CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

create-orchestra-pipeline

Create, validate, and remediate Orchestra pipeline definitions, as YAML or OML. Use when asked to build a new pipeline, add tasks to an existing pipeline, fix pipeline validation errors, or author Orchestra workflow definitions from a description. Trigger on phrases like "create a pipeline", "add a dbt task", "write orchestra yaml", "write orchestra oml", "fix validate errors", or when editing `.yml`, `.yaml` or `.oml` files under orchestra/ or similar pipeline directories.

Quality

92%

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 well-structured, domain-expert skill body: concrete commands and tool calls throughout, an explicit validate-remediate feedback loop with a retry cap, a pre-deploy confirmation step, and cleanly annotated one-level-deep references. The only weaknesses are the absence of a minimal inline pipeline example and a few over-long sentences that could be tightened.

Suggestions

Include a minimal inline YAML (or OML) pipeline skeleton in Step 3 so the core authoring task doesn't depend entirely on the external reference.

Rewrite Step 5.5 as a short two-item checklist (connection validation, DBT project_dir) instead of one long sentence.

Tighten the Git-backed deploy note in Notes — its deploy-semantics detail could largely live in the referenced yaml-authoring.md section it already cites.

DimensionReasoningScore

Conciseness

Lean and information-dense with essentially no explanation of concepts Claude already knows — every note carries non-obvious domain knowledge ("orchestra-cli validate reads its input as YAML, so it can't parse an .oml file"). Not 5 because a few passages are tangled and could be trimmed, notably the single-sentence Step 5.5 checkpoint ("confirm two things first rather than shipping placeholders: every non-null connection: value matches...") and the 60-word Git-backed deploy sentence in Notes.

4 / 5

Actionability

Gives concrete executable commands and tool calls ("orchestra-cli pipeline validate <path/to/pipeline.yml>", "pip install orchestra-lang", "oml_lang.analyze(source).errors()", "pipeline_context(<alias>)", MCP tool names) plus concrete defaults ("${{ ENV.VAR }}", "${{ MATRIX.key }}"). Not 5 because the core authoring task ships no inline YAML/OML example — the format is entirely deferred to the reference — leaving a minor gap for the most common case.

4 / 5

Workflow Clarity

Steps 1–6 are clearly sequenced with an explicit validation step, a remediation feedback loop ("Re-validate, patching only what the latest errors report. Cap this at around 5 attempts — if still failing, present the YAML with the remaining errors"), and a pre-deploy confirmation checkpoint (Step 5.5) plus a structured reporting checklist. Matches the anchor-5 pattern of explicit validation with error-recovery loops.

5 / 5

Progressive Disclosure

The body is a clear overview with three well-signaled, one-level-deep references, each annotated with its content ("yaml-authoring.md — schema, integrations, variables, optional sections"; "examples.md — multi-stage patterns"; "tools-quick-ref.md — validate_pipeline, create_pipeline, update_pipeline"), keeping detail appropriately split out of SKILL.md. Navigation is easy and no content that belongs in a reference is inlined.

5 / 5

Total

18

/

20

Passed

Description

96%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: explicit what-and-when structure, concrete natural trigger phrases with file extensions, and a clearly bounded Orchestra-specific niche. Voice is appropriately third-person and the length stays concise while remaining comprehensive.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete actions — "Create, validate, and remediate Orchestra pipeline definitions, as YAML or OML" plus "build a new pipeline, add tasks to an existing pipeline, fix pipeline validation errors" — covering the skill's full scope in both supported formats. Not the 4 anchor because coverage of the skill's capabilities is comprehensive rather than having minor gaps.

5 / 5

Completeness

Clearly answers both: what ("Create, validate, and remediate Orchestra pipeline definitions, as YAML or OML") and when ("Use when asked to build a new pipeline... fix pipeline validation errors", reinforced by a "Trigger on phrases like..." clause with concrete phrases). Exactly the anchor-5 pattern of explicit what + when with concrete triggers.

5 / 5

Trigger Term Quality

Explicit natural trigger phrases ("create a pipeline", "add a dbt task", "write orchestra yaml", "write orchestra oml", "fix validate errors") plus file extensions (.yml, .yaml, .oml) and a directory convention (orchestra/). Matches the comprehensive-with-extensions anchor; only trivial variations like "update a pipeline" are absent.

5 / 5

Distinctiveness Conflict Risk

The Orchestra-platform niche is clear and the extension triggers are scoped "under orchestra/ or similar pipeline directories", keeping conflict risk low. Not 5 because the bare phrase "create a pipeline" and the fuzzy qualifier "or similar pipeline directories" could overlap with generic CI/CD pipeline skills.

4 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

orchestra-hq/orchestra-skills

Path

skills/orchestra/skills/create-orchestra-pipeline/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.