CtrlK
BlogDocsLog inGet started
Tessl Logo

integration-orchestrator

Generate a phased delivery orchestration plan for creative-direction-driven work: which skills run when, what locks at which gate, how handoffs occur, and how the cadence implements in the team's tools (Jira, Linear, Notion, Figma, GitHub) with AI agents via MCP and CLI. A temporal map of phases, lock points, handoff specs, gate definitions, and QA verification gates. Distinct from `creative-brief` (static project brief) and `creative-direction` (aesthetic direction). Triggers on integration orchestrator, delivery cadence, project orchestration, when does the brief lock, how to phase creative direction, design-development handoff, QA gate, agent-driven QA, and when a creative-direction project is starting, mid-flight with broken cadence, or integrating AI agents into PM workflow. Does NOT fire for project scoping (use `creative-brief`), aesthetic direction (use `creative-direction`), or general project management without a creative-direction throughline.

74

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable orchestration framework with clear sequencing, validation gates, and clean progressive disclosure into real reference files. Its only weakness is mild verbosity in the framing and failure-pattern prose.

Suggestions

Tighten the opening 'What this skill is' framing and the 'Failure patterns' section — lead with the concrete framework rather than motivational context to reduce tokens that don't add new information.

Consider moving the seven 'Common project-type cadences' summary block into references/cadence-patterns.md since that reference already expands them, leaving SKILL.md as a pointer to avoid duplicating the skeletal phase maps.

Trim repeated restatements of the 'brief drift / re-work' problem across the intro, framework, and failure-patterns sections to a single canonical statement.

DimensionReasoningScore

Conciseness

Mostly efficient but carries motivational framing ('A brief tells a team what to make. Creative direction tells them what it should feel like') and repeated emphasis on failure modes that could be tightened; not padded with concepts Claude already knows, but not maximally lean.

2 / 3

Actionability

Concrete, specific guidance throughout — named phases and gates with measurable criteria ('client signed the brief artifact in writing', 'Playwright critical-flow suite green, console error count at or below baseline'), exact tool mappings (Jira Epics with 'Phase', 'Locked', 'Approver', 'Gate Status' fields), a 5-status taxonomy, and an explicit 8-section output structure. For an instruction-only skill the guidance is fully actionable.

3 / 3

Workflow Clarity

Clear sequence (phasing → gates → lock points → handoffs) with explicit validation checkpoints: the QA verification gate must pass before transition to Done, failure routes to Blocked, and the agent does not retry autonomously — a defined feedback loop for risky transitions.

3 / 3

Progressive Disclosure

SKILL.md is an overview with seven one-level-deep reference files, each clearly signaled in a 'Reference files' section; all seven referenced paths (cadence-patterns, gate-definitions, handoff-protocols, platform-implementation, team-size-modulation, automation-and-qa-tooling, example-orchestration) exist under references/, giving easy navigation without deep nesting.

3 / 3

Total

11

/

12

Passed

Description

100%

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, well-triggered, and clearly differentiated description written in third person. It names concrete actions, lists natural trigger terms, and explicitly disambiguates from neighboring skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'which skills run when, what locks at which gate, how handoffs occur' and named artifacts 'phases, lock points, handoff specs, gate definitions, and QA verification gates' across specific tools (Jira, Linear, Notion, Figma, GitHub) via MCP and CLI.

3 / 3

Completeness

Explicitly answers what (a temporal orchestration plan) and when (an explicit 'Triggers on...' clause plus a 'Does NOT fire for...' negative-trigger clause), satisfying the highest anchor.

3 / 3

Trigger Term Quality

'Triggers on integration orchestrator, delivery cadence, project orchestration, when does the brief lock, how to phase creative direction, design-development handoff, QA gate, agent-driven QA' covers natural terms a PM would actually say.

3 / 3

Distinctiveness Conflict Risk

'Distinct from creative-brief ... and creative-direction' plus 'Does NOT fire for project scoping ... aesthetic direction ... general project management' carves out a clear niche unlikely to conflict with sibling skills.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
rampstackco/claude-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.