New: 97,000+ 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

Specify

by RafaelGB in RafaelGB/Obsidian-ZettelFlow

Stage 1 of the SDD pipeline — write a ZettelFlow spec into a GitHub issue body (problem, value, functional requirements, testable acceptance criteria, capability disclosure, out-of-scope).

MITAuto-check passedProduct & Project Management

Install Specify

skills CLI
$ npx skills add RafaelGB/Obsidian-ZettelFlow --skill specify -a claude-code

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

GitHub CLI
$ gh skill install RafaelGB/Obsidian-ZettelFlow specify --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/RafaelGB/Obsidian-ZettelFlow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/specify .claude/skills/specify && 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
specify
GitHub stars
174
Token cost
~759 tokens
SKILL.md length
358 words
Files
3 (incl. references)
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

Stage 1 of the SDD pipeline — write a ZettelFlow spec into a GitHub issue body (problem, value, functional requirements, testable acceptance criteria, capability disclosure, out-of-scope).

  • Works in 3 steps: If an issue number is given: gh issue… → If new work with no issue: the agent… → Spec content (always in the issue body)
  • The user says specify
  • SKILL.md covers Owner, Steps and Quality bar (the stage-1 gate)
  • Calls gh and npm

What it does

Specify is an agent skill from RafaelGB/Obsidian-ZettelFlow. Stage 1 of the SDD pipeline — write a ZettelFlow spec into a GitHub issue body (problem, value, functional requirements, testable acceptance criteria, capability disclosure, out-of-scope). Use when the user says "specify", "write a spec", "spec out issue

Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/diagrams.md` and `references/verification.md`).

It sits in Product & Project Management, covering User stories. It works with GitHub and Obsidian. The repository describes itself as: ZettelFlow is a plugin for Obsidian that helps you to create and manage your notes in a Zettelkasten way. The licence is MIT.

When your agent uses it

  • The user says specify
  • Tasks that involve User stories

Example prompts

  • “specify”
  • “write a spec”
  • “/specify”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. If an issue number is given: gh issue view to read the existing body. The agent will
  2. If new work with no issue: the agent creates a new issue with gh issue create --title "..." --body "...".
  3. Spec content (always in the issue body)

What it can do on your machine

Read from SKILL.md and the folder at commit 27647ea. 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

    Shell commands in SKILL.md call:

    • gh
    • npm

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

  • Network

    No URLs in SKILL.md. Its commands use gh and npm, which can reach the network depending on how they are called.

    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

Specify loads about 759 tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 358 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~759
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.6k

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 RafaelGB/Obsidian-ZettelFlow at commit 27647ea, republished under its MIT licence (© RafaelGB). 358 words, ~759 tokens.

Download SKILL.mdSave it as .claude/skills/specify/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
specify
description
Stage 1 of the SDD pipeline — write a ZettelFlow spec into a GitHub issue body (problem, value, functional requirements, testable acceptance criteria, capability disclosure, out-of-scope). Use when the user says "specify", "write a spec", "spec out issue

/specify — write the spec into the GitHub issue

Stage 1 of the SDD pipeline. The spec is the issue body — it fixes WHAT and WHY, with acceptance criteria the change is measured against at stage 5.

No local files — specs live in GitHub Issues, not in a specs/ directory.

Owner

Delegate to the spec-author agent. Give it the issue number or a description; it reads the issue, the relevant code, and docs/development/constitution.md, then writes the spec.

Steps

  1. If an issue number is given: gh issue view <N> to read the existing body. The agent will update it with the spec content using gh issue edit <N> --body "...".
  2. If new work with no issue: the agent creates a new issue with gh issue create --title "..." --body "...".
  3. Spec content (always in the issue body):
    • Problem / Value — the user- or maintainer-facing pain; for obsidian-score items, name the guideline/score impact.
    • Functional requirements (FR-n) — numbered, atomic, so plan/tasks can cite them.
    • Acceptance criteria (AC-n) — testable, Given/When/Then where possible. Always include the concrete guardrail (e.g. "npm run lint:obsidian reports no new violations", "es.ts has every key en.ts has").
    • Capability disclosure — tick file-system / network / clipboard / script-exec / none (constitution §VII).
    • Diagrams — at least one Mermaid diagram (flow / state / sequence). Rules and templates: references/diagrams.md. Show empty/loading/error states (UX-first), annotate expensive edges (performance) and where logs/events fire (observability).
    • How to verify — the last section, always: the automated proofs (command → the ACs they prove) and a hand-walkable script a tester (or the user) can follow to see it work, with preconditions, numbered steps, the empty state and the negative. Rules and template: references/verification.md. Automate what can be automated; name the reason for every step that stays manual.
    • Out of scope / Open questions — keep the change small; surface unknowns now.
Show full SKILL.md (67 more words)Show less

Quality bar (the stage-1 gate)

  • Every acceptance criterion is observable and testable — not "works well".
  • Every acceptance criterion has a prover in How to verify — a command or a numbered manual step. An AC nobody can check is not an AC.
  • Capabilities are disclosed.
  • Scope is bounded (explicit out of scope).
  • No solution design leaked in.

Add the sdd:planned label when the spec is ready for /plan.

© RafaelGB, 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 2 other files (references) in .claude/skills/specify of RafaelGB/Obsidian-ZettelFlow.

  • SKILL.md
  • references/diagrams.md
  • references/verification.md

Open the folder on GitHubat commit 27647ea

Compare with similar skills

Specify 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.

Specify compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Specify this skillRafaelGB/Obsidian-ZettelFlow174—~759Automated safety check: PassMIT
Create Issuetradingstrategy-ai/frontend150—~607Automated safety check: PassNone
Specgetsentry/sentry-react-native1.8k—~1.1kAutomated safety check: PassMIT
Abo Issue Watcherjeeftor/audiobook-organizer189—~417Automated safety check: PassMIT
Execute Issuelbedner/aegis-stack143—~1.1kAutomated safety check: PassMIT
Create Issue Gatesickn33/agentic-awesome-skills47k2 repos~696Automated safety check: PassMIT

Similar skills

  • Create Issue

    tradingstrategy-ai/frontend

    Creates a new GitHub issue with structured user story format, acceptance criteria, and project integration.

    150 GitHub stars~607 tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

  • Spec

    getsentry/sentry-react-native

    Official

    Produce a verified spec — problem, desired outcome, and acceptance criteria — before building.

    1.8k GitHub stars~1.1k tokensUpdated today
    Product & Project ManagementAuto-check passed

  • Abo Issue Watcher

    jeeftor/audiobook-organizer

    Inspect Audiobook Organizer GitHub issues, comments, acceptance criteria, linked PRs, and next steps.

    189 GitHub stars~417 tokensUpdated 27 days ago
    Product & Project ManagementAuto-check passed

  • Execute Issue

    lbedner/aegis-stack

    A skill your agent uses when handed a GitHub issue (number or URL) to execute end to end.

    143 GitHub stars~1.1k tokensUpdated today
    Product & Project ManagementAuto-check passed

  • Create Issue Gate

    sickn33/agentic-awesome-skills

    A skill your agent uses when starting a new implementation task and an issue must be created with strict acceptance criteria gating before execution.

    47k GitHub starsUsed in 2 repos~696 tokens
    Product & Project ManagementAuto-check passed

  • Zoonk Issue Planning

    zoonk/zoonk

    Break work into GitHub issues, epics, or dependencies when the user explicitly requests an issue breakdown.

    157 GitHub stars~707 tokensUpdated 5 days ago
    Product & Project ManagementAuto-check passed

More from RafaelGB/Obsidian-ZettelFlow

All 9 skills in this repo

  • New Action

    RafaelGB/Obsidian-ZettelFlow

    Scaffold a new ZettelFlow action following the project's 4-file convention (Action / Component / Settings / SettingsReader), register it, and document it.

    174 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Obsidian Plugin Quality

    RafaelGB/Obsidian-ZettelFlow

    Audit ZettelFlow against the official Obsidian plugin guidelines and the Community-hub automated review / quality score.

    174 GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Release

    RafaelGB/Obsidian-ZettelFlow

    Cut a compliant ZettelFlow plugin release — version bump, versions.json, build, tag, and a GitHub Release whose notes follow the house format.

    174 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Sdd

    RafaelGB/Obsidian-ZettelFlow

    The Spec-Driven Development pipeline for ZettelFlow — the end-to-end flow (constitution → specify → plan → tasks → implement → verify) and which skill/agent owns each stage.

    174 GitHub stars~842 tokensUpdated today
    Auto-check passed

  • TDD

    RafaelGB/Obsidian-ZettelFlow

    The test-driven development workflow for ZettelFlow — write a failing test first, run jest, use the Obsidian mock and the bare-specifier alias mappings, and know which code is unit-testable.

    174 GitHub stars~724 tokensUpdated today
    Auto-check passed

  • Implement

    RafaelGB/Obsidian-ZettelFlow

    Stage 4 of the SDD pipeline — execute a ZettelFlow task checklist (in a GitHub issue comment) test-first (red → green → refactor), one commit per advance, keeping npm run verify green and CI green…

    174 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Specify

What does Specify do?

Stage 1 of the SDD pipeline — write a ZettelFlow spec into a GitHub issue body (problem, value, functional requirements, testable acceptance criteria, capability disclosure, out-of-scope). Specify is an agent skill from RafaelGB/Obsidian-ZettelFlow. Stage 1 of the SDD pipeline — write a ZettelFlow spec into a GitHub issue body (problem, value, functional requirements, testable acceptance criteria, capability disclosure, out-of-scope).

When should I use Specify?

Specify fits situations like: the user says specify; tasks that involve User stories.

How do I install Specify in Claude Code?

Run `npx skills add RafaelGB/Obsidian-ZettelFlow --skill specify -a claude-code`. Or copy the skill folder (.claude/skills/specify in RafaelGB/Obsidian-ZettelFlow) into .claude/skills/specify in your project. Claude Code loads it when a task matches its description.

How do I install Specify in Codex?

Run `npx skills add RafaelGB/Obsidian-ZettelFlow --skill specify -a codex`. Or copy the skill folder (.claude/skills/specify in RafaelGB/Obsidian-ZettelFlow) into .agents/skills/specify in your project. Codex loads it when a task matches its description.

Can I use Specify 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 RafaelGB/Obsidian-ZettelFlow --skill specify -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/specify, .gemini/skills/specify, .github/skills/specify and .opencode/skills/specify in your project.

What does Specify need to run?

Going by SKILL.md and its folder, Specify needs the command-line tools its instructions call (gh and npm).

Does Specify access the network?

SKILL.md contains no URLs. Its commands use gh and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Specify 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 Specify use?

Specify 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 Specify use?

About 759 tokens (SKILL.md is roughly 3k 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 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Specify?

Skills that share tags, products or a category with Specify: Create Issue (tradingstrategy-ai/frontend, 150 stars), Spec (getsentry/sentry-react-native, 1.8k stars), Abo Issue Watcher (jeeftor/audiobook-organizer, 189 stars) and Execute Issue (lbedner/aegis-stack, 143 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Specify?

RafaelGB (a GitHub user) maintains it in RafaelGB/Obsidian-ZettelFlow, which has 174 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 7, 2026.

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