skills/update-project-html/SKILL.md
Incrementally refresh the architecture atlas when the project diagram drifts from actual code. Measures drift before updating to determine scope, then updates the base atlas and re-renders HTML.
npx skillsauth add laitszkin/apollo-toolkit update-project-htmlInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Incrementally refresh the base atlas and rendered HTML based on code changes in the current branch, working tree, or a specified commit range. Keep the architecture diagram continuously aligned with the actual codebase.
evidence.sourceFile:sourceLine); unresolved ones are tagged inferredapltk codegraphPrerequisite before measuring drift. The code graph provides the structural baseline for comparison with the atlas.
Before choosing commands, run apltk codegraph --help and apltk codegraph <subcommand> --help. Use the live help output to inspect files, symbols, call relationships, contextual flows, or impact radius relevant to the atlas drift.
Consult references/codegraph.md for detailed flags.
Read the existing architecture diagram. Capture the relationship between features and submodules.
Read only
atlas.index.yaml+ the YAML files of affected features. Do not read unrelated features or unchanged modules to preserve context economy.
Before deciding the update scope, compare the atlas against the current code:
atlas.index.yaml with the current directory structure: are there added / removed directories or modules?Determine the update strategy based on drift severity:
init-project-htmlAnalyze the diff scope and filter non-architectural changes:
Map the filtered diff hunks to the affected features.
Dispatch subagents in parallel to cross-reference the code against the architecture diagram and verify whether the atlas has errors or omissions.
apltk CLIUse apltk architecture commands to update the architecture diagram:
Before invoking any apltk architecture command, run apltk architecture --help and the relevant subcommand help, then follow the live CLI guidance.
Consult references/architecture.md for CLI flag details (parameter reference, mutation series).
When inferring components from a diff hunk, use --evidence inferred with a file:line source. For example:
apltk architecture add module <slug> --part-of <feature> \
--evidence inferred:src/auth/controller.ts:42
After completing the update, re-measure drift to confirm it has been reduced to an acceptable range.
Confirm the following before finishing:
observed for source-confirmed, inferred otherwise)apltk architecture validatereferences/codegraph.md — apltk codegraph CLI reference; verify current usage with apltk codegraph --help.references/architecture.md — apltk architecture CLI reference; verify current usage with apltk architecture --help.references/definition.md — Detailed definitions of feature and submodule.development
Review a pull request — interactive PR selection via `gh`, 4-dimension code review (hallucinated code, architecture, performance, test validity), then post severity-graded comments with fix suggestions on the PR. Not for spec-based review — use `review` instead.
development
Read a user-specified PDF that marks the week's key financial events, deeply research each marked event with current sources, capture any additional breaking financial developments, and produce a concise Chinese-capable PDF briefing that explains what happened and why it matters.
documentation
Generate long-form videos (more than 10 minutes) by following user instructions and invoking related skills only when needed (`openai-text-to-image-storyboard`, `docs-to-voice`, `remotion-best-practices`). For text inputs, extract a complete long-form story arc, generate fresh storyboard images (no reuse of previously generated pictures), and render a 16:9 animated long-form video.
tools
協助完成自動化版本發佈。同步文檔、更新版本號、推送 tag 並建立 GitHub Release。