CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-connector

Add or update a Sim knowledge base connector for syncing documents from an external source, including auth mode, config fields, pagination, document mapping, tags, and registry wiring. Use when working in `apps/sim/connectors/{service}/` or adding a new external document source.

67

Quality

84%

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

71%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.

This is a dense, expert-level procedural skill: nearly every token encodes non-obvious repository-specific contracts (canonical pairs, metadata-based hashing, content deferral, retry budgets) and it ends with a strong verification checklist. Its weaknesses are structural — a monolithic single-file layout where selector tables and worked pattern examples belong in reference files — plus a duplicated section, and the absence of an explicit post-implementation validate-and-fix loop.

Suggestions

Move the 'Available selector keys' table and the two canonical-pair worked examples into a references/ file (e.g. references/selectors.md), keeping a brief rule summary in SKILL.md with a clearly signaled link.

Remove the duplicate 'Reference Implementations' section (lines 383-388 vs 496-502) by merging them into the single list near the end.

Add an explicit verification step after registration (e.g. run validateConfig, typecheck/build, and confirm the connector appears in the modal), with a fix-and-retry loop before declaring the task complete.

DimensionReasoningScore

Conciseness

Almost all content is non-obvious, repo-specific knowledge (canonical pairs, contentDeferred invariant, metadata-hash strategy, fetchWithRetry budgets) rather than concepts Claude already knows. However, at ~525 lines it has trimmable material: two full canonical-pair worked examples (Airtable and Jira), a 16-row selector table, and a duplicated 'Reference Implementations' section (lines 383-388 and 496-502).

4 / 5

Actionability

Concrete TypeScript templates with real imports, exact file paths, hash-format patterns, and a one-line registry wiring snippet, plus five named reference implementations to copy from. Minor gaps: connector method bodies are comment stubs, the API-key example elides configFields (/* ... */), and no complete pagination-loop example is shown, so it is not fully copy-paste ready.

4 / 5

Workflow Clarity

A clear four-step sequence up front (read API docs, determine auth, create config, register), an explicit 'Sync Engine Behavior (Do Not Modify)' boundary section, and a comprehensive final checklist provide most checkpoints. Not 5 because there is no explicit post-implementation verification feedback loop (build/test/fix-and-retry) and validateConfig guidance lacks an error-recovery path.

4 / 5

Progressive Disclosure

Sections are well-organized and point to real codebase files (connectors/types.ts, hooks/selectors/registry.ts, reference implementations), but the skill is a single ~525-line monolith with no bundle files. The selector-key table and the canonical-pair pattern examples clearly belong in references/ files the body could point to, matching the anchor where content that should be separate is inline.

3 / 5

Total

15

/

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 states the capability concretely, enumerates the full scope of connector work, and gives an explicit use-when clause with both a path-based and an intent-based trigger. The only gap is that users often name the specific service (e.g. 'add a Confluence connector'), and none of those service names appear as trigger terms.

Suggestions

Add one or two example service names (e.g. 'such as Confluence, Google Drive, or Notion') to the use-when clause so users who say 'add a Confluence connector' match naturally.

Consider a synonym like 'integration' or 'external source' phrasing variation to widen natural-language matching without adding vagueness.

DimensionReasoningScore

Specificity

The description enumerates concrete actions comprehensively — 'Add or update a Sim knowledge base connector for syncing documents from an external source, including auth mode, config fields, pagination, document mapping, tags, and registry wiring' — covering every phase of the task with no vague filler.

5 / 5

Completeness

It explicitly answers both what ('Add or update a Sim knowledge base connector for syncing documents... including auth mode, config fields, pagination...') and when ('Use when working in apps/sim/connectors/{service}/ or adding a new external document source') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural terms like 'connector', 'knowledge base', 'syncing documents', 'external document source', and the path 'apps/sim/connectors/{service}/' are present, but common variations users would actually say — specific service names (Confluence, Notion, Google Drive) or synonyms like 'integration' — are missing.

4 / 5

Distinctiveness Conflict Risk

A clear niche — 'Sim knowledge base connector' with a specific directory path and 'registry wiring' — makes it highly distinguishable and very unlikely to trigger for the wrong skill.

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (529 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

itsablabla/jada-ironman

Path

.agents/skills/add-connector/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.