CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-trigger

Create or update Sim webhook triggers using the generic trigger builder, service-specific setup instructions, outputs, and registry wiring. Use when working in `apps/sim/triggers/{service}/` or adding webhook support to an integration.

64

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

70%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 highly actionable, well-sequenced skill with strong validation checkpoints (type-check, alignment checker, rollback logic, final checklist). Its weaknesses are token efficiency — near-duplicate trigger templates and repeated outputs examples — and the absence of any progressive disclosure: a monolithic single file where the automatic-registration material belongs in a separate reference.

Suggestions

Replace the full Event B secondary-trigger template with a short delta note ("identical to the primary trigger except: no `includeDropdown`, its own id/name/description") — the current block duplicates ~40 lines for a one-line difference.

Move the "Automatic Webhook Registration" section (~200 lines, including the route and delete-helper templates) into a reference file such as references/automatic-registration.md and keep a 5-line summary plus a pointer in SKILL.md.

Merge the duplicated output-schema examples: Step 1's `build{Service}Outputs` and the later "Trigger Outputs" section teach the same rules twice; keep one canonical example and reduce the other to the Supported/NOT-Supported bullet list.

DimensionReasoningScore

Conciseness

The body is mostly project-specific knowledge Claude cannot know (buildTriggerSubBlocks options, registry wiring, provider-subscriptions cleanup), so most tokens earn their place. But it could be tightened: the full Event B template duplicates the primary trigger with only the `includeDropdown` line changed, and outputs are defined twice (Step 1's `build{Service}Outputs` and the later "Trigger Outputs" section) — matching the "mostly efficient but some unnecessary explanation / could be tightened" anchor rather than the lean one.

3 / 5

Actionability

Guidance is highly concrete: complete TypeScript templates, exact file paths (`apps/sim/lib/webhooks/utils.server.ts`, `provider-subscriptions.ts`), and runnable commands (`bunx scripts/check-trigger-alignment.ts {service}`, `bun run type-check`). It sits below "fully executable, copy-paste ready" because the `{service}`/`{Service}` placeholder templates and elided sections (`// ... other config ...`, `{ id: 'operation', /* ... */ }`) mean code is not directly runnable without assembly — justified for a templated skill, but still a gap.

4 / 5

Workflow Clarity

Steps 1–6 give a clear, ordered sequence, and the closing checklist provides explicit validation checkpoints: "Run `bun run type-check` to verify no TypeScript errors", "Restart dev server", "Test trigger UI", and "Run `bunx scripts/check-trigger-alignment.ts {service}` to verify alignment". The automatic-registration path even includes a feedback loop (rollback via `db.delete` when external creation fails). Not a 4: checkpoints are explicit, not implicit.

5 / 5

Progressive Disclosure

There are no bundle files at all (no references/, scripts/, or assets/), so everything lives inline in a ~700-line SKILL.md. Internal structure is good (numbered steps, headers, checklist), but large self-contained blocks — the ~200-line "Automatic Webhook Registration" section and the full helper-function templates — are exactly the kind of content that belongs in one-level-deep reference files, matching the "content that should be separate is inline" anchor.

3 / 5

Total

15

/

20

Passed

Description

87%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 that states concrete capabilities and an explicit, natural "Use when" trigger clause in third-person voice. Its only weakness is modest coverage of what the body actually teaches (automatic registration, output alignment), which keeps specificity at 4 rather than 5.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Create or update Sim webhook triggers", "service-specific setup instructions, outputs, and registry wiring" — grounded in a named system ("the generic trigger builder"). It falls short of a 5 because it omits major capabilities the body covers, such as automatic webhook registration and webhook input formatting, so coverage has minor gaps.

4 / 5

Completeness

It explicitly answers both questions: the "what" ("Create or update Sim webhook triggers using the generic trigger builder, service-specific setup instructions, outputs, and registry wiring") and the "when" ("Use when working in `apps/sim/triggers/{service}/` or adding webhook support to an integration") with concrete trigger phrases. Not a 4 because the "when" clause is already explicit and specific rather than something that merely could be more so.

5 / 5

Trigger Term Quality

Natural phrases like "webhook triggers", "webhook support", and "adding webhook support to an integration" match what a user would actually say, plus a concrete path trigger (`apps/sim/triggers/{service}/`). A few common variations are missing (e.g., "new trigger", "event trigger", specific service names), keeping it below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche — Sim webhook triggers with named integration points (trigger builder, registry wiring, triggers directory) — so it is unlikely to fire for unrelated skills. It stays in third person ("Create or update") with no over-claims.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (709 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

16

Passed

Repository

itsablabla/jada-ironman

Path

.agents/skills/add-trigger/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.