prp-orchestrate

Turn the current session into an SDLC orchestrator that coordinates parallel background agents running PRP skills in isolated worktrees - decompose work into workstreams, launch and steer agents with the native agent tools, hold review gates as the user's proxy, and sequence merges. Use when the user wants to "spawn N agents in separate worktrees", "run prp-issue on these issues in parallel", "orchestrate these features", "act as my orchestrator", "coordinate agents through the PRP pipeline", "ship these issues in parallel", or invokes /prp-orchestrate.

Quality

96%

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

92%Weight 40%Scale 1-3

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 tightly written, highly actionable, well-sequenced orchestration workflow that avoids concept re-explanation and supplies concrete commands with validation checkpoints. The main weakness is a referenced bundle file (templates/orchestration-run.md) that does not exist, slightly undermining progressive disclosure.

Suggestions

Ship the referenced templates/orchestration-run.md (the run-file format) alongside references/launching.md, or inline its essential fields so the body does not depend on a missing file.

Verify every path mentioned in SKILL.md (references/ and templates/) resolves to a real bundle file before treating the skill as complete.

Consider moving the byte-identical PRP store resolver block into a shared script reference if it is duplicated across PRP skills, to keep the overview lean.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence — it never explains what a worktree, git, or a PR is — and every line is procedure-specific (store resolver, tool names, hard rules); despite its length the density is earned for a genuinely complex multi-phase orchestration, so it is not the verbosity-penalized 2.	3 / 3
Actionability	Provides copy-paste-ready executable bash (the PRP store resolver block) and concrete commands/paths ("gh pr diff <n> --name-only", "git log origin/<base>..<base>", "$PRP_DIR/orchestration/<run-id>.md") with specific tool calls, matching the fully-executable anchor; not 2 because the guidance is complete rather than pseudocode or missing key details.	3 / 3
Workflow Clarity	Seven phases are clearly sequenced (Intake → Initialize → Launch → Monitor → Gates → Integrate → Close) with explicit checkpoints (the Phase 1 CHECKPOINT, "Re-check gh pr checks before the next merge") and feedback loops ("blocked report → gate it… SendMessage the decision back"); not 2 because validation checkpoints are explicit rather than implicit.	3 / 3
Progressive Disclosure	SKILL.md is a clear overview with one-level-deep, well-signaled references ("read it before the first launch") to references/launching.md, which exists — but it also points to templates/orchestration-run.md, which is not present in the bundle; per the guideline to score against actual bundle structure, a missing referenced file breaks clean navigation, so it is capped at 2 rather than 3.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong across all dimensions: it states concrete capabilities, provides many natural trigger phrases, explicitly covers both what and when, and occupies a clearly distinct niche. It does not over-claim or pad with fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "decompose work into workstreams, launch and steer agents with the native agent tools, hold review gates as the user's proxy, and sequence merges" — matching the anchor for multiple specific concrete actions; it does not fall to 2 because the action list is comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers both what (an SDLC orchestrator that coordinates parallel agents) and when ("Use when the user wants to…" with concrete triggers); it is above 2 because the when-clause is explicit, not merely implied.	3 / 3
Trigger Term Quality	Quotes natural phrases a user would actually say — "spawn N agents in separate worktrees", "run prp-issue on these issues in parallel", "act as my orchestrator", "ship these issues in parallel" — plus the /prp-orchestrate invocation, giving strong coverage of common variations rather than just one keyword.	3 / 3
Distinctiveness Conflict Risk	The PRP-pipeline / worktree-orchestration niche is sharply scoped with distinct triggers unlikely to fire for unrelated skills; not 2 because the triggers are specific enough to avoid meaningful overlap.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Wirasm/prp
Path: .claude/skills/prp-orchestrate/SKILL.md
Commit: 1142738

Reviewed: 11 days 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.