CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

plan

Plan safe risk-scoped PsychSift work by inspecting the current change, selecting the smallest local verification ladder, and separating provider-backed checks into explicit approval gates. Use before non-trivial changes or when asked what checks are needed.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Plan

  1. Confirm the task objective, affected areas, and preserve unrelated work.
  2. Select the smallest sufficient local verification gate (test:focused or verify:cheap).
  3. Keep genuine safety gates intact: Supabase migrations, diff integrity, secrets, and auth/privacy rules.
  4. Keep live database, provider API calls, production readiness, and deployments approval-gated.
  5. Proceed autonomously with routine reversible local engineering; do not stall on procedural friction.
  6. Present the plan and verification results clearly in chat.
Repository

BigSimmo/PsychSift

Path

.agents/skills/plan/SKILL.md

Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.