CtrlK
BlogDocsLog inGet started
Tessl Logo

gg

Working pattern for Grida Gateway (GG) — Grida's first-party, metered, no-BYOK AI surface: the scoped-token mint, the OpenAI-compatible + native gateway endpoints, the `gg` client provider, and the desktop wiring that spends org credit without a user key. Anchor for the `GRIDA-GG: <surface>` grep marker; its security half is `GRIDA-SEC-006`. Use when adding or touching any GG file, the `gg` provider kind, the `gg:ai` token audience, or deciding whether code belongs to the gateway surface. Companions: `security` (the GRIDA-SEC-006 half), `ee-billing` (the ledger it spends), `agent-system` and `desktop` (the two hosts).

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

96%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 tightly written, highly actionable working-pattern skill with clear sequencing and a well-signaled cross-reference structure. The only minor gap is the absence of dedicated reference files, which keeps progressive disclosure just below the top anchor.

DimensionReasoningScore

Conciseness

Dense and lean with no padding — it assumes Claude knows JWT/billing/gateway concepts and devotes every line to surface-specific rules (marker format, naming map, dependency direction, security precedence), so every token earns its place.

5 / 5

Actionability

Provides executable guidance: the grep command `grep -rn 'GRIDA-GG' editor packages desktop`, paste-ready marker comments, a concrete identifier table, and a numbered working checklist with a hard dependency-direction rule, covering the common cases copy-paste ready.

5 / 5

Workflow Clarity

The "Working on GG" section is a clear numbered sequence with an explicit checkpoint (the security-crossing pass runs the security review first, then this skill) and a stated invariant to protect, which is well above the bar for an organizational skill.

5 / 5

Progressive Disclosure

Well-organized into clear sections with one-level-deep cross-references to companion skills and a canonical spec URL, and no nested references; it stops short of 5 only because all detail is inline with no separate reference files within this bundle.

4 / 5

Total

19

/

20

Passed

Description

92%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.

A strong, specific description that clearly scopes the GG working pattern and gives concrete use-when guidance. Its only weakness is that most trigger terms are internal code markers rather than vocabulary a user would naturally utter.

DimensionReasoningScore

Specificity

Enumerates four concrete surfaces (scoped-token mint, OpenAI-compatible + native gateway endpoints, the `gg` client provider, desktop wiring) plus the GRIDA-GG grep marker, giving comprehensive coverage of what the working pattern spans.

5 / 5

Completeness

Explicitly answers both what ("Working pattern for Grida Gateway … four surfaces … grep marker") and when ("Use when adding or touching any GG file …") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Contains natural trigger phrases ("Use when adding or touching any GG file, the `gg` provider kind, the `gg:ai` token audience") and key identifiers, but most triggers are internal markers rather than terms a user would naturally say, leaving a few natural synonyms unaccounted for.

4 / 5

Distinctiveness Conflict Risk

A clear niche (Grida's first-party no-BYOK metered AI gateway) with explicit companions (security, ee-billing, ee, agent-system, desktop) and carve-outs (BYOK providers, billing ledger), giving minimal conflict risk.

5 / 5

Total

19

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 8 suspicious

Warning

Total

15

/

16

Passed

Repository
gridaco/grida
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.