CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

connector

Create, test, validate, and deploy Insight Connectors. Supports both nocode (declarative YAML) and CDK (Python) connector types. Commands: /connector create <name>, /connector test <name>, /connector schema <name>, /connector deploy <name>, /connector validate <name>.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/connector/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%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 strongly actionable, information-dense skill body that captures non-obvious wiring invariants and operational gotchas with exact commands. Its weaknesses are the missing validation steps around the destructive reset operation and deep operational detail (secrets, credentials, rotation) inlined in the overview rather than split into reference files.

Suggestions

Add explicit validation/verification steps around '/connector reset' (e.g. confirm the connector name and tenant, verify Bronze tables dropped, check state file cleaned) so the destructive flow is no longer capped at workflow clarity 3.

Move the Airbyte Architecture deep-dive (Secret YAML structure, credential tables, password rotation) into a reference file (e.g. references/airbyte.md) and keep a one-line pointer in SKILL.md.

Trim duplication between the frontmatter command list, the body's routing table, and the per-command sections to reduce token cost.

DimensionReasoningScore

Conciseness

The body is dense and imperative, encoding repo-specific failure modes Claude could not know, with no explanations of known concepts; however the command routing table duplicates the description's command list and some sections (logs, credentials) run long enough to trim — efficient with minor over-explanation, anchor 4 rather than the lean anchor 5.

4 / 5

Actionability

Fully executable guidance throughout: exact commands ('python3 scripts/ci/connector_wiring.py', './run-sync.sh <connector> <tenant>'), concrete kubectl/yq/curl one-liners, specific paths, and placeholders ({INGESTION_DIR}, {CONNECTOR_PATH}) defined in the Context Variables table — copy-paste ready and covering the common cases.

5 / 5

Workflow Clarity

The routing table, test ladder (L0→L1→L2), pre-PR wiring guard, and log/health verification provide a clear sequence with checkpoints, but '/connector reset' is destructive — it "deletes the Airbyte connection, source, and definition, drops the Bronze database" — with no written validation or verification step, capping workflow clarity at 3 per the destructive-operation rule.

3 / 5

Progressive Disclosure

Good structure: a routing table cleanly signals seven workflows/*.md files and the README/PATTERNS references are one level deep and clearly labeled; however substantial deep-dive material (Secret YAML structure, three credential systems, password rotation) is inlined in SKILL.md where reference files would serve better — minor organization gaps, anchor 4.

4 / 5

Total

16

/

20

Passed

Description

70%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 specific, distinct description with concrete actions and command triggers, undermined by the complete absence of a 'Use when...' trigger clause. It reads as a command index rather than guidance on when Claude should invoke the skill.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the user asks to create, test, validate, or deploy an Insight Connector, or mentions connector schemas, syncs, or connector packaging.' to fix the completeness cap.

Include natural trigger synonyms (sync, ingestion, connector package, Airbyte connector) so the skill fires on phrasings that don't use the exact command verbs.

Trim the enumerated command list (it duplicates the verb sentence and the body's routing table) and instead use the space for trigger guidance.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Create, test, validate, and deploy Insight Connectors") plus connector types and a command inventory, but omits build/reset/workflow/logs and the verb list duplicates the command list — minor gaps in coverage, matching anchor 4 rather than the comprehensive anchor 5.

4 / 5

Completeness

The "what" is clear (create/test/validate/deploy Insight Connectors, nocode and CDK types), but there is no "Use when..." clause or equivalent explicit trigger guidance — the command list only weakly implies "when", which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Natural terms users would say ("connector", "create", "test", "deploy", "validate") plus explicit /connector command triggers, but synonyms like "sync", "integration", or "ingestion" are missing — good coverage with a few natural terms absent, so anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

"Insight Connectors" with the nocode/CDK distinction and /connector slash-commands defines a clear niche with distinct triggers and minimal conflict risk against generic document or code skills, matching anchor 5.

5 / 5

Total

16

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

relative_links

Relative link issues: 7 missing

Warning

referenced_paths_exist

Referenced path issues: 2 missing, 2 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository

constructorfabric/insight

Path

.claude/skills/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.