CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agntix-webhooks

Receive and verify Agntix webhooks (voice and chat AI-agent platform, delivered by Svix). Use when setting up Agntix webhook handlers, debugging svix-signature verification, or handling the session.created and session.ended events with post-call analysis.

Quality

82%

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

67%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 solid, information-dense handler guide with executable verification code, explicit fail-closed error handling, and a well-organized one-level-deep reference bundle. Main weaknesses are dead links to nonexistent examples/ directories, re-explanation of the standard Svix signing scheme, and a lengthy promotional Related Skills section that spends tokens without adding instructional value.

Suggestions

Fix or remove the links to examples/express/, examples/nextjs/, and examples/fastapi/ — the bundle contains no examples/ directory, so users following 'For complete handlers with tests' hit dead paths.

Trim the 9-entry Related Skills section to the few most relevant (e.g., svix-webhooks and webhook-handler-patterns) or move the full catalog into a reference file.

Drop the inline re-explanation of the Standard Webhooks HMAC-SHA256 mechanics (signed-content format, v1 space-separated entries) and defer those details to references/verification.md, keeping only the Agntix-specific deviations (flat envelope, eventType as event name, webhook-* header fallback).

DimensionReasoningScore

Conciseness

The core sections (verification, events, env var, local dev) are dense and fact-rich, but the body re-explains the Standard Webhooks HMAC-SHA256 scheme mechanics ("signs it with HMAC-SHA256 using the base64-decoded secret... base64-encodes the result... space-separated v1,<signature> entries") that Claude already knows, and devotes roughly 25 lines to a 9-entry Related Skills catalog, attribution boilerplate, and a recommended-skill promo. Mostly efficient but includes unnecessary explanation and could be tightened, matching anchor 3 rather than anchor 4's 'minor instances'.

3 / 5

Actionability

Provides executable JavaScript and Python verification snippets, a copy-paste tunnel command ("npx hookdeck-cli listen 3000 agntix --path /webhooks/agntix"), the env var with its value format, and explicit response codes (500 fail-closed, 400 on bad signature). Not anchor 5: the Python snippet leaves id/ts/sig and the os import undefined, and the pointer to "complete handlers with tests" at examples/express/, examples/nextjs/, examples/fastapi/ leads to directories that do not exist in the bundle — minor but real gaps.

4 / 5

Workflow Clarity

A coherent implicit sequence runs through the sections (tunnel endpoint → add endpoint and subscribe in Developer dashboard → verify signature → parse → deduplicate on id + eventType → return 2xx → process async), with explicit validation checkpoints ("parse only after verify passes", "throws on a bad signature or a timestamp outside the window", fail-closed 500 on unset secret). Not anchor 5 because the sequence is distributed across sections rather than consolidated, and error-recovery guidance (the Hookdeck retry window workaround) covers only one failure mode.

4 / 5

Progressive Disclosure

The three real references (references/overview.md, references/setup.md, references/verification.md) exist, are one level deep, and are well signaled both contextually and in a Reference Materials section with descriptions — structure is otherwise anchor-5 quality. However, the body links to examples/express/, examples/nextjs/, and examples/fastapi/, none of which exist in the bundle, so navigation breaks at exactly the point where a user needs complete handler code. This is more than the trivial gap that would still allow anchor 5, fitting anchor 4's 'minor organization gaps'.

4 / 5

Total

15

/

20

Passed

Description

91%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: third-person, concise, with an explicit 'Use when' clause carrying three concrete trigger scenarios and full coverage of the domain's natural vocabulary. The only weakness is minor overlap risk with generic Svix webhook skills via the shared svix-signature trigger term.

DimensionReasoningScore

Specificity

Concrete actions are named — "Receive and verify Agntix webhooks", "setting up Agntix webhook handlers, debugging svix-signature verification", "handling the session.created and session.ended events with post-call analysis" — several specific actions with minor coverage gaps. It exceeds anchor 3 (only 1-2 actions) but is not the comprehensive action list of anchor 5.

4 / 5

Completeness

Explicitly answers both: what ("Receive and verify Agntix webhooks (voice and chat AI-agent platform, delivered by Svix)") and when ("Use when setting up Agntix webhook handlers, debugging svix-signature verification, or handling the session.created and session.ended events"). Both are concrete and trigger-phrase-rich, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Natural terms a user would say are comprehensively covered: "Agntix webhooks", "webhook handlers", "svix-signature", "session.created", "session.ended", "post-call analysis". For this niche platform the product vocabulary is the natural vocabulary, and all of it is present; no common synonym is missing.

5 / 5

Distinctiveness Conflict Risk

Anchored on the niche platform name Agntix with event-specific triggers, giving a clear niche; however "debugging svix-signature verification" is a trigger shared with any Svix-delivered webhook skill (a generic svix-webhooks skill exists in the same family), creating minor overlap risk. Not anchor 5 because that shared trigger phrase could pull generic Svix questions; not anchor 3 because Agntix scoping is dominant.

4 / 5

Total

18

/

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

relative_links

Relative link issues: 3 missing

Warning

Total

15

/

16

Passed

Repository

hookdeck/webhook-skills

Path

skills/agntix-webhooks/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.