CtrlK
BlogDocsLog inGet started
Tessl Logo

alethical

github.com/alethical-org/alethical

SkillAddedReview
browser-user-test

.claude/skills/browser-user-test/SKILL.md

Run an end-to-end browser test of Alethical as a real user — after a feature lands, on demand ("browser-test this", "drive the app", "test it like a user"), or before calling frontend work done. Spawns a FRESH-context agent on a cheap model that knows nothing about the implementation, drives the running app through a browser in scripted user stories or free exploration, and reports what breaks. Also owns the on-demand Playwright checks (just e2e) and the path from a stable story to a Playwright spec.

71

design-build

.claude/skills/design-build/SKILL.md

—

Invalid
design-intake

.claude/skills/design-intake/SKILL.md

—

Invalid
design-review

.claude/skills/design-review/SKILL.md

Use when a draft (not-yet-final) Design mockup + bundle arrives and needs evaluating against Alethical's real data, backend capability, and UX before anyone builds it. Pressure-tests every element for buildability + honesty (grounded-answers), applies the design-audit accessibility/interaction rubric to everything a static design can reveal, and routes prioritized feedback to Design, the current coding agent, or the maintainer. Pre-build. First in the design- skill set: design-review → design-intake → design-build → design-audit.

68

file-github-issue

.claude/skills/file-github-issue/SKILL.md

Use when creating, categorizing, re-scoping, or sweeping GitHub issues on Alethical's Roadmap board (org `alethical-org` Project

67

requirement-coverage

.claude/skills/requirement-coverage/SKILL.md

Use before merging work that delivers an issue's or brief's acceptance criteria. An independent reviewer maps each accepted requirement to evidence suited to it and records verified, implemented but unverified, partial, missing or not applicable for the reviewed head commit.

71

resume-research-workflow

.claude/skills/resume-research-workflow/SKILL.md

Use when launching, stopping, or resuming an expensive multi-agent research run (deep-research or a Workflow fan-out) — how to checkpoint at launch, stop before a usage meter runs into paid overage, and resume from the journal cache byte-identically instead of re-paying. Invoke before firing a long Workflow, when the maintainer names a usage threshold or reports a meter running hot, and before diagnosing an empty or failed run as lost work.

70

when-to-act-without-approval

.claude/skills/when-to-act-without-approval/SKILL.md

Use when deciding whether a change is yours to ship or needs the maintainer's approval first, and to look up what to verify before shipping it — the per-domain carve-out details behind `.claude/rules/workflow.md` rule 10 (front-end, backend, migrations, paid production runs, dead-code removal, concurrent-session safety) plus the catalogue of handbacks that produced each grant. Invoke before opening a PR, when tempted to ask "want me to ship this?", and before committing or merging while other sessions are running.

63

workflow-overhead-audit

.claude/skills/workflow-overhead-audit/SKILL.md

—

Invalid