Last updated: 2026-04-13
Live reference — regenerated by /skills-dashboard in Claude Code. Edit the source at ~/.claude/skills/skills-dashboard/SKILL.md.
| Command | How to invoke | Purpose |
|---|
| task-start | /task-start [file] | First session on a task — read, plan, execute, append first AI Response |
| task-continue | /task-continue [file] | Process latest Human Response, append new AI Response |
| task-complete | /task-complete [file] | Close task: extract lessons, log/delete, commit offer |
| task-prep | /task-prep [file] | Hydrate task with full context; clarity check; sets status: ready |
| task-from-chat | ”convert this to a task”, /task-from-chat | Convert chat-discovered task into SMTM task file |
| project-start | /project-start [name] | Initialize new KB project structure |
| project-continue | /project-continue [name] | Continue active project: process Talbot Response, update STATUS.md, append next Claude Response |
| project-task-complete | /project-task-complete | End project session: write log, tick STATUS.md, update _tmp.md |
| tmp-do | /tmp-do | Implement tasks from _tmp.md |
| tmp-plan | /tmp-plan | Plan tasks from _tmp.md, await approval |
| Skill | How to invoke | Purpose |
|---|
| brainstorming | ”let’s brainstorm”, “explore options” | Explore intent and design before implementing |
| writing-plans | ”write a plan”, “plan this” | Create implementation plan from spec/requirements |
| executing-plans | ”execute the plan” | Run a written plan with review checkpoints |
| subagent-driven-development | auto-triggered | Parallelize independent tasks via subagents |
| test-driven-development | auto-triggered on features/bugfixes | TDD workflow before writing implementation code |
| Skill | How to invoke | Purpose |
|---|
| systematic-debugging | auto-triggered on bugs/failures | Debug before proposing fixes |
| verification-before-completion | auto-triggered before “done” | Require evidence before claiming success |
| requesting-code-review | auto-triggered after implementation | Validate work meets requirements |
| receiving-code-review | auto-triggered on review feedback | Handle review feedback with rigor |
| finishing-a-development-branch | auto-triggered when work is done | Decide merge/PR/cleanup strategy |
| simplify | /simplify | Review changed code for quality and efficiency |
| Skill | How to invoke | Purpose |
|---|
| using-superpowers | auto-triggered at session start | Establish skill discovery and usage rules |
| session-save | ”save context”, “checkpoint”, /session-save | Emergency save — write recovery file for next session |
| session-continue | ”resume session”, “load context”, /session-continue | Load a session-save file and resume autonomously |
| Skill | How to invoke | Purpose |
|---|
| research | /research [path] | Research a topic from a task file; appends cited report |
| Skill | How to invoke | Purpose |
|---|
| frontend-design | auto-triggered on web UI work | Create distinctive, production-grade frontend interfaces |
| Skill | How to invoke | Purpose |
|---|
| skill-creator | ”create a skill”, “improve this skill” | Create/iterate on skills with evals and description optimization |
| writing-skills | auto-triggered when creating/editing skills | Ensure skill quality before deployment |
| Command | Invoke | Means |
|---|
| cpw | /cpw | ”Confirm understanding, plan, await approval.” |
| ptr | /ptr | ”Proceed autonomously, test, report.” |
| ss | /ss | ”See attached screenshot.” |
| Command | Invoke | Purpose |
|---|
| test-all | /test-all | Full test suite: unit + TS + lint + 7 Playwright projects |
Deployment: Use the web-deploy utility (~/utils/web/web-deploy/) directly — no slash command.
When adding or removing skills, update the inventory in this file:
~/.claude/skills/skills-dashboard/SKILL.md
Then run /skills-dashboard — it will refresh Dashboard.md in the KB automatically.