/c--projects-dashclaw-route-changes
Make focused changes to API routes with verification.
$ npx -y skills add ucsandman/DashClaw --skill c--projects-dashclaw-route-changes --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/c--projects-dashclaw-route-changes
Context preview
The summary Claude sees to decide when to auto-load this skill.
Make focused changes to API routes with verification.
SKILL.md
c--projects-dashclaw-route-changes.SKILL.mdname: c--projects-dashclaw-route-changes description: Make focused changes to API routes with verification.
c--projects-dashclaw-route-changes
Trigger
Use when an HTTP route or server module needs to be added or changed.
Files to inspect first
- `C:\Projects\DashClaw\app\api-keys\page.js`
- `C:\Projects\DashClaw\app`
- `C:\Projects\DashClaw\app\lib\sessionViewer.mjs`
- `C:\Projects\DashClaw\app\api\mcp\route.js`
- `C:\Projects\DashClaw\middleware.js`
Steps
1. Read each file listed above before any edit. 2. Establish a verification baseline before any edit. 3. Plan the changes — list edits up front. 4. Apply edits in one pass; avoid re-reading the same file ≥ 3 times. 5. Run the project's verification command; do not declare done until it passes.
Verification gates
- No new high-confidence repeated-run signals in the session's tool sequence.
- No secret-output guard hits.
What not to do
- Don't introduce new abstractions when an existing one fits.
- Don't add error handling for scenarios that can't happen — only at system boundaries.
- Don't widen scope to a refactor when the trigger calls for a focused change.
--- Generated by AgentLens from session `acec7ebd-b7d3-4e21-8582-f9617e66b654` at `2026-05-12T21:42:09.652Z`. Skill candidate distilled from 3 similar prior session(s). Review and edit before relying on it.
🛡️ The approval and policy layer for AI agents. Intercept risky actions before they run, block them, or approve them remotely.
Repo: ucsandman/DashClaw
Other skills on dashclaw.
- /build-dashclaw
Contribute to the DashClaw codebase — architecture, scaffolding, tests, CI
Open skill - /compliance-drift-evals
Set up compliance exports, drift detection, evaluations, scoring, and learning analytics
Open skill - /create-policies
Create and test DashClaw guard policies for agent governance
Open skill - /instrument-agent
Integrate DashClaw SDK into any agent using the 4-step governance loop
Open skill - /manage-approvals
Human-in-the-loop approval workflows for governed agent actions
Open skill - /register-on-dashclaw
Register any agent (including this one) as a governed agent on a DashClaw instance
Open skill

