Skip to content

Last updated: 2026-04-13

Live reference — regenerated by /skills-dashboard in Claude Code. Edit the source at ~/.claude/skills/skills-dashboard/SKILL.md.


CommandHow to invokePurpose
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-chatConvert 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-completeEnd project session: write log, tick STATUS.md, update _tmp.md
tmp-do/tmp-doImplement tasks from _tmp.md
tmp-plan/tmp-planPlan tasks from _tmp.md, await approval

🔧 Development Process [Plugin: superpowers]

Section titled “🔧 Development Process [Plugin: superpowers]”
SkillHow to invokePurpose
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-developmentauto-triggeredParallelize independent tasks via subagents
test-driven-developmentauto-triggered on features/bugfixesTDD workflow before writing implementation code

SkillHow to invokePurpose
systematic-debuggingauto-triggered on bugs/failuresDebug before proposing fixes
verification-before-completionauto-triggered before “done”Require evidence before claiming success
requesting-code-reviewauto-triggered after implementationValidate work meets requirements
receiving-code-reviewauto-triggered on review feedbackHandle review feedback with rigor
finishing-a-development-branchauto-triggered when work is doneDecide merge/PR/cleanup strategy
simplify/simplifyReview changed code for quality and efficiency

SkillHow to invokePurpose
using-superpowersauto-triggered at session startEstablish skill discovery and usage rules
session-save”save context”, “checkpoint”, /session-saveEmergency save — write recovery file for next session
session-continue”resume session”, “load context”, /session-continueLoad a session-save file and resume autonomously

SkillHow to invokePurpose
research/research [path]Research a topic from a task file; appends cited report

🎨 Frontend / UI [Plugin: frontend-design]

Section titled “🎨 Frontend / UI [Plugin: frontend-design]”
SkillHow to invokePurpose
frontend-designauto-triggered on web UI workCreate distinctive, production-grade frontend interfaces

⚙️ Skill Management [Plugin: skill-creator]

Section titled “⚙️ Skill Management [Plugin: skill-creator]”
SkillHow to invokePurpose
skill-creator”create a skill”, “improve this skill”Create/iterate on skills with evals and description optimization
writing-skillsauto-triggered when creating/editing skillsEnsure skill quality before deployment

CommandInvokeMeans
cpw/cpw”Confirm understanding, plan, await approval.”
ptr/ptr”Proceed autonomously, test, report.”
ss/ss”See attached screenshot.”

CommandInvokePurpose
test-all/test-allFull 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.