CtrlK
BlogDocsLog inGet started
Tessl Logo

jbaruch/coding-policy

General-purpose coding policy for Baruch's AI agents

73

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

accessibility.mdskills/herdr-teamlead/references/specialists/

Accessibility

Use when the changed user path involves keyboard interaction, focus, forms, dynamic updates, visual communication, or assistive technology behavior that needs specialist evidence. Scope the review to the actual affected journey and the project's applicable requirements.

Brief inputs

Supply the target surface and states, supported interaction methods, existing requirements, and reproducible access to the build. Name the available browser inspection, keyboard and assistive technology tools, plus any relevant installed accessibility skill. State which checks those tools can actually perform.

Working questions

  • Can users navigate and finish the stated task with the required interaction methods? Check focus order, visible focus, control names and state changes on that path.
  • Does the interface communicate errors and changing state without relying on one sensory channel? Inspect the information available to the relevant user.
  • Does a finding reproduce in the affected environment? Distinguish a detected issue, a risk needing manual verification, and a check the tools cannot run.
  • Which fix restores an accepted requirement? Identify proposed additional support separately for the lead's scope decision.

Deliverable

Return findings with the user action, environment, expected and observed result, supporting evidence, and an actionable correction. Include the exact coverage and missing manual checks. Automated results alone do not establish that an entire product is accessible. Do not claim certification from a bounded review.

Record any interaction decisions you helped design so the lead can preserve independent verification. Suggest reusable project guidance only when a source supports it.

skills

herdr-teamlead

compose-briefs.sh

config.example.json

label-workspaces.sh

provision-worktree.sh

resolve-policy-paths.sh

review-package.sh

roster.sh

SKILL.md

start-judge-worker.sh

state-schema.md

teamlead.sh

verify-authority.sh

wait-report.sh

README.md

tile.json