
Verifying Before Done
by riekelte67b7af9ac74No license5 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 3 weeks ago
Use when about to say "done", "fixed", "passing", or "shipped", or when reporting the outcome of any change. Encodes verification as the definition of done: drive the change at its surface, run the verify command, report faithfully, distrust green suites, own failing gates. Use before every completion claim, even when the change was small and obviously correct, which is when this is skipped.
- e67b7af9ac74Currentcommit e67b7afPublished Oct 8, 2026
Source and attribution
Source:riekelt/principal-engineerinplugins/principal-engineer/skills/verifying-before-doneat commite67b7af
License: No license
Content belongs to its original authors. SourceWeft indexes it from a public repository.
More from riekelt/principal-engineer

Writing Unit Tests
riekelt
Guides writing and refactoring unit tests around behavior-first principles: one behavior per test, deterministic setup, boundary-only mocks.

Testing Changes
riekelt
Guides which tests a behavior change owes, including regression tests, discriminating assertions and red-test handling.

Scoping Changes
riekelt
Guides agents on sizing fixes to their trigger, decomposing oversized work visibly, and driving approved plans to completion.

Principal Engineering
riekelt
Encodes evidence-over-theory engineering discipline, safety rules, and a pre-change checkpoint for non-trivial software work.

Operating Safely
riekelt
Encodes safety guards for destructive operations, secrets hygiene, and concurrent-session work on live systems.

Keeping One Source Of Truth
riekelt
Encodes a one-fact-one-source doctrine for code and data, covering derivation, duplicate absorption and disagreement handling.
More in AI & Agents

Ppt Template Creator
anthropics
Turns a user's PowerPoint template into a reusable skill that generates branded presentations.

Skill Development
anthropics
Guides creation of Claude Code plugin skills, covering structure, descriptions, progressive disclosure and validation.

Plugin Structure
anthropics
Guides the structure, manifest, and component layout of Claude Code plugins.

Command Development
anthropics
Guides creation of Claude Code slash commands, covering structure, YAML frontmatter, arguments and plugin features.

Claude Md Improver
anthropics
Audits CLAUDE.md files in a repository, scores their quality, and applies approved targeted improvements.

Find Skills
vercel-labs
Guides discovery, quality checking and installation of agent skills via the npx skills CLI.