Coordinate spec-driven development for a GitHub, Jira, Linear, or other issue-tracker issue marked ready-to-spec by using write-product-spec and write-tech-spec, creating PRODUCT.md and TECH.md…
Install the "spec" agent skill from https://github.com/warpdotdev-demos/cloud-factory-demo/tree/main/.agents/skills/spec into .claude/skills/spec/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add warpdotdev-demos/cloud-factory-demo --skill spec -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "spec" agent skill from https://github.com/warpdotdev-demos/cloud-factory-demo/tree/main/.agents/skills/spec into .agents/skills/spec/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add warpdotdev-demos/cloud-factory-demo --skill spec -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "spec" agent skill from https://github.com/warpdotdev-demos/cloud-factory-demo/tree/main/.agents/skills/spec into .cursor/skills/spec/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add warpdotdev-demos/cloud-factory-demo --skill spec -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "spec" agent skill from https://github.com/warpdotdev-demos/cloud-factory-demo/tree/main/.agents/skills/spec into .gemini/skills/spec/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add warpdotdev-demos/cloud-factory-demo --skill spec -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "spec" agent skill from https://github.com/warpdotdev-demos/cloud-factory-demo/tree/main/.agents/skills/spec into .github/skills/spec/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add warpdotdev-demos/cloud-factory-demo --skill spec -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "spec" agent skill from https://github.com/warpdotdev-demos/cloud-factory-demo/tree/main/.agents/skills/spec into .opencode/skills/spec/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
spec
GitHub stars
320
Token cost
~2.1k tokens
SKILL.md length
1,081 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT
At a glance
Coordinate spec-driven development for a GitHub, Jira, Linear, or other issue-tracker issue marked ready-to-spec by using write-product-spec and write-tech-spec, creating PRODUCT.md and TECH.md…
Works in 10 steps: Identify the issue and repository → Verify required spec-writing skills → Post a spec-started status comment → …
Tasks that involve PRD writing
SKILL.md covers Workflow, Spec result and Guardrails
Reaches oz.warp.dev and oz.staging.warp.dev
What it does
Spec is an agent skill from warpdotdev-demos/cloud-factory-demo. Coordinate spec-driven development for a GitHub, Jira, Linear, or other issue-tracker issue marked ready-to-spec by using write-product-spec and write-tech-spec, creating PRODUCT.md and TECH.md, opening a pull request, and routing the issue onward.
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering PRD writing, Issue triage and Pull requests. It works with GitHub and Jira. The licence is MIT.
When your agent uses it
Tasks that involve PRD writing
Tasks that involve Issue triage
Tasks that involve Pull requests
Example prompts
“/spec”
Workflow steps
10 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit ab21d0c. 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
Hosts in commands or code, which the agent is likely to contact:
oz.warp.dev
oz.staging.warp.dev
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
Spec loads about 2.1k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 1,081 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~63
When it runs· the whole SKILL.md, loaded when a task matches
~2.1k
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.
Download SKILL.mdSave it as .claude/skills/spec/SKILL.md (or your agent's skills folder).
name
spec
description
Coordinate spec-driven development for a GitHub, Jira, Linear, or other issue-tracker issue marked ready-to-spec by using write-product-spec and write-tech-spec, creating PRODUCT.md and TECH.md, opening a pull request, and routing the issue onward.
Spec
Create checked-in product and technical specs for the issue passed in the user's prompt. Do not implement the product change.
This skill is a thin coordinator around the shared common-skills:
.agents/skills/write-product-spec/SKILL.md
.agents/skills/write-tech-spec/SKILL.md
Use those skills for the actual PRODUCT.md and TECH.md content. This skill owns issue intake, artifact location, branch/PR handoff, status comments, and readiness labels.
Workflow
1. Identify the issue and repository
Extract the issue URL, key, or number from the prompt. Determine whether it belongs to GitHub Issues, Jira, Linear, or another tracker.
Confirm the current checkout is the repository where the future implementation should happen. If the prompt does not identify one issue unambiguously, ask for clarification before writing specs.
2. Verify required spec-writing skills
Confirm these files exist in the checkout:
.agents/skills/write-product-spec/SKILL.md
.agents/skills/write-tech-spec/SKILL.md
If either file is missing, stop and report that the common spec skills must be installed before spec work can proceed. Do not write substitute specs from memory.
3. Post a spec-started status comment
For GitHub Issues, post a short status comment before doing spec work so issue subscribers know an agent has started.
Use the authenticated gh CLI when available. Include:
That automated Oz spec work has started.
That the output will be checked-in PRODUCT.md and TECH.md files.
A follow-along link to the Oz run (see Oz run URLs below).
Keep this comment concise.
Oz run URLs
When posting any follow-along or status link to an Oz cloud run, use the Oz web app URL — never invent links from the API host.
Correct format:
text
https://oz.warp.dev/runs/<run-id>
On staging / WarpDev, use:
text
https://oz.staging.warp.dev/runs/<run-id>
Rules:
Path is /runs/ (plural), never /run/.
Host is oz.warp.dev (or oz.staging.warp.dev), never app.warp.dev or app.staging.warp.dev.
Prefer a full run URL already provided by the runtime, action output, dispatcher, or logs. If you only have a run id, build the URL with the format above.
If you see https://app.warp.dev/run/<id> or https://app.warp.dev/runs/<id>, rewrite it to https://oz.warp.dev/runs/<id> before posting.
Do not use a GitHub Actions workflow run URL as the Oz follow-along link.
If no Oz run id or link is available yet, say the Oz follow-along link is not available yet rather than substituting another URL, and continue spec work.
4. Fetch tracker context
Use the best available integration in this order:
A relevant MCP server or native tracker tool
The tracker's authenticated CLI, such as gh
The tracker's API or web page
Fetch:
Full issue title and description
Comments and discussion
Existing labels, status, assignee, project, and linked issues
Attachments, screenshots, logs, reproduction steps, examples, and acceptance criteria
Related open issues, likely duplicates, dependencies, and nearby product work
Do not write specs solely from the issue title. Do not expose credentials or secrets while fetching tracker data.
If tracker context is missing critical product intent, post a concise blocker comment with the specific missing information and stop instead of inventing requirements.
Use a stable lowercase slug based on the tracker and issue number, such as github-123-add-export-options or linear-app-321-new-image-export-flow.
Create the specs/<issue-slug>/ directory if needed. If the repository already has a different established specs directory convention, follow it while still producing files named exactly PRODUCT.md and TECH.md.
6. Write PRODUCT.md with write-product-spec
Read .agents/skills/write-product-spec/SKILL.md and follow it to write specs/<issue-slug>/PRODUCT.md.
Provide the common skill with:
The issue title, description, comments, and linked context
roadmap.md and vision.md if present
Any existing product docs, specs, or related issues
The chosen output path
The product spec should define user-facing behavior, goals, non-goals, acceptance criteria, and open product questions. If material product questions remain, keep them explicit in PRODUCT.md.
7. Write TECH.md with write-tech-spec
After PRODUCT.md exists, read .agents/skills/write-tech-spec/SKILL.md and follow it to write specs/<issue-slug>/TECH.md.
Provide the common skill with:
The completed PRODUCT.md
The issue context and related comments
roadmap.md and vision.md if present
Relevant codebase paths, architecture constraints, tests, build commands, and dependencies found during research
The chosen output path
The technical spec should describe the implementation approach, affected code areas, alternatives considered, validation plan, rollout or migration concerns, and open technical questions.
Show full SKILL.md (410 more words)Show less
8. Create a specs pull request
Create a descriptive branch such as spec/issue-123-short-title.
Commit only the spec artifacts and any directly necessary documentation changes. Use a clear commit message. When committing, include:
Co-Authored-By: Oz <oz-agent@warp.dev>
Push the branch and open a GitHub pull request against the repository's default branch using the authenticated gh CLI.
The PR description should include:
A direct link to the original issue
Links to PRODUCT.md and TECH.md
Summary of the product and technical direction
Open questions or reviewer decisions needed
Whether the specs are ready for implementation after review
Do not include a closing keyword such as Closes #123; the spec PR does not implement the issue.
9. Publish the handoff
For GitHub Issues, post a final comment on the original issue with:
Link to the specs PR
Paths to PRODUCT.md and TECH.md
Whether the issue is ready for implementation after spec review
Any remaining product or technical questions
If both PRODUCT.md and TECH.md have no material open questions and the specs PR is ready for review, apply a spec-review label if available, such as spec-ready-for-review. Keep or remove Ready to spec according to the repository's convention.
Do not apply Ready to implement until the spec PR has been reviewed or the repository explicitly treats authored specs as implementation-ready without review.
If permissions prevent creating the branch, opening the PR, commenting, or updating labels, report the completed local artifacts and the permission error.
Do not implement the product change during spec work.
Do not close, assign, reprioritize, or otherwise mutate the issue unless the user asks.
Do not overwrite unrelated labels.
Do not claim specs are implementation-ready if material product or technical decisions remain unresolved.
Do not post raw secrets, tokens, private environment variables, command output dumps, or internal reasoning in status comments, specs, PR descriptions, or issue comments.
Do not write substitute PRODUCT.md or TECH.md content without reading and following the common write-product-spec and write-tech-spec skills.
Post progress sparingly: always post the spec-started comment, then post at most two additional progress comments before the final specs PR unless blocked or explicitly asked for more updates.
Spec 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.
Spec compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
Spec this skillwarpdotdev-demos/cloud-factory-demo
Support spec-driven development in projects that use OpenFastTrace, a system-requirements document in doc/systemrequirements.md, an arc42-style design in doc/design.md, and per-issue task plans in…
Sorts a backlog of open pull requests into must-merge, candidate, superseded and deferred, writes a triage doc and works the merge loop before a release.
Triages and works through GitHub issues and pull requests in the Q00/ouroboros repo as a maintainer, within a stated review boundary and clear limits on what it may change.
Daily outer loop that reviews human reactions to automated review-pr comments, synthesizes durable organizational knowledge, and opens a PR to update the review-pr skill when the feedback is worth…
Triage an incoming GitHub, Jira, Linear, or other issue-tracker issue against the current codebase and related open issues, then return a structured decision with exactly one…
Verify or reproduce visible product behavior by delegating to Oz's dedicated computer-use capability, requiring a native Oz video artifact for meaningful UI flows and durable Oz run/artifact links.
Sets up a beginner-friendly Oz cloud software factory that automatically triages new GitHub issues, specs issues labeled ready-to-spec, implements issues labeled ready-to-implement, reviews PRs, and…
Implement a fix or feature from a GitHub, Jira, Linear, or other issue-tracker issue by fetching issue context, inspecting the current codebase, making code changes, validating them, verifying…
Coordinate spec-driven development for a GitHub, Jira, Linear, or other issue-tracker issue marked ready-to-spec by using write-product-spec and write-tech-spec, creating PRODUCT.md and TECH.md…. Spec is an agent skill from warpdotdev-demos/cloud-factory-demo.md, opening a pull request, and routing the issue onward.
When should I use Spec?
Spec fits situations like: tasks that involve PRD writing; tasks that involve Issue triage; tasks that involve Pull requests.
How do I install Spec in Claude Code?
Run `npx skills add warpdotdev-demos/cloud-factory-demo --skill spec -a claude-code`. Or copy the skill folder (.agents/skills/spec in warpdotdev-demos/cloud-factory-demo) into .claude/skills/spec in your project. Claude Code loads it when a task matches its description.
How do I install Spec in Codex?
Run `npx skills add warpdotdev-demos/cloud-factory-demo --skill spec -a codex`. Or copy the skill folder (.agents/skills/spec in warpdotdev-demos/cloud-factory-demo) into .agents/skills/spec in your project. Codex loads it when a task matches its description.
Can I use Spec 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 warpdotdev-demos/cloud-factory-demo --skill spec -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spec, .gemini/skills/spec, .github/skills/spec and .opencode/skills/spec in your project.
What does Spec need to run?
SKILL.md names no scripts, command-line tools or credentials: Spec is instructions for the agent only.
Does Spec access the network?
SKILL.md names 2 domains. In commands or code: oz.warp.dev and oz.staging.warp.dev; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Is Spec 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 Spec use?
Spec 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 Spec use?
About 2.1k tokens (SKILL.md is roughly 8.3k 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 Spec?
Skills that share tags, products or a category with Spec: Oft Spec Driven Development (itsallcode/openfasttrace, 198 stars), Exposed Bug Fix Workflow (JetBrains/Exposed, 9.3k stars), Pre-Release PR Triage (jamiepine/voicebox, 57k stars) and Ouroboros Maintainer Triage (Q00/ouroboros, 6.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Spec?
warpdotdev-demos (a GitHub organization) maintains it in warpdotdev-demos/cloud-factory-demo, which has 320 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on August 12, 2026.