

2 / 5

Trigger Term Quality

"Google Contacts" and "gog" are natural terms a user would say, but there are no variations or synonyms ("contacts", "address book", "People API"). Anchor 3 ('Some relevant keywords but missing common variations') is the closest fit; anchor 4 requires noticeably broader keyword coverage.

3 / 5

Distinctiveness Conflict Risk

"Google Contacts" plus the specific tool "gog" carves a clear, distinct niche with minimal conflict risk. It sits at anchor 4 rather than 5 only because the thin description provides few trigger phrases to distinguish it from sibling gog skills (e.g., Gmail contact management).

4 / 5

Total

11

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
openclaw/gogcli
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.