New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Prd Os

by assafkip in assafkip/kipi-system

PRD creation and PRD execution operating system. An agent skill from assafkip/kipi-system.

MITAuto-check passedProduct & Project Management

Install Prd Os

skills CLI
$ npx skills add assafkip/kipi-system --skill prd-os -a claude-code

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

GitHub CLI
$ gh skill install assafkip/kipi-system prd-os --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/assafkip/kipi-system.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/prd-os/skills/prd-os .claude/skills/prd-os && 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
prd-os
GitHub stars
112
Token cost
~1.6k tokens
SKILL.md length
804 words
Files
2 (incl. references)
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

PRD creation and PRD execution operating system. An agent skill from assafkip/kipi-system.

  • The founder asks to turn a rough idea into a PRD
  • SKILL.md covers Status, State machines, Commands and Non-negotiables, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Run a Codex review on a PRD

What it does

Prd Os is an agent skill from assafkip/kipi-system. PRD creation and PRD execution operating system. Use when the founder asks to turn a rough idea into a PRD, run a Codex review on a PRD or issue, decompose an approved PRD into issue specs, or execute an issue with scope enforcement and receipt-based closeout. Not for general product ideation or casual drafting; this is the formal gated workflow.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/fable-discipline-v1.md`).

It sits in Product & Project Management, covering PRD writing. The repository describes itself as: Your AI brain, externalized. It remembers everything you do, then becomes whatever role you need. Same skeleton can run as your chief of staff, lawyer, PM, or investigator. Plain… The licence is MIT.

When your agent uses it

  • The founder asks to turn a rough idea into a PRD
  • Run a Codex review on a PRD
  • Decompose an approved PRD into issue specs
  • Execute an issue with scope enforcement and receipt-based closeout

Example prompts

  • “/prd-os”

What it can do on your machine

Read from SKILL.md and the folder at commit 16d4724. 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

Prd Os loads about 1.6k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 89 tokens; SKILL.md has 804 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.4k

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 assafkip/kipi-system at commit 16d4724, republished under its MIT licence (© assafkip). 804 words, ~1,650 tokens.

Download SKILL.mdSave it as .claude/skills/prd-os/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
prd-os
description
PRD creation and PRD execution operating system. Use when the founder asks to turn a rough idea into a PRD, run a Codex review on a PRD or issue, decompose an approved PRD into issue specs, or execute an issue with scope enforcement and receipt-based closeout. Not for general product ideation or casual drafting; this is the formal gated workflow.

prd-os

Formal, repo-native workflow for PRD creation and PRD execution inside Claude Code. An independent reviewer is the gate at both phases: Codex, or a Claude senior-staff-engineer subagent when Codex is unavailable.

Whichever reviewer ran is recorded in the findings ledger as codex-review, codex-adversarial, claude-review, or claude-adversarial. Stamping one for another puts false provenance in a repo whose thesis is receipts. Enforcement is partial and the boundary matters: the REVIEWER_SOURCES validator in findings_writer.py refuses any value outside that set (so manual and plan cannot fill a review gate), but no checker can tell which of the four actually ran. That last step is a model decision with no gate behind it.

Status

Operational. Plugin version is authoritative in .claude-plugin/plugin.json; the state machines, commands, and gates below are shipped and enforced by the runner scripts. CHANGELOG.md carries the per-version history.

State machines

PRD: idea -> draft -> in-review -> draft (on revise) -> approved -> archived.

Issue: open -> in-progress -> closed. Receipts required between approve and close: verified, reviewed, findings_triaged.

Commands

PRD side (this plugin): /prd-start, /prd-review, /prd-triage, /prd-approve, /prd-split, /prd-archive, /prd-personas, /prd-map.

There is no /prd-revise command. A PRD returns to draft via prd_runner.py advance draft after triage.

Issue side ships in the kipi-dsse plugin, not this one: /issue-start <id>, /issue-approve, /issue-verify, /issue-review, /issue-closeout, /issue-amend. The two plugins share the .prd-os/ state directory and the findings ledger.

Bootstrap: /prd-os-init (runs once per repo to scaffold .prd-os/, write config.json, and add the runtime state dir to .gitignore). It does NOT register hooks -- that claim shipped through 0.17.0 with no code behind it (ASK-402). Hooks come from this plugin's hooks/hooks.json when the plugin is enabled.

Ledger CLI (no slash command; run through kipi judgment <subcommand>): the Judgment Compiler freezes decision-time workflow context for each triage decision into an append-only hash-chained receipt ledger. See scripts/judgment_compiler.py and the operator guide.

Non-negotiables

  • PRD drafting must not drift into implementation. Scope enforcement restricts edits to the PRD file during drafting.
  • Issue planning stays in open status. The stop-gate does not arm until /issue-approve transitions to in-progress.
  • Empty allowed_files means deny-all except the active spec itself (control-plane carve-out). This is a fixed contract; do not propose allow-all behavior.
  • Every finding gets a disposition before approve or closeout. The enum is exactly pending, accepted, rejected, deferred (DISPOSITIONS in findings_writer.py); the writer refuses anything else. No finding may be left pending. rejected and deferred require --rationale.
  • Concurrent PRD and issue contexts are blocked. /prd-start refuses if an issue is in-progress; /issue-start refuses if a PRD is in-review.
  • The reviewer never edits. Claude is the sole editor. Codex runs through /codex:review and /codex:adversarial-review and returns findings for Claude to triage; a Claude reviewer subagent runs read-only under the same contract.
  • Runtime state (.claude/state/active-{prd,issue}.json) is never committed. The bootstrap command adds the state directory to .gitignore.
  • Out-of-scope findings are never dropped. A deferred disposition auto-creates an open spillover item, and gates run stays red until it is resolved. See Spillover below.
Show full SKILL.md (320 more words)Show less

Spillover: out-of-scope findings never vanish

An issue found mid-work that is out of scope must be CAPTURED, not mentioned. The ledger is .prd-os/spillover.jsonl; the standing gate enforces it.

  • Capture: prd_runner.py spillover add --source <id> --severity <medium|high|major|blocker> --desc "..." (a deferred triage disposition does this automatically; rejected does not). A new minor/low/nit is refused (exit 2): fix it now or reject it with a reason.
  • Gate: prd_runner.py gates run FAILS while any item is open — the same no-bypass re-proof as the registered gates. Forgetting an item = a red gate.
  • Resolve: spillover resolve <id> --resolution-ref <closed-issue-id> (refuses unless that issue is actually closed) or --void "<reason>" for a non-item.
  • Report: closeout/archive name each item, its resolving issue, the fix, and the system impact. See the .claude/rules/no-orphan-findings.md rule.

Portable core vs repo-local split

Plugin (portable): commands, runner scripts, hooks, templates, review rubric, findings schema, tests.

Repo (local): .prd-os/config.json, .prd-os/prds/, .prd-os/issues/, .prd-os/findings/, .claude/state/.

Ledger files (spillover.jsonl, gates.jsonl, judgments.jsonl) resolve to the shared worktree ledger root, so parallel worktrees write to one ledger rather than diverging copies.

Execution discipline

fable-discipline is this plugin's execution-discipline layer (recon before edit, verify against a copy with a negative self-test, single-writer chokepoints, scar-anchored why-comments). /issue-start loads it for PRD/DSSE work; the fable-discipline-auto-invoke rule loads it for everything else. Its deterministic slice (test isolation) is enforced by the fable-discipline-lint hook in this plugin's hooks.json.

Load-path warning

These commands run from the marketplace clone (~/.claude/plugins/marketplaces/<mp>/), not from a project's plugins/ directory. An edit to a project copy is inert until the clone is refreshed. Confirm which copy is live before relying on a change to command or skill text.

Upgrade policy

Plugin follows semver. MAJOR bumps may change the state machine, remove commands, or change the findings schema; they require operator action. MINOR bumps are additive. PATCH bumps are fixes. Config schema version is tracked separately in .prd-os/config.json and bumps only when the runner cannot load older configs without migration. See CHANGELOG.md.

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

Files

SKILL.md and 1 other file (references) in plugins/prd-os/skills/prd-os of assafkip/kipi-system.

  • SKILL.md
  • references/fable-discipline-v1.md

Open the folder on GitHubat commit 16d4724

Compare with similar skills

Prd Os 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.

Prd Os compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prd Os this skillassafkip/kipi-system112—~1.6kAutomated safety check: PassMIT
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Ralph Tui Create Beadssubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT
Trellis Brainstormanjiemo/SunnyBeach1787 repos~4kAutomated safety check: PassApache-2.0
Ralph Tui Create Beads Rustsubsy/ralph-tui2.5k1 repos~2.8kAutomated safety check: PassMIT
Ralph Tui Create JSONsubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT

Similar skills

  • CCPM Project Management

    automazeio/ccpm

    Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed

  • Ralph Tui Create Beads

    subsy/ralph-tui

    Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.

    2.5k GitHub starsUsed in 1 repo~2.6k tokens
    Product & Project ManagementAuto-check passed

  • Trellis Brainstorm

    anjiemo/SunnyBeach

    Guides collaborative requirements discovery before implementation.

    178 GitHub starsUsed in 7 repos~4k tokens
    Product & Project ManagementAuto-check passed

  • Ralph Tui Create Beads Rust

    subsy/ralph-tui

    Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).

    2.5k GitHub starsUsed in 1 repo~2.8k tokens
    Product & Project ManagementAuto-check passed

  • Ralph Tui Create JSON

    subsy/ralph-tui

    Convert PRDs to prd.json format for ralph-tui execution. An agent skill from subsy/ralph-tui.

    2.5k GitHub starsUsed in 1 repo~2.6k tokens
    Product & Project ManagementAuto-check passed

  • Prd Generator

    jamesrochabrun/skills

    Generate comprehensive Product Requirements Documents (PRDs) for product managers.

    216 GitHub starsUsed in 2 repos~3.8k tokens
    Product & Project ManagementAuto-check passed

More from assafkip/kipi-system

All 14 skills in this repo

  • Deck AI

    assafkip/kipi-system

    Turns a markdown file into a themed, image-rich slide deck exported as PDF, using Slidev for layouts and Unsplash for photos, all run locally.

    112 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check: notes

  • Unified Design Router

    assafkip/kipi-system

    Routes visual design requests to built-in logo, corporate identity, slide, banner, social photo and icon workflows, backed by style data and AI image generation.

    112 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

  • Improve Idea Critique

    assafkip/kipi-system

    Judges a pasted tip, post or video summary against what the kipi system already has, and returns adopt, skip or already-built with the files that back the verdict.

    112 GitHub stars~729 tokensUpdated yesterday
    Auto-check passed

  • Fable Discipline

    assafkip/kipi-system

    Teaches staged, verifiable coding habits for multi-file tasks and ships a hook that blocks tests from touching live data.

    112 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

  • Root-Cause Analysis Writer

    assafkip/kipi-system

    Writes a structured, blameless root-cause analysis for a defect that escaped a test or gate, separating surface from structural causes and linting the result.

    112 GitHub stars~796 tokensUpdated yesterday
    Auto-check passed

  • Architecture Review

    assafkip/kipi-system

    Surfaces architectural friction in real code — shallow modules, tight coupling, untested seams — and proposes deepening refactors using Ousterhout's deep-module principle (small interface hiding a…

    112 GitHub stars~817 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Prd Os

What does Prd Os do?

PRD creation and PRD execution operating system. An agent skill from assafkip/kipi-system. Prd Os is an agent skill from assafkip/kipi-system. PRD creation and PRD execution operating system.

When should I use Prd Os?

Prd Os fits situations like: the founder asks to turn a rough idea into a PRD; run a Codex review on a PRD; decompose an approved PRD into issue specs; execute an issue with scope enforcement and receipt-based closeout.

How do I install Prd Os in Claude Code?

Run `npx skills add assafkip/kipi-system --skill prd-os -a claude-code`. Or copy the skill folder (plugins/prd-os/skills/prd-os in assafkip/kipi-system) into .claude/skills/prd-os in your project. Claude Code loads it when a task matches its description.

How do I install Prd Os in Codex?

Run `npx skills add assafkip/kipi-system --skill prd-os -a codex`. Or copy the skill folder (plugins/prd-os/skills/prd-os in assafkip/kipi-system) into .agents/skills/prd-os in your project. Codex loads it when a task matches its description.

Can I use Prd Os 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 assafkip/kipi-system --skill prd-os -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prd-os, .gemini/skills/prd-os, .github/skills/prd-os and .opencode/skills/prd-os in your project.

What does Prd Os need to run?

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

Does Prd Os 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 Prd Os 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 Prd Os use?

Prd Os 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 Prd Os use?

About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.7k tokens, read only when the agent opens those files.

What are the alternatives to Prd Os?

Skills that share tags, products or a category with Prd Os: CCPM Project Management (automazeio/ccpm, 8.4k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Trellis Brainstorm (anjiemo/SunnyBeach, 178 stars) and Ralph Tui Create Beads Rust (subsy/ralph-tui, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prd Os?

assafkip (a GitHub user) maintains it in assafkip/kipi-system, which has 112 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 7, 2026.

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