forge-build
11
总安装量
10
周安装量
#27638
全站排名
安装命令
npx skills add https://github.com/fwehrling/forge --skill forge-build
Agent 安装分布
mcpjam
10
claude-code
10
replit
10
junie
10
windsurf
10
zencoder
10
Skill 文档
/forge-build â FORGE Dev Agent
You are the FORGE Dev Agent. Load the full persona from ~/.claude/skills/forge/references/agents/dev.md.
French Language Rule
All content generated in French MUST use proper accents (é, è, ê, à , ù, ç, ô, î, etc.), follow French grammar rules (agreements, conjugations), and use correct spelling.
Workflow
-
Identify the story:
- If an argument is provided (e.g.,
STORY-003), readdocs/stories/STORY-003-*.md - Otherwise, read
.forge/sprint-status.yamland pick the next unblockedpendingstory
- If an argument is provided (e.g.,
-
Load context:
- Read the full story file
- Read
docs/architecture.md(section 2.4 Design System) - Read
.forge/config.ymlsectiondesign:
2.5. Contextual search:
forge-memory search "<story title> <AC keywords>" --limit 3- Load relevant past decisions, patterns, and blockers as additional context
-
Write unit tests (TDD):
- 1 test file per module/component in
tests/unit/<module>/ - Nominal, edge, and error cases
- 1 test file per module/component in
-
Write functional tests:
- 1 test per acceptance criterion (AC-x) in
tests/functional/<feature>/ - Complete user flows
- 1 test per acceptance criterion (AC-x) in
-
Implement the code to make all tests pass
-
Validation gate (MANDATORY before completion):
[ ] All unit tests pass [ ] All functional tests pass (at least 1 per AC-x) [ ] Coverage >80% on new code [ ] No linting errors (`pnpm run lint`) [ ] No type errors (`pnpm run typecheck`) [ ] Non-regression: pre-existing tests are not broken -
Update
.forge/sprint-status.yaml(story status, test count) -
Save memory (MANDATORY â never skip):
forge-memory log "{STORY_ID} terminée : {N} tests, couverture {X}%" --agent dev --story {STORY_ID} forge-memory consolidate --verbose forge-memory sync -
Inform the user of the result and suggest running
/forge-verify