CtrlK
BlogDocsLog inGet started
Tessl Logo

orchestra-dbt-slim-ci-setup

Retrofits dbt Slim CI onto an existing Orchestra production dbt pipeline using latest_production, state:modified+, and --defer, with GitHub Actions run-pipeline as the primary CI trigger. Use when setting up Orchestra Slim CI, dbt CI/CD in Orchestra, run-pipeline for dbt, or latest_production defer state in a dbt repo or from outside it.

68

1.00x
Quality

75%

Does it follow best practices?

Impact

100%

1.00x

Average score across 1 eval scenario

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/orchestra/skills/orchestra-dbt-slim-ci-setup/SKILL.md

The canonical home for this skill is orchestra-hq/orchestra-skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 well-structured, concise overview with a clear sequenced workflow and validation checkpoint. Its main weaknesses are the bundle's delivery: the referenced templates/ files are absent (weakening actionability) and several reference paths are broken or malformed (weakening progressive disclosure), plus a small doc-table duplication across SKILL.md and a reference file.

Suggestions

Add the missing templates/ files (pipeline-inputs-snippet.yml, github-dbt-slim-ci.yml, github-dbt-slim-ci-incremental.yml) to the bundle, or inline minimal working snippets in the body if the templates are not shipped.

Fix the broken reference path ../../references/orchestra/mcp-playbook.md to point at the actual mcp-playbook.md location, and ship that file since both the body and references/orchestra-slim-ci.md link to it.

Add a short failure-handleshooting note after the validation step (e.g. what to check when validate_pipeline or dbt parse fails) to complete the feedback loop, and drop the duplicated Doc index table in favor of the one in references/orchestra-slim-ci.md.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — terse bullets, real tool names, no explanation of known concepts — but the five-row Doc index table duplicates the near-identical doc table already in references/orchestra-slim-ci.md, so those tokens do not fully earn their place. Efficient with minor trimming possible, matching the 4 anchor rather than 5.

4 / 5

Actionability

Steps name concrete tools (`list_pipelines`, `validate_pipeline`, `dbt parse`, specific files to read) but the actual patch content is delegated to templates/pipeline-inputs-snippet.yml and templates/github-dbt-slim-ci.yml, and no templates/ directory exists in the bundle — key executable details are missing, and there is no inline YAML or command example. This matches the 3 anchor (some concrete guidance but incomplete, missing key details); it is above 2 because most steps are executable as written.

3 / 5

Workflow Clarity

A clear 10-step sequence with a dedicated validation step (validate_pipeline, dbt parse, approval-gated start_pipeline) and an already-configured fallback path. Minor gap: no explicit on-failure loop for setup validation (what to do when validate_pipeline or dbt parse fails is unstated — the companion debug skill only covers failed PR checks), which keeps it at 4 rather than the 5 anchor's explicit feedback loops.

4 / 5

Progressive Disclosure

The design is good — a lean overview with clearly signaled one-level-deep references — but scored against the actual bundle, 3 of the 8 referenced paths are broken: the entire templates/ directory (pipeline-inputs-snippet.yml, github-dbt-slim-ci.yml) is missing, and references/orchestra/mcp-playbook.md is referenced via a malformed ../../references/orchestra/ path with no such file, leaving steps 3, 5, and 6 with dead links. Navigation exists and is well signaled but does not resolve, sitting between the 3 and 4 anchors.

3 / 5

Total

14

/

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: third-person, concrete mechanisms, an explicit trigger clause, and a clearly distinct niche. The only gaps are that the capability reads as one retrofit action rather than a list of distinct actions, and a few natural synonyms (e.g. "PR checks", "dbt continuous integration") are absent.

Suggestions

Add one or two more distinct action verbs beyond "retrofits" (e.g. "patches pipeline YAML and generates GitHub Actions workflows") to enumerate the concrete operations performed.

Include natural synonyms such as "PR checks" or "dbt continuous integration" in the Use-when clause to broaden trigger coverage.

DimensionReasoningScore

Specificity

"Retrofits dbt Slim CI onto an existing Orchestra production dbt pipeline using latest_production, state:modified+, and --defer" names the domain and several concrete mechanisms (GitHub Actions run-pipeline as primary CI trigger), but the capability is framed as a single retrofit action with techniques rather than a list of multiple distinct actions like extract/fill/merge, so it sits between the 3 and 5 anchors — noticeably above the midpoint.

4 / 5

Completeness

"Retrofits dbt Slim CI onto an existing Orchestra production dbt pipeline... with GitHub Actions run-pipeline as the primary CI trigger" clearly answers what, and the explicit "Use when setting up..." clause with concrete trigger phrases answers when — matching the 5 anchor exactly. Not below: the when clause is explicit with multiple concrete triggers, not merely present.

5 / 5

Trigger Term Quality

"Use when setting up Orchestra Slim CI, dbt CI/CD in Orchestra, run-pipeline for dbt, or latest_production defer state in a dbt repo or from outside it" covers good natural phrases a user would say, but misses common variations like "PR checks", "dbt continuous integration", or "defer to production" — good coverage with a few natural terms missing, matching the 4 anchor.

4 / 5

Distinctiveness Conflict Risk

The Orchestra + dbt Slim CI niche is highly specific with distinct trigger terms (latest_production defer state, run-pipeline for dbt); no generic overlap with other skills — a clear niche with minimal conflict risk.

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

relative_links

Relative link issues: 2 missing, 1 suspicious

Warning

referenced_paths_exist

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

Warning

Total

14

/

16

Passed

Repository
orchestra-hq/orchestra-skills
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.