prp-loop

Runs the detached, resumable PRP pipeline in fresh headless CLI sessions, cycling plan, implementation, PR, review, and corrections with persisted state and safety bounds. Use only when the user explicitly asks to "run the full PRP loop", "run this detached", "continue across context windows", use headless autonomous execution, resume a saved loop, or invokes $prp-loop. Use prp-issue for ordinary end-to-end delivery.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%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.

An actionable, well-structured skill body with executable commands and a clear cyclic workflow backed by validation and safety bounds. The only slack is a small amount of historical commentary that could be cut for token efficiency.

Suggestions

Trim or remove the 'UX note' about the retired Ralph loop — it is historical context that does not help Claude execute the current skill.

Inline the one or two exact validation commands (e.g. how to run --validate or read the green sentinel from the state file) so the workflow checkpoints are fully self-contained rather than delegated to the script.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanation of what a PR or codex is), but the 'UX note' contrasting the retired Ralph loop is historical context that does not earn its tokens and could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready executable commands for the common cases — starting ('uv run ... prp_loop.py "$ARGUMENTS" --cli codex'), resuming ('--resume'), stopping after a stage ('--until implement'), and an authoritative green check ('--validate "<cmd>"').	5 / 5
Workflow Clarity	The plan→implement→PR→review→cycle sequence is clearly enumerated with validation checkpoints (VALIDATION: GREEN sentinel, --validate) and explicit halt conditions; because validation is described rather than missing, the destructive-cap does not apply, though the exact validation invocations are delegated to the script rather than inlined.	4 / 5
Progressive Disclosure	A short, well-sectioned overview that points one level deep to a single real bundle script (scripts/prp_loop.py, confirmed present), with no nested references and easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

100%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 covers concrete capabilities, natural trigger terms, both what-and-when, and explicit conflict avoidance with a sibling skill. Every dimension lands at the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('cycling plan, implementation, PR, review, and corrections') alongside concrete features ('fresh headless CLI sessions', 'persisted state and safety bounds'), giving comprehensive coverage of the pipeline's capabilities.	5 / 5
Completeness	Clearly answers both 'what' (runs the detached, resumable PRP pipeline cycling plan/implementation/PR/review/corrections) and 'when' via an explicit 'Use only when the user explicitly asks to...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would actually say ('run the full PRP loop', 'run this detached', 'continue across context windows', 'resume a saved loop') plus the invocation token $prp-loop, covering synonyms and the explicit trigger surface.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (the detached cyclic loop) with distinct triggers and explicit deconfliction guidance ('Use prp-issue for ordinary end-to-end delivery'), minimizing overlap with sibling skills.	5 / 5
	Total	20 / 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: Wirasm/prp
Path: .agents/skills/prp-loop/SKILL.md
Commit: 9724799

Reviewed: ~9 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.