Agent skill

Prp Deliver

by Wirasm in Wirasm/prp

This is an experimental skill. An agent skill from Wirasm/prp.

MITAuto-check passed

Install Prp Deliver

skills CLI
$ npx skills add Wirasm/prp --skill prp-deliver -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Wirasm/prp prp-deliver --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Wirasm/prp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/prp-deliver .claude/skills/prp-deliver && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
prp-deliver
GitHub stars
2.3k
Token cost
~1.7k tokens
SKILL.md length
985 words
Files
1
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

This is an experimental skill. An agent skill from Wirasm/prp.

  • Works in 6 steps: Resolve and plan → Implement and open the PR → Review independently → …
  • SKILL.md covers Ownership contract, 1. Resolve and plan, 2. Implement and open the PR and 3. Review independently, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Prp Deliver is an agent skill from Wirasm/prp. This is an experimental skill. Never use it unless the user explicitly tells you to invoke $prp-deliver.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Prompts, workflows and more for agentic engineering. The licence is MIT.

Example prompts

  • “/prp-deliver”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Resolve and plan
  2. Implement and open the PR
  3. Review independently
  4. Correct and re-review until ready
  5. Require green CI
  6. Return the outcome

What it can do on your machine

Read from SKILL.md and the folder at commit 4352925. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prp Deliver loads about 1.7k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 985 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Wirasm/prp at commit 4352925, republished under its MIT licence (© Wirasm). 985 words, ~1,747 tokens.

Download SKILL.mdSave it as .claude/skills/prp-deliver/SKILL.md (or your agent's skills folder).
name
prp-deliver
description
This is an experimental skill. Never use it unless the user explicitly tells you to invoke $prp-deliver.

Arguments: $ARGUMENTS (and $1, $2, ...) refer to the arguments given when this skill was invoked. Take them from the user's request; if absent, infer them from the conversation.

Deliver to a Reviewed PR

Own one outcome from source input to a published READY TO MERGE review and green CI. Act as the sub-orchestrator for this delivery: start and steer specialist agents, preserve their handoff artifacts, and do not implement or review the work in this context.

Input: $ARGUMENTS (if absent, use the conversation).

Ownership contract

  • Continue autonomously through plan, implementation, PR, review, correction, re-review, and CI. A published report is observable progress, not a pause point.
  • Run stages sequentially in the delivery owner's checkout. Only one implementation or correction agent may mutate it at a time.
  • Use a fresh agent for planning, a fresh agent for implementation, and a fresh independent agent for every review. Resume the implementation agent for corrections while it remains available.
  • Keep the plan path, implementation report, PR, latest review report, publication URL, and agent handles. Durable artifacts—not recalled summaries—cross context windows.
  • Keep a verbatim caller-decisions record of two kinds: constraints that bind the whole delivery, such as scope, base, and product decisions; and dispositions attached to one finding or blocker. A constraint applies to every later stage. A disposition applies only to the finding it names, while that finding is live. Update the record when the caller resolves a blocker, and pass each fresh agent the constraints plus the dispositions its stage acts on, verbatim.
  • Carry the burden of proof. Prove completion with green validation, the live PR, the complete published review, its READY TO MERGE verdict, and green required CI.
  • Stop only when a product decision, missing prerequisite primitive, inaccessible dependency, permission boundary, or repeated no-progress failure cannot be resolved autonomously. Report the exact decision or access needed and a recommendation.
  • Do not merge the PR. The caller owns the merge gate.

1. Resolve and plan

Accept an issue or tracker URL, PRD, document, existing .plan.md, free-form request, conversation context, or reviewed PR.

  • Review-only request or contributor PR: use $prp-review; this is not a delivery run.
  • Existing plan: use it. If it is issue-derived and lacks a verified Plan Publication, start a planning agent with $prp-plan publish <absolute-path> first.
  • Issue whose plan was already published: let $prp-implement resolve it from source metadata and require that agent to return the persisted absolute plan path.
  • Existing PR with a published PRP review: resolve its plan and implementation report, then enter correction or review without repeating completed stages.
  • Otherwise start a fresh agent with this prompt:

Invoke $prp-plan against <complete input>. Additional caller context: <relevant context and explicit base, if any>. Caller constraints, verbatim: <constraints or "None">. Return the absolute plan path, source and publication URLs, and any concrete blocker.

Require an absolute plan path before review and, for issue-derived plans, a verified published-plan URL.

2. Implement and open the PR

Start a fresh agent in the same checkout with this prompt:

Invoke $prp-implement on <absolute plan path or source issue> with base <explicit base, if any>. Caller constraints, verbatim: <constraints or "None">. Own implementation through validation, scoped commit, PR creation, linked PRD updates, and the implementation report. Return VALIDATION: GREEN, the resolved absolute plan path, absolute report path, and PR URL; otherwise return the concrete blocker.

Do not begin review without VALIDATION: GREEN, a live PR, and the implementation report.

Show full SKILL.md (421 more words)Show less

3. Review independently

Start a fresh agent with this prompt:

Invoke $prp-review on <PR URL or number> with scopes <requested scopes, if any>. Caller constraints, verbatim: <constraints or "None">. Publish the complete review to GitHub. Return the verdict, canonical review-report path, verified publication URL, and any review blocker.

Require the complete canonical review report, its absolute path, its complete GitHub publication, and the verified publication URL.

4. Correct and re-review until ready

For NEEDS FIXES, REVIEW INCOMPLETE, or any OPEN finding, send the complete review report—not an abbreviated finding list—to the implementation agent:

Continue this delivery by invoking $prp-implement in review-correction mode for <PR>. Read <plan>, <implementation report>, and the complete review at <review report>. Caller constraints and the dispositions for findings in this report, verbatim: <constraints and dispositions or "None">. Disposition every finding under the skill's fix-now, follow-up, and decline rules. Restore VALIDATION: GREEN and update the implementation report. Commit and push only when repository changes are required; for an evidence-only disposition, prove the PR head is unchanged.

Let the implementation agent disposition the report using its plan and code context. Prefer fixing valid, narrow, low-risk findings now; track only valuable distinct outcomes, and decline speculative or directionally wrong work without creating backlog noise.

If that agent is unavailable, start a fresh correction agent with the same complete artifact bundle. After every correction or disposition, start another fresh review agent with the caller constraints, the complete canonical report, and the dispositions under verification, then update the canonical publication. Repeat until READY TO MERGE with every finding terminal, or a genuine blocker survives without new evidence or progress. Do not wait for or check CI between rounds; CI clears once, at the end of the delivery, on the final head.

5. Require green CI

After READY TO MERGE, wait for every required CI check. A pending check is not green. Return a PR-caused failure and its complete evidence to the implementation agent and tell it to invoke $prp-implement in CI-correction mode, then run a fresh review against the changed head. When the repository has no required CI, rerun its authoritative local validation instead and record that evidence.

6. Return the outcome

Return the implemented outcome, absolute plan and implementation-report paths, PR URL, READY TO MERGE verdict, latest review-report path, GitHub publication URL, validation summary, and CI results. These are the proof the caller verifies before accepting the workstream. Only then suggest meaningful remaining non-blocking follow-ups. If genuinely blocked, return the same artifact bundle plus the exact blocker and recommended next action.

© Wirasm, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/prp-deliver of Wirasm/prp.

Open the folder on GitHubat commit 4352925

Compare with similar skills

Prp Deliver next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Prp Deliver compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prp Deliver this skillWirasm/prp2.3k—~1.7kAutomated safety check: PassMIT
No Explicit Anythedaviddias/Front-End-Checklist74k—~565Automated safety check: PassMIT
Experimental Designaiming-lab/AutoResearchClaw15k—~286Automated safety check: PassMIT
Experimentationcbrock84/headcount2k—~971Automated safety check: PassMIT
Flow Delivernyldn/claude-octopus4.2k1 repos~7.9kAutomated safety check: PassMIT
Deliver Specchrisbanes/skills1.1k—~1.4kAutomated safety check: PassApache-2.0

Similar skills

  • No Explicit Any

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing TypeScript files for type safety regressions, during code review of functions that handle external data, or when the codebase has ESLint warnings for…

    74k GitHub stars~565 tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Experimental Design

    aiming-lab/AutoResearchClaw

    Best practices for designing reproducible ML experiments. An agent skill from aiming-lab/AutoResearchClaw.

    15k GitHub stars~286 tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed
  • Experimentation

    cbrock84/headcount

    Designs, runs, and reads A/B tests and growth experiments — hypothesis, sample size, duration, and honest interpretation.

    2k GitHub stars~971 tokensUpdated 21 days ago
    Marketing & SEOAuto-check passed
  • Flow Deliver

    nyldn/claude-octopus

    Multi-AI validation, scoring, and review using available external providers (Double Diamond Deliver phase)

    4.2k GitHub starsUsed in 1 repo~7.9k tokens
    Frontend & DesignAuto-check passed
  • Deliver Spec

    chrisbanes/skills

    A skill your agent uses when explicitly asked to deliver an approved GitHub or local spec through a reviewed pull request, or when a Project controller delegates one claimed implementation ticket.

    1.1k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Deliver Artifacts

    openakita/openakita

    Deliver artifacts (files/images/voice) to current IM chat via gateway, returning a receipt.

    2k GitHub stars~288 tokensUpdated 15 days ago
    Auto-check passed

More from Wirasm/prp

All 37 skills in this repo
  • PRP Loop

    Wirasm/prp

    Runs the plan, implement and review pipeline detached in fresh headless sessions, looping review and fix until the pull request is clean.

    2.3k GitHub stars~894 tokensUpdated 7 days ago
    Auto-check passed
  • Runs a detached, resumable loop that plans, implements, opens a PR, reviews and fixes a feature across headless CLI sessions until the review is clean.

    2.3k GitHub stars~863 tokensUpdated 7 days ago
    Auto-check passed
  • Coordinates several PRP workstreams in isolated Git worktrees from one session, verifying proof, holding merge gates and sequencing the merges.

    2.3k GitHub stars~3.5k tokensUpdated 7 days ago
    Auto-check passed
  • Turns a PRD, issue or description into an implementation-ready plan grounded in codebase evidence, adding root-cause analysis for bugs and publishing issue plans back to the issue.

    2.3k GitHub stars~4.1k tokensUpdated 7 days ago
    Auto-check passed
  • PRP Plan

    Wirasm/prp

    Writes an implementation-ready plan for a feature, bug fix, refactor or chore from a PRD, issue or description, grounded in codebase evidence, and can post it back to the source issue.

    2.3k GitHub stars~4k tokensUpdated 7 days ago
    Auto-check passed
  • PRP Spike

    Wirasm/prp

    Settles a feasibility question with the smallest throwaway build that could disprove it, in an isolated worktree, ending in a verdict backed by evidence instead of a PR.

    2.3k GitHub stars~3.8k tokensUpdated 7 days ago
    Auto-check passed

Questions about Prp Deliver

What does Prp Deliver do?

This is an experimental skill. An agent skill from Wirasm/prp. Prp Deliver is an agent skill from Wirasm/prp. This is an experimental skill.

How do I install Prp Deliver in Claude Code?

Run `npx skills add Wirasm/prp --skill prp-deliver -a claude-code`. Or copy the skill folder (.agents/skills/prp-deliver in Wirasm/prp) into .claude/skills/prp-deliver in your project. Claude Code loads it when a task matches its description.

How do I install Prp Deliver in Codex?

Run `npx skills add Wirasm/prp --skill prp-deliver -a codex`. Or copy the skill folder (.agents/skills/prp-deliver in Wirasm/prp) into .agents/skills/prp-deliver in your project. Codex loads it when a task matches its description.

Can I use Prp Deliver in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Wirasm/prp --skill prp-deliver -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prp-deliver, .gemini/skills/prp-deliver, .github/skills/prp-deliver and .opencode/skills/prp-deliver in your project.

What does Prp Deliver need to run?

SKILL.md names no scripts, command-line tools or credentials: Prp Deliver is instructions for the agent only.

Does Prp Deliver access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Prp Deliver safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Prp Deliver use?

Prp Deliver is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prp Deliver use?

About 1.7k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Prp Deliver?

Skills that share tags, products or a category with Prp Deliver: No Explicit Any (thedaviddias/Front-End-Checklist, 74k stars), Experimental Design (aiming-lab/AutoResearchClaw, 15k stars), Experimentation (cbrock84/headcount, 2k stars) and Flow Deliver (nyldn/claude-octopus, 4.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prp Deliver?

Wirasm (a GitHub user) maintains it in Wirasm/prp, which has 2,258 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 2, 2026.

Source: Wirasm/prp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.