CtrlK
BlogDocsLog inGet started
Tessl Logo

prp-orchestrate

Turns the current session into the operator's SDLC proxy for parallel PRP workstreams in isolated worktrees. It owns the combined outcome, steers autonomous deliveries, holds human and merge gates, verifies proof, and sequences 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.

69

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 orchestration policy with strong sequencing, explicit validation gates, and concrete commands, undermined by a broken reference: the required `templates/orchestration-run.md` is missing from the bundle, which lowers both actionability and navigation quality. Some reinforcement of the verification mandate across sections could be consolidated.

Suggestions

Ship `templates/orchestration-run.md` in the bundle (or inline its required run-file/Event-log format) — it is cited as required reading for both creating (section 2) and closing (section 7) a run, so its absence makes those steps unexecutable and breaks navigation.

State the review/CI proof requirement once in an authoritative place (e.g., `references/launching.md`) and reference it from the Role contract, section 4, and section 6 instead of restating it in all three.

For the gate digests and final handoff, either inline a minimal filled-in example or point to the exact section of the template that defines their format, so those steps are copy-paste actionable without the template.

DimensionReasoningScore

Conciseness

The body is dense, prescriptive policy with no padding and no explanation of concepts Claude already knows, but the review/CI-proof mandate is restated across the Role contract, section 4, and section 6, and the detached-CLI prohibition appears three times. Efficient with minor repetition that could be trimmed.

4 / 5

Actionability

Mostly executable guidance: the PRP store resolver bash block, `git worktree add -b <branch> .worktrees/<name> origin/<base>`, `timeout 1800 gh pr checks <n> --required --watch --fail-fast`, and `gh pr diff <n> --name-only` are copy-paste ready. It falls short of 5 because section 2 directs creating the run file from `templates/orchestration-run.md`, which is absent from the bundle, and the digest/handoff formats are only named, not shown.

4 / 5

Workflow Clarity

Clear sequenced phases (intake/gate, initialize, launch, monitor/steer, gates, integrate, close out) with explicit validation checkpoints: review and CI proof required before acceptance and again before each merge, merge-commit reachability from `origin/<base>`, rebase/conflict-resolution/validate/push feedback after each merge, and a two-restart cap with escalation. The seven-question design checklist in section 1 makes this match the anchor despite the missing template.

5 / 5

Progressive Disclosure

Structure is good and references are one level deep and clearly signaled ("Read `references/launching.md` before the first launch"), and that file exists in the bundle. However `templates/orchestration-run.md` is referenced twice as required reading for creating and closing the run and does not exist anywhere in the bundle, so navigation fails for the run format — more than a minor organization gap, though not the buried or deeply nested references of lower anchors.

3 / 5

Total

16

/

20

Passed

Description

91%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 with a rich set of natural quoted trigger phrases and third-person voice. The only weaknesses are mildly abstract capability phrasing and a couple of triggers broad enough to overlap with closely related orchestration skills.

DimensionReasoningScore

Specificity

"It owns the combined outcome, steers autonomous deliveries, holds human and merge gates, verifies proof, and sequences merges" lists several specific actions with named mechanisms (isolated worktrees, merge gates). Not 5 because phrases like "owns the combined outcome" and "verifies proof" stay abstract and coverage presumes familiarity with the PRP skill family.

4 / 5

Completeness

It explicitly answers both: the "what" (steers deliveries, holds gates, verifies proof, sequences merges) and the "when" ("Use when the user wants to ... or invokes $prp-orchestrate") with concrete trigger phrases, matching the anchor exactly.

5 / 5

Trigger Term Quality

Seven quoted natural trigger phrases — "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", "$prp-orchestrate" — give comprehensive coverage with synonyms and variations a user of this system would actually say.

5 / 5

Distinctiveness Conflict Risk

The PRP-pipeline framing and "$prp-orchestrate" invocation mark a clear niche, but generic triggers like "act as my orchestrator" and "orchestrate these features" could also fire for closely related orchestration or PRP-loop skills. Anchor 4 (mostly distinct, minor overlap risk with closely related skills) fits better than 5.

4 / 5

Total

18

/

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
Wirasm/prp
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.