orchestrate

Use when driving one or more tasks end to end from the local bare-repo root — a feature designed with the user first when its scope is open, or a ready list of tasks — ordering them, cutting a worktree per task, handing each to a subagent that runs new-feat, running prep-pr with every finding fixed rather than reported, and shepherding each pull request to a squash merge and worktree teardown. Not for a one-file change, and not outside the bare repo.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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, highly actionable orchestration workflow with explicit validation checkpoints and error-recovery feedback loops. The body is dense and mostly lean, though a few rationale asides and directive-prose steps could be tightened or made more copy-paste ready. Progressive disclosure is handled cleanly with a single one-level-deep reference.

Suggestions

Tighten inline rationale asides (e.g., the 'a wrong assumption in a plan is copied faithfully...' sentence) to the operational rule, moving the why to references/gotchas.md where the full reasoning already lives.

Add copy-paste command templates for the directive-prose steps (Step 1 context gathering, Step 3 dispatch) — e.g., a minimal dispatch message skeleton — to push actionability toward fully executable.

A few commands use bare placeholders like <dir>/<prefix>; a one-line worked example with concrete values would make the worktree and merge commands copy-paste ready for the common case.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and dense with operational specifics rather than generic concepts Claude already knows, but inline rationale asides ('which is the point...', 'a wrong assumption in a plan is copied faithfully...') could be trimmed. Not a 5 because some explanatory prose does not strictly earn its place; not a 3 because the body is broadly lean and assumes competence.	4 / 5
Actionability	Provides concrete executable commands (git worktree add, bun install, gh pr view --json, gh pr merge --squash) and a concrete dispatch contract, but several steps (Step 1 context gathering, Step 3 dispatch framing) are directive prose without copy-paste code. Not a 5 because not every step is copy-paste ready; not a 3 because the commands present are executable and specific.	4 / 5
Workflow Clarity	Clearly sequenced Steps 00→0→1-5 with explicit validation checkpoints ('No subagent's stated verification counts... check the mechanical half yourself') and feedback loops for error recovery (subagent-death handling, DIRTY/BEHIND rebase, never merge red).	5 / 5
Progressive Disclosure	Body is the orchestration overview; the full gotcha table is split to references/gotchas.md (a real file), referenced one level deep and clearly signaled ('The full table, with the reason behind each, is references/gotchas.md'). Easy navigation via section headers.	5 / 5
	Total	18 / 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, specific description that clearly states what the skill does and when to use it, including negative triggers. Trigger-term coverage is good but could add a few more natural synonyms. It is distinguishable from peer skills with negligible overlap risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'ordering them, cutting a worktree per task, handing each to a subagent that runs new-feat, running prep-pr... shepherding each pull request to a squash merge and worktree teardown' — covering the orchestration flow comprehensively.	5 / 5
Completeness	Explicitly answers both what (the full chain of actions) and when ('Use when driving one or more tasks end to end'), and adds negative triggers ('Not for a one-file change, and not outside the bare repo').	5 / 5
Trigger Term Quality	'driving one or more tasks end to end', 'a feature... open scope', and 'a ready list of tasks' are natural phrases a user would say, but a few common synonyms are missing. Not a 3 because the coverage is good rather than partial; not a 5 because synonyms like 'multi-task', 'feature work', or 'PR workflow' are absent.	4 / 5
Distinctiveness Conflict Risk	Highly specific niche — 'local bare-repo root', 'new-feat', 'prep-pr', 'squash merge' — with explicit out-of-scope boundaries, giving minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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: xchromo/osn
Path: .claude/skills/orchestrate/SKILL.md
Commit: 5438649

Reviewed: ~11 hours ago

Table of Contents

Discovery Implementation Validation

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.