Agent skill

Spec Creation

by bybren-llc in bybren-llc/safe-agentic-workflow

Spec creation with pattern references, acceptance criteria, and demo scripts.

MITAuto-check passedProduct & Project Management

Install Spec Creation

skills CLI
$ npx skills add bybren-llc/safe-agentic-workflow --skill spec-creation -a claude-code

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

GitHub CLI
$ gh skill install bybren-llc/safe-agentic-workflow spec-creation --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/bybren-llc/safe-agentic-workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/spec-creation .claude/skills/spec-creation && 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
spec-creation
GitHub stars
423
Token cost
~1.3k tokens
SKILL.md length
104 words
Files
2
Skills in repo
42
Repo updated
First seen
Licence
MIT

At a glance

Spec creation with pattern references, acceptance criteria, and demo scripts.

  • Works in 4 steps: Navigate to {page} → Click {button} → Observe {expected behavior} → …
  • Creating implementation specs
  • SKILL.md covers Purpose, When This Skill Applies, Stop-the-Line Conditions and Demo Script, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Spec Creation is an agent skill from bybren-llc/safe-agentic-workflow. Spec creation with pattern references, acceptance criteria, and demo scripts. Use when creating implementation specs, defining acceptance criteria, or breaking down user stories.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).

It sits in Product & Project Management, covering User stories. The repository describes itself as: SAW — SAFe Agentic Workflow AI Agent Harness for Multi-Agent Team Workflows Built on SAFe methodology (Scaled Agile Framework), adapted for AI agent teams (Now With AI-DLC!)… The licence is MIT.

When your agent uses it

  • Creating implementation specs
  • Defining acceptance criteria
  • Breaking down user stories

Example prompts

  • “/spec-creation”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Grep, Glob

Workflow steps

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

  1. Navigate to {page}
  2. Click {button}
  3. Observe {expected behavior}
  4. Verify {success indicator}

What it can do on your machine

Read from SKILL.md and the folder at commit 26ca58b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Grep
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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

Spec Creation loads about 1.3k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 104 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 bybren-llc/safe-agentic-workflow at commit 26ca58b, republished under its MIT licence (© bybren-llc). 104 words, ~1,292 tokens.

Download SKILL.mdSave it as .claude/skills/spec-creation/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
spec-creation
description
Spec creation with pattern references, acceptance criteria, and demo scripts. Use when creating implementation specs, defining acceptance criteria, or breaking down user stories.
allowed-tools
Read, Write, Grep, Glob
context
fork
argument-hint
[ticket-id]

Spec Creation Skill

Purpose

Guide spec creation with clear acceptance criteria, pattern references for execution agents, and testable success validation commands.

When This Skill Applies

Invoke this skill when:

  • Creating implementation specs
  • Breaking down user stories
  • Defining acceptance criteria
  • Adding pattern references for execution
  • Creating demo scripts for validation
  • Translating business requirements to technical specs

Stop-the-Line Conditions

FORBIDDEN Patterns
markdown
# FORBIDDEN: Missing acceptance criteria

## Implementation

Just do the thing.

<!-- No testable outcomes defined -->

# FORBIDDEN: No pattern reference

## Technical Approach

Build it however you want.

<!-- Execution agents need pattern pointers -->

# FORBIDDEN: No success validation

## Done Criteria

Looks good to reviewer.

<!-- No command to verify completion -->
CORRECT Patterns
markdown
# CORRECT: Clear acceptance criteria

## Acceptance Criteria

- [ ] User can click button → modal appears
- [ ] Modal shows validation errors for empty fields
- [ ] Successful submission shows success toast

# CORRECT: Pattern reference for execution

## Pattern Reference

- **UI Pattern**: `patterns_library/ui/modal-form.md`
- **API Pattern**: `patterns_library/api/crud-endpoint.md`
- **RLS Pattern**: `patterns_library/security/rls-user-data.md`

# CORRECT: Success validation command

## Success Validation

```bash
# Run these commands to verify implementation
yarn test:unit --grep "ModalForm"
curl -X POST http://localhost:3000/api/endpoint -d '{"test": true}'
```

## Spec Template (MANDATORY)

Every spec must include:

````markdown
# SPEC-{{TICKET_PREFIX}}-{number}: {Feature Name}

## Summary

{One paragraph describing the feature}

## User Story

As a [user type], I want [goal] so that [benefit].

## Acceptance Criteria

- [ ] {Testable criterion 1}
- [ ] {Testable criterion 2}
- [ ] {Testable criterion 3}

## Pattern References

- **UI**: `patterns_library/ui/{pattern}.md`
- **API**: `patterns_library/api/{pattern}.md`
- **Database**: `patterns_library/database/{pattern}.md`
- **Security**: Follow RLS patterns in `docs/database/RLS_IMPLEMENTATION_GUIDE.md`

## Success Validation Command

```bash
# Run this to verify the feature works
{validation command}

Demo Script

  1. Navigate to {page}
  2. Click {button}
  3. Observe {expected behavior}
  4. Verify {success indicator}

Logical Commits

  1. feat(scope): implement data model [{{TICKET_PREFIX}}-{number}]
  2. feat(scope): add API endpoint [{{TICKET_PREFIX}}-{number}]
  3. feat(scope): create UI component [{{TICKET_PREFIX}}-{number}]
  4. test(scope): add unit tests [{{TICKET_PREFIX}}-{number}]

## Acceptance Criteria Patterns

### User Action Criteria

```markdown
- [ ] User can {action} → {result}
- [ ] When user {triggers}, system {responds}
- [ ] User receives {feedback} after {action}
```

### Data Criteria

```markdown
- [ ] Data persists after {action}
- [ ] User can only see their own {data type}
- [ ] {field} validates {constraint}
```

### Error Criteria

```markdown
- [ ] Invalid input shows {error message}
- [ ] Network failure shows retry option
- [ ] Unauthorized access returns 401
```

## Pattern Discovery for Specs

Before writing any spec:

```bash
# Find existing patterns
ls patterns_library/

# Search for similar implementations
grep -r "similar feature" app/ lib/

# Check existing specs for format
ls specs/
cat specs/SPEC-{{TICKET_PREFIX}}-XXX-example.md
```

## Spec Quality Checklist

Before submitting spec:

- [ ] All acceptance criteria are testable (can verify pass/fail)
- [ ] Pattern references point to existing patterns
- [ ] Success validation command is runnable
- [ ] Demo script is step-by-step reproducible
- [ ] Logical commits follow SAFe format
- [ ] Linear ticket referenced

## Output Locations

| Output Type  | Location                                              |
| ------------ | ----------------------------------------------------- |
| Impl specs   | `specs/SPEC-{{TICKET_PREFIX}}-{number}-{description}.md`            |
| Requirements | `docs/agent-outputs/requirements/{{TICKET_PREFIX}}-{number}-*.md`   |
| ADRs         | `docs/adr/ADR-{number}-{description}.md`              |

## Evidence for Linear

After spec approval:

```markdown
**BSA Spec Evidence**

**Spec**: specs/SPEC-{{TICKET_PREFIX}}-{number}-{description}.md
**Status**: Approved by [reviewer]

**Deliverables**:

- [x] Acceptance criteria defined
- [x] Pattern references added
- [x] Demo script created
- [x] Ready for implementation
```

## Authoritative References

- **Spec Template**: `docs/archive/specs/spec_template.md`
- **Pattern Library**: `patterns_library/README.md`
- **Planning Guide**: `docs/team/PLANNING-AGENT-META-PROMPT.md`
- **SAFe Workflow**: `CONTRIBUTING.md`

© bybren-llc, 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 in .claude/skills/spec-creation of bybren-llc/safe-agentic-workflow.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit 26ca58b

Compare with similar skills

Spec Creation 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 Creation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Spec Creation this skillbybren-llc/safe-agentic-workflow423—~1.3kAutomated safety check: PassMIT
User Story Writerdeanpeters/Product-Manager-Skills7.2k2 repos~2.9kAutomated safety check: PassCustom licence
Ralph Tui Create Beadssubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT
Agile Product Owneralirezarezvani/claude-skills28k3 repos~3.2kAutomated safety check: PassMIT
Ralph Tui Create Beads Rustsubsy/ralph-tui2.5k1 repos~2.8kAutomated safety check: PassMIT
To Specbestofjs/bestofjs3.1k21 repos~757Automated safety check: PassMIT

Similar skills

  • User Story Writer

    deanpeters/Product-Manager-Skills

    Writes user stories in Mike Cohn's format with Gherkin acceptance criteria, turning user needs into development-ready work with testable conditions.

    7.2k GitHub starsUsed in 2 repos~2.9k tokens
    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
  • Agile Product Owner

    alirezarezvani/claude-skills

    Writes INVEST-checked user stories with acceptance criteria, splits epics, plans sprints from velocity and ranks the backlog with a weighted score.

    28k GitHub starsUsed in 3 repos~3.2k tokens
    Product & Project ManagementAuto-check passed
  • 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
  • To Spec

    bestofjs/bestofjs

    Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

    3.1k GitHub starsUsed in 21 repos~757 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

More from bybren-llc/safe-agentic-workflow

All 42 skills in this repo
  • Multi-Agent Coordination Template

    bybren-llc/safe-agentic-workflow

    Agent assignment matrix, blocker escalation, and TDM coordination patterns. Use when assigning work to specialist agents, managing blockers across agents…

    423 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed
  • API Route Patterns

    bybren-llc/safe-agentic-workflow

    API route implementation patterns with RLS, validation, and error handling. Use when creating API routes, implementing CRUD endpoints, adding server-side…

    423 GitHub stars~1.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Technical Documentation Templates

    bybren-llc/safe-agentic-workflow

    Documentation templates for ADRs, runbooks, architecture docs, and knowledge transfer documents. Use when creating Architecture Decision Records, writing…

    423 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Deployment SOP Checklist

    bybren-llc/safe-agentic-workflow

    Deployment workflows, pre-deploy validation, smoke testing, and rollback procedures. Use when deploying to staging or production, running smoke tests…

    423 GitHub stars~950 tokensUpdated 2 mo ago
    Auto-check passed
  • Frontend Patterns Template

    bybren-llc/safe-agentic-workflow

    Frontend patterns for modern web frameworks, component libraries, auth flows, and analytics. Use when building UI components, creating pages, implementing…

    423 GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Advanced Git Operations

    bybren-llc/safe-agentic-workflow

    Advanced git operations including rebase, bisect, cherry-pick, and conflict resolution. Use when rebasing feature branches, debugging with bisect…

    423 GitHub stars~1.6k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Spec Creation

What does Spec Creation do?

Spec creation with pattern references, acceptance criteria, and demo scripts. Spec Creation is an agent skill from bybren-llc/safe-agentic-workflow. Spec creation with pattern references, acceptance criteria, and demo scripts.

When should I use Spec Creation?

Spec Creation fits situations like: creating implementation specs; defining acceptance criteria; breaking down user stories.

How do I install Spec Creation in Claude Code?

Run `npx skills add bybren-llc/safe-agentic-workflow --skill spec-creation -a claude-code`. Or copy the skill folder (.claude/skills/spec-creation in bybren-llc/safe-agentic-workflow) into .claude/skills/spec-creation in your project. Claude Code loads it when a task matches its description.

How do I install Spec Creation in Codex?

Run `npx skills add bybren-llc/safe-agentic-workflow --skill spec-creation -a codex`. Or copy the skill folder (.claude/skills/spec-creation in bybren-llc/safe-agentic-workflow) into .agents/skills/spec-creation in your project. Codex loads it when a task matches its description.

Can I use Spec Creation 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 bybren-llc/safe-agentic-workflow --skill spec-creation -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-creation, .gemini/skills/spec-creation, .github/skills/spec-creation and .opencode/skills/spec-creation in your project.

What does Spec Creation need to run?

SKILL.md names no scripts, command-line tools or credentials: Spec Creation is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Grep, Glob.

Does Spec Creation 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 Spec Creation 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 Creation use?

Spec Creation 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 Creation use?

About 1.3k tokens (SKILL.md is roughly 5.2k 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 Creation?

Skills that share tags, products or a category with Spec Creation: User Story Writer (deanpeters/Product-Manager-Skills, 7.2k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Agile Product Owner (alirezarezvani/claude-skills, 28k 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 Spec Creation?

bybren-llc (a GitHub organization) maintains it in bybren-llc/safe-agentic-workflow, which has 423 GitHub stars. The repository holds 42 skills in this directory. The repository was last updated on July 20, 2026.

Source: bybren-llc/safe-agentic-workflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.