CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

autumn

Autumn billing in Epicenter: `autumn.config.ts`, `autumn-js` credit checks, `atmn` CLI, plan gates, and metered AI usage. Use when changing billing, pricing, credits, plan access, refunds, or usage events.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 high-quality integration guide: nearly all content is project-specific and actionable, with correct sequencing of billing-critical operations and good internal navigation. The main improvement levers are de-duplicating section content vs. the gotchas list, replacing placeholder code comments with real error responses, and splitting bulk reference material into bundle files.

Suggestions

Remove the duplicated long-form explanations in 'Common Gotchas' (items 3, 5, 8 repeat the Naming Conventions, Plan Structure, and Proportional Billing sections) — keep gotchas as one-line pointers to those sections.

Replace placeholder comments like `// Return 402 with balance info` with the actual error-response code so the credit-check and middleware snippets are copy-paste ready.

Move the SDK/CLI reference detail and plan-item variant specs into references/ files (e.g., references/sdk.md, references/plans.md) linked from short summary sections, keeping SKILL.md as a lean overview.

Add an explicit post-push validation step (e.g., re-run `bun x atmn preview` or verify plans in the dashboard after `atmn push --prod`) to close the feedback loop on config changes.

DimensionReasoningScore

Conciseness

The body is dense with non-inferable, project-specific knowledge (plan-item variant rules, interval exclusivity, fail-closed policy, secret-key rotation), but several topics are explained twice at length — proportional billing, naming conventions, and interval exclusivity each reappear in 'Common Gotchas' — which is trimmable duplication. Fits 'minor instances of over-explanation'; not 5 because of this repeated content.

4 / 5

Actionability

Concrete, near-executable TypeScript and `bun x atmn ...` commands with real project paths cover the common cases, but a few snippets are templates rather than copy-paste ready — e.g. `if (!allowed) { // Return 402 with balance info }` is a comment placeholder and snippets reference undefined locals (`error`, `data.model`). Fits 'concrete code with minor gaps'; not 5 due to those placeholders.

4 / 5

Workflow Clarity

Sequencing and most checkpoints are explicit (blocking `getOrCreate` before `check()`, fail-closed credit gating before expensive provider calls, `atmn preview` dry-run before push, authGuard → customer-ensuring middleware → credit gate). Not 5 because there is no validate-after-push feedback loop or error-recovery steps for config pushes, leaving 'minor validation gaps'.

4 / 5

Progressive Disclosure

With no bundle files, the single 345-line body is well organized — clear headers, tables, `---` separators, and a project-file map make navigation easy — matching 'good structure; most content appropriately placed'. Not 5 because bulk reference material (full SDK/CLI reference, plan-variant details) is inlined in SKILL.md where one-level-deep reference files would keep the overview leaner.

4 / 5

Total

16

/

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 description: it names a clearly-scoped niche with concrete artifacts and capabilities, and provides an explicit, trigger-rich 'Use when' clause. The only weakness is modest synonym coverage in trigger terms (e.g., no 'subscription', 'payment', or 'Stripe').

DimensionReasoningScore

Specificity

Names the domain and five concrete capabilities ('`autumn-js` credit checks', '`atmn` CLI, plan gates, and metered AI usage', '`autumn.config.ts`'), comprehensively covering the integration surface for its niche; not 4 because coverage has no material gaps.

5 / 5

Completeness

Explicitly answers both what ('Autumn billing in Epicenter: ... credit checks, `atmn` CLI, plan gates, and metered AI usage') and when ('Use when changing billing, pricing, credits, plan access, refunds, or usage events') with concrete trigger phrases; not 4 because the 'when' clause is already fully explicit and specific.

5 / 5

Trigger Term Quality

Good natural keyword coverage ('billing, pricing, credits, plan access, refunds, or usage events') but misses common synonyms a user might say such as 'subscription', 'payment', 'Stripe', or 'invoice'; not 5 because synonym coverage is incomplete.

4 / 5

Distinctiveness Conflict Risk

'Autumn billing in Epicenter' plus product-specific artifacts (`atmn`, `autumn.config.ts`, `autumn-js`) carves out a clear niche with minimal conflict risk against generic billing skills; not 4 because the product scoping makes wrong-skill triggering unlikely.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

EpicenterHQ/epicenter

Path

.agents/skills/autumn/SKILL.md

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.