Aikc project workflow
Skill AHappyAtlas/ai-knowledge-center/ai-knowledge/skills/aikc-project-workflow
Local-first project context, verification gates, and repo-scoped MCP for coding agents.From the repository description
npx -y skills add AHappyAtlas/ai-knowledge-center --skill aikc-project-workflowAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
4.4 KB, 968 tokens by cl100k_base, as published. Nobody here has run it
AIKC Project Workflow Skill
Use this skill when changing the AI Knowledge Center package itself: CLI behavior, project upgrade templates, manifest loading, dashboard metadata, gates, telemetry, or this repository's AI workflow knowledge.
Stable Project Facts
- Package name:
ai-knowledge-center. - Global CLI names:
aikcandai-knowledge-center. - Published CLI entrypoint:
dist/cli/aikc.js. - Source CLI entrypoint:
src/cli/aikc.ts. - Project upgrade logic lives in
src/cli/project-upgrader.ts. - Production dashboard and API are served by Fastify from one port, default
127.0.0.1:4318. - Development uses two processes: server on
4318and Vite UI on5177.
Change Guidance
- Prefer editing
src/and rebuilding; do not hand-editdist/unless release artifacts are explicitly required. - Keep CLI options documented in
README.mdaligned withsrc/cli/aikc.ts. - Keep scaffold templates in
src/cli/project-upgrader.tsaligned with root examples inai-knowledge/. - New-project and upgrade templates must include AIKC-maintained
ai-knowledge/core/**, compatibility entrypoints, internal AI workflow scripts underai-knowledge/scripts/**, and a mandatory final knowledge-capture decision. - Keep the ownership boundary explicit:
ai-knowledge/core/**is upgraded by AIKC; project-specific reusable knowledge belongs inai-knowledge/skills/**or project-owned references. - Core workflow templates must ask agents to package repeated operations as project scripts, project skills, MCP/server tools, or references, with local host OS and remote target OS considered separately.
- Core workflow templates must treat AI workflow loops as bounded loops with explicit input, output, validation, budget, stop condition, and human escalation.
- Core workflow templates must keep AI-facing knowledge compact and maintain human-readable companions under
ai-knowledge/human/**only when meaning changes or missing companions are backfilled. - Core workflow templates must include token-efficiency guidance for minimal context loading, log summaries, structured output, caches, operations indexes, doctor commands, and compact closeout.
- Core workflow templates must preserve AIKC project capabilities that are not project-specific: manifest contract, dashboard metadata, gates/commands, MCP, telemetry, Dagger, project discovery, API automation, safe upgrade semantics, and release discipline.
- Core workflow templates must guide agents to prefer mature open-source packages over hand-rolled implementations when they improve CLI parsing, file discovery, search, schema/API contracts, logging, config paths, watchers, process execution, or MCP/server tooling.
- Keep the dashboard initialization prompt in
src/client/App.tsxaligned withsrc/cli/project-upgrader.ts, so copied prompts, CLI upgrade, and dashboard auto-init describe the same behavior. - Avoid making
aikc --versionstart the server if adding version support; handle informational flags before importingsrc/server/index.ts. - Preserve the documented behavior that
aikc upgrade --writecreates candidates for conflicts instead of overwriting project-specific files. - Existing projects should be updateable: changed local files get
*.aikc-upgrade.mdcandidates and an AI handoff prompt, not blind overwrites. - Keep knowledge token checks sparse: trigger them for explicit token/context/routing work, first run state creation, or changes to workflow entrypoints and the compact skill index.
- For token/cache/MCP evaluation, read
ai-knowledge/core/open-source-token-tools.mdafter this skill. Prefer AIKC's built-in context-pack, repo-map, log-summary, run-bounded, token-budget-check, repo-scoped filesystem MCP, andaikc mcp --project .before adding new tools. Treat Context7 as the approved optional docs lookup; treat semantic code-search MCPs as optional repo-scoped additions only whenrepo-mapis too broad. - Package publishing uses the local environment file when needed: load
NPM_TOKENfrom.env.localinto the process environment fornpm whoamiandnpm publish, never print the token, and checkNPM_TOKEN_EXPIRES_ATbefore relying on it.
Validation
For source changes, run:
npm run typecheck
npm run lint
npm run build
For knowledge-only changes, run:
node ai-knowledge/scripts/knowledge-check.cjs
For package/CLI changes, also verify:
npm pack --dry-run
npm whoami
Only add new knowledge here when it is stable and useful for future tasks.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.