Chalk Labs
Need help deploying st-define?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/hyusecs-st-define
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
Use cases: writing
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 and code. Checked Oct 26, 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/st-define
What's inside
- Skill name
st-define- Description
- Full-lane Define phase. Grill the user, write the feature spec, clarify gaps, run the checklist, and stop at the gate "user agrees the spec".
- License
- MIT
- Instructions
- 42 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# /stratum:st-define <feature description> You are the orchestrator and you run this phase yourself: grilling needs the user. Plugin root (`<plugin root>`) is two levels up from this skill's base directory. Use absolute paths. In every procedure file, `<PLUGIN_ROOT>` means this plugin root. ## 0. Start 1. If `<project>/.stratum/` does not exist, stop and tell the user to run `/stratum:st-init`. 2. Read `<project>/.stratum/state.json` if it exists. Define starts a feature, so it is never out of order. If no description is given and state.json names a feature, redo Define on that feature: skip step 2 of "Steps" and revise its existing `spec.md`. 3. If `lane` is not set, it is `full`. ## Steps 1. **Grill.** Run the `st-grill` skill on the description. One question at a time, each with your recommended answer. Stop when scope, users, data, privacy, and done-criteria are clear. 2. **Specify.** Follow `<plugin root>/procedures/specify.md`. Input: the description plus a short summary of the grilling answers. It creates `specs/NNN-short-name/spec.md`, the `checklists/requirements.md` quality checklist, and writes `.stratum/state.json` with `phase: define`. 3. **Clarify, only if gaps remain.** If the spec still has `[NEEDS CLARIFICATION]` markers or failing items in `checklists/requirements.md`, follow `<plugin root>/procedures/clarify.md`. Otherwise skip it and say so in one line. 4. **Checklist.** Follow `<plugin root>/procedures/checklist.md`. Input: the feature's highest impact areas (for example privacy, access, offline, screens). ## Gate: user agrees the spec Show the spec in short form: user stories with priority, the FRs, success criteria, and open assumptions. Ask: "Do you agree the spec?" Edit and ask again until they say yes. Do not start `/stratum:st-plan` before that. On yes: have `st-git` commit the spec files with exact paths. ## Always - Never skip the commit guard. If a commit is blocked, tell the user; do not work around it. - Push only when the user says "push".
From HyuseCS/stratum, MIT.
More from HyuseCS/stratum
- 0.604score
st-handoff
HyuseCS
Write the session handoff to .stratum/handoff.md so the next session starts where this one stopped.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
st-ponytail-audit
HyuseCS
Quality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
st-build
HyuseCS
Full-lane Build phase.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
st-inspect
HyuseCS
Full-lane Inspect phase.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
st-model
HyuseCS
Set the model or effort a Stratum agent uses in this project, saved in .stratum/models.json.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
st-plan
HyuseCS
Full-lane Plan phase.
SkillAFreshness: A★ 3Claude Code +9 - 0.600score
st-graphify
HyuseCS
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question…
SkillAFreshness: A★ 3Claude Code +9 - 0.597score
st-close
HyuseCS
Full-lane Close phase.
SkillAFreshness: A★ 3Claude Code +9 - 0.596score
st-issues
HyuseCS
Turn the current feature's tasks.md into GitHub issues on the repo's own GitHub remote, skipping tasks that already have one.
SkillAFreshness: A★ 3Claude Code +9 - 0.596score
st-git
HyuseCS
Commit on demand through the st-git agent.
SkillAFreshness: A★ 3Claude Code +9 - 0.596score
st-debug
HyuseCS
Run the st-debug agent on demand for one task of the current feature, then verify with st-verify.sh (test green, no added comment lines).
SkillAFreshness: A★ 3Claude Code +9 - 0.596score
st-constitution
HyuseCS
Create or amend the project rules in .stratum/constitution.md from the user's words, with a version bump and sync report.
SkillAFreshness: A★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 4
- Last commit (this folder)
- Oct 14, 2026 (18 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/HyuseCS/stratum
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from HyuseCS
- 0.604score
st-handoff
HyuseCS
Write the session handoff to .stratum/handoff.md so the next session starts where this one stopped.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
st-ponytail-audit
HyuseCS
Quality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
st-plan
HyuseCS
Full-lane Plan phase.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
st-build
HyuseCS
Full-lane Build phase.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
st-inspect
HyuseCS
Full-lane Inspect phase.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
st-model
HyuseCS
Set the model or effort a Stratum agent uses in this project, saved in .stratum/models.json.
SkillAFreshness: A★ 3Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get st-define running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
st-define skill. Agent Mart. https://agentmart.dev/skills/hyusecs-st-define (last updated 2026-10-24)