文件历史

提交图

6 次代码提交

作者 SHA1 备注 提交日期
Addy Osmani b765343015 docs: tighten redundant-verification wording for consistency
Unify the framing across the verification note, rationalization row,
and red flag entry in both incremental-implementation and
test-driven-development skills. The previous wording mixed "once per
increment" (correct) with "no additional value after success" (only
true if nothing has changed), which an agent could read as "skip
verification entirely after one success."

The unified rule: after a successful run, don't repeat the same
command unless the code has changed since.
2026-05-06 18:12:48 -07:00
Sreedhar Busanelli ad35cbf9cf Fix: Add guidance to prevent redundant build verification commands
Fixes #47

## Changes
- Add verification guidance to incremental-implementation skill checklist
- Add test guidance to test-driven-development skill verification section
- Add common rationalizations about redundant verification in both skills
- Add red flags for running same command multiple times after success

## Impact
This addresses the issue where agents run build verification commands (npx tsc --noEmit, npx vite build, npm test) multiple times consecutively after successful runs, providing clear guidance to trust the first successful verification.
2026-04-13 11:44:42 -05:00
Federico Bartoli fea75b1647 Align skill descriptions with Anthropic best practices
Update all SKILL.md descriptions to lead with what the skill does
(third person) followed by trigger conditions, per Anthropic's
skill authoring docs. All original trigger conditions preserved.
Update description max chars to match Anthropic spec (1024).
Retain workflow-summary warning in skill-anatomy.md to prevent
agents from following descriptions instead of reading full skills.
Add Table of Contents to reference files longer than 100 lines so
Claude can see the full scope of available information even when
previewing with partial reads.
2026-03-31 22:41:45 +02:00
Federico Bartoli 702a894889 Soften prescriptive language for Claude 4.6 compatibility
Anthropic's Claude 4 prompting best practices document warns that
newer models overtrigger on strong directive language (Never/Always/MUST)
that was necessary for older models. This replaces aggressive directives
with natural phrasing across skills and agents while preserving all
security-critical rules (OWASP, prompt injection, secrets) unchanged.

Also reframes trunk-based development as "Recommended" with a note
acknowledging alternative branching strategies like gitflow.
2026-03-31 19:29:59 +02:00
Addy Osmani f34cdea627 Add cross-reference from incremental-implementation to git workflow
The commit step in the increment cycle now points to the
git-workflow-and-versioning skill for atomic commit guidance.
2026-03-28 00:42:21 -07:00
Addy Osmani 7ea265f17d add incremental-implementation and frontend-ui-engineering skills
Build phase skills covering thin vertical slices and
production-quality UI development patterns.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-15 14:36:36 -08:00