Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/supagetto-creating-specs
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/creating-specs
What's inside
- Skill name
creating-specs- Description
- Synthesize the current conversation into a spec. Use when the user says "to spec".
- License
- MIT
- Instructions
- 75 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Do NOT interview the user; just synthesize what you already know. ## Process 1. Explore the repo to understand the current state of the codebase, if you haven't already. Use the project's domain glossary vocabulary throughout the spec. Done when you have a working mental model of the relevant codebase areas. 2. Sketch out the seams — points where you can observe or substitute behaviour for testing — at which you're going to test the feature. Existing seams should be preferred to new ones. Use the highest seam possible. If new seams are needed, propose them at the highest point you can. The fewer seams across the codebase, the better - the ideal number is one. Check with the user that these seams match their expectations. Done when the user has confirmed the proposed seams. 3. Write the spec using the template below, then save it as `SPEC.md` inside a new spec directory. Follow the naming and path conventions in the using-workbench skill. Done when the file is saved. <spec-template> ## Problem Statement The problem that the user is facing, from the user's perspective. ## Solution The solution to the problem, from the user's perspective. ## User Stories A LONG, numbered list of user stories. Each user story should be in the format of: 1. As an <actor>, I want a <feature>, so that <benefit> <user-story-example> 1. As a mobile bank customer, I want to see balance on my accounts, so that I can make better informed decisions about my spending </user-story-example> This list of user stories should be extremely extensive and cover all aspects of the feature. ## Implementation Decisions A list of implementation decisions that were made. This can include: - The modules that will be built/modified - The interfaces of those modules that will be modified - Technical clarifications from the developer - Architectural decisions - Schema changes - API contracts - Specific interactions Do NOT include specific file paths or code snippets. They may end up being outdated very quickly. Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it within the relevant decision and note briefly that it came from a prototype. Trim to the decision-rich parts, not a working demo, just the important bits. ## Testing Decisions A list of testing decisions that were made. Include: - A description of what makes a good test (only test external behavior, not implementation details) - Which modules will be tested - Prior art for the tests (i.e. similar types of tests in the codebase) ## Out of Scope A description of the things that are out of scope for this spec. ## Further Notes Any further notes about the feature. </spec-template>
From supagetto/README.ai, MIT.
More from supagetto/README.ai
- 0.570score
setting-up-graft
supagetto
Use when graft/ or .serena/ is not git-ignored, or graft cards are not greppable by ripgrep, or the user asks to set up graft.
SkillAFreshness: AClaude Code +9 - 0.569score
reading-web-pages
supagetto
Read the main content of a web page URL as markdown.
SkillAFreshness: AClaude Code +9 - 0.565score
reviewing-spec-implementations
supagetto
Review changes since a fixed point against the originating spec.
SkillAFreshness: AClaude Code +9 - 0.565score
huddling
supagetto
Pressure-test a decision with a crew of five voices who answer independently, peer-review each other anonymously, and get a verdict from bigbrain.
SkillAFreshness: AClaude Code +9 - 0.564score
creating-tasks
supagetto
Break a plan, spec, or conversation into tracer-bullet tasks with blocking edges.
SkillAFreshness: AClaude Code +9 - 0.564score
implementing-specs
supagetto
Implement work from a spec and its tasks.
SkillAFreshness: AClaude Code +9 - 0.564score
writing-commit-messages
supagetto
Use when writing a commit message or when the user says "commit change".
SkillAFreshness: AClaude Code +9 - 0.564score
removing-ai-tells
supagetto
Remove AI tells from prose.
SkillAFreshness: AClaude Code +9 - 0.564score
creating-questionnaires
supagetto
Create a questionnaire for someone else to fill in.
SkillAFreshness: AClaude Code +9 - 0.560score
describing-changes
supagetto
Use when showing the shape of a change as pseudocode views.
SkillAFreshness: AClaude Code +9 - 0.559score
resolving-merge-conflicts
supagetto
Use when resolving an in-progress git merge/rebase conflict, or when the user says "resolve merge conflict" or "fix merge conflict".
SkillAFreshness: AClaude Code +9 - 0.559score
requesting-clarification
supagetto
Use when the user signals confusion about your last message, including short interjections like "wait", "what", "huh", or "again".
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 5, 2026 (24 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/supagetto/README.ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from supagetto
- 0.570score
setting-up-graft
supagetto
Use when graft/ or .serena/ is not git-ignored, or graft cards are not greppable by ripgrep, or the user asks to set up graft.
SkillAFreshness: AClaude Code +9 - 0.569score
reading-web-pages
supagetto
Read the main content of a web page URL as markdown.
SkillAFreshness: AClaude Code +9 - 0.565score
huddling
supagetto
Pressure-test a decision with a crew of five voices who answer independently, peer-review each other anonymously, and get a verdict from bigbrain.
SkillAFreshness: AClaude Code +9 - 0.565score
reviewing-spec-implementations
supagetto
Review changes since a fixed point against the originating spec.
SkillAFreshness: AClaude Code +9 - 0.564score
implementing-specs
supagetto
Implement work from a spec and its tasks.
SkillAFreshness: AClaude Code +9 - 0.564score
creating-tasks
supagetto
Break a plan, spec, or conversation into tracer-bullet tasks with blocking edges.
SkillAFreshness: AClaude Code +9
Cite this page
creating-specs skill. Agent Mart. https://agentmart.dev/skills/supagetto-creating-specs (last updated 2026-10-24)