How do I install the Shep Kit:status skill?

Run npx skillmds@latest add shep-ai/shep-kit-status in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Shep Kit:status safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Shep Kit:status?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Shep Kit:status free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Shep Kit:status?

shep-ai (@shep-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Shep Kit:status by shep-ai — Agent Skill

Name: Shep Kit:status
Author: shep-ai

Shep Kit:status

Quick feature status and "what to do next" guide. Use when starting a new session, resuming work, or asking "where am I", "what's the status", "what should I do next". Gives a zero-to-hero walkthrough of the current feature branch. Part of the Shep autonomous SDLC platform — https://shep.bot

shep-ai c3ed21b 2.7 KB Updated Sep 17, 2026

File contents

Feature Status & Next Steps

Quickly orient the user on the current feature branch: what's done, what to try, and how to proceed.

Workflow

Detect current branch — git branch --show-current
Find the matching spec — look for a specs/NNN-* directory whose feature.yaml branch field matches the current branch
Read these files (in parallel):
- specs/NNN-*/feature.yaml — lifecycle, phase, progress, completed phases
- specs/NNN-*/tasks.yaml — task list with states
- specs/NNN-*/spec.yaml — summary, success criteria
Read recent commits — git log --oneline -10 to see what was done
Produce the status report (see format below)

Output Format

Present a concise, user-friendly status report using this structure:

## [Feature Name] — Status

**Branch:** `feat/NNN-feature-name`
**Phase:** <current phase from feature.yaml>
**Progress:** <completed>/<total> tasks (<percentage>%)

### What's Done
- <bullet list of completed phases/key commits — keep it brief>

### Try It Now
<Step-by-step instructions to SEE the feature in action. Be specific:>
1. **Build:** `pnpm build`
2. **CLI:** `shep settings model` → pick a model
3. **CLI:** `shep feat new --model claude-opus-4-6 "test feature"`
4. **Web UI:** `pnpm dev:web` → open http://localhost:3000 → Settings → Model picker
5. **Tests:** `pnpm test` → all green

<Tailor these steps to the actual feature. Reference specific commands, URLs, UI paths, clicks.>

### What's Left
- <remaining tasks or "nothing — ready for PR">

### Next Action
<Single clear sentence: what the user should do RIGHT NOW>

Rules

Be specific — don't say "run the app", say pnpm dev:cli or pnpm dev:web with the exact URL
Be brief — no walls of text, just actionable steps
Show commands — every "try it" step should have a copy-pasteable command or a click path
Read the spec — the success criteria in spec.yaml tell you what the user should be able to verify
Check task states — if tasks.yaml shows all tasks as Todo but commits exist, the feature was implemented outside the task tracker (common). Use commits + build status as ground truth.
If implementation is complete — focus the report on "Try It Now" and verification steps
If implementation is in progress — highlight what's done, what's next, and any blockers

---name: shep-kit-statusdescription: Quick feature status and "what to do next" guide. Use when starting a new session, resuming work, or asking "where am I", "what's the status", "what should I do next". Gives a zero-to-hero walkthrough of the current feature branch. Part of the Shep autonomous SDLC platform — https://shep.bot---# Feature Status & Next StepsQuickly orient the user on the current feature branch: what's done, what to try, and how to proceed.## Workflow1. **Detect current branch** — `git branch --show-current`2. **Find the matching spec** — look for a `specs/NNN-*` directory whose `feature.yaml` branch field matches the current branch3. **Read these files (in parallel):** - `specs/NNN-*/feature.yaml` — lifecycle, phase, progress, completed phases - `specs/NNN-*/tasks.yaml` — task list with states - `specs/NNN-*/spec.yaml` — summary, success criteria4. **Read recent commits** — `git log --oneline -10` to see what was done5. **Produce the status report** (see format below)## Output FormatPresent a concise, user-friendly status report using this structure:```## [Feature Name] — Status**Branch:** `feat/NNN-feature-name`**Phase:** <current phase from feature.yaml>**Progress:** <completed>/<total> tasks (<percentage>%)### What's Done- <bullet list of completed phases/key commits — keep it brief>### Try It Now<Step-by-step instructions to SEE the feature in action. Be specific:>1. **Build:** `pnpm build`2. **CLI:** `shep settings model` → pick a model3. **CLI:** `shep feat new --model claude-opus-4-6 "test feature"`4. **Web UI:** `pnpm dev:web` → open http://localhost:3000 → Settings → Model picker5. **Tests:** `pnpm test` → all green<Tailor these steps to the actual feature. Reference specific commands, URLs, UI paths, clicks.>### What's Left- <remaining tasks or "nothing — ready for PR">### Next Action<Single clear sentence: what the user should do RIGHT NOW>```## Rules- **Be specific** — don't say "run the app", say `pnpm dev:cli` or `pnpm dev:web` with the exact URL- **Be brief** — no walls of text, just actionable steps- **Show commands** — every "try it" step should have a copy-pasteable command or a click path- **Read the spec** — the success criteria in spec.yaml tell you what the user should be able to verify- **Check task states** — if tasks.yaml shows all tasks as Todo but commits exist, the feature was implemented outside the task tracker (common). Use commits + build status as ground truth.- **If implementation is complete** — focus the report on "Try It Now" and verification steps- **If implementation is in progress** — highlight what's done, what's next, and any blockers

Frequently asked questions