Claude-skill-registry klondike-agent-workflow
Manage multi-session AI agent workflows using klondike CLI. Use when working on klondike-managed projects (those with .klondike/ directory), when starting/ending coding sessions, tracking features through lifecycle, or maintaining coherence across context window resets. Triggers on session management, feature tracking, progress handoffs, and verification workflows.
install
source · Clone the upstream repo
git clone https://github.com/majiayu000/claude-skill-registry
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/klondike-agent-workflow" ~/.claude/skills/majiayu000-claude-skill-registry-klondike-agent-workflow && rm -rf "$T"
manifest:
skills/data/klondike-agent-workflow/SKILL.mdsource content
Klondike Agent Workflow
Klondike bridges context windows for long-running agent sessions. Critical: Always use CLI commands—never directly read/edit .klondike/*.json files or agent-progress.md.
CRITICAL: Common Mistakes to Avoid
❌ NEVER do these:
(wrong syntax - useklondike --help
alone orklondike
without --help)klondike <command>
(wrong - just run the command, it will show usage)klondike feature --help- Read
directly (use.klondike/features.json
)klondike feature list - Edit
manually (auto-generated, changes are lost)agent-progress.md
without feature ID (must beklondike feature start
)klondike feature start F001- Feature IDs like
orf001
(must be uppercase:1
)F001
✓ DO these:
alone shows all commandsklondike
to see featuresklondike feature list
for detailsklondike feature show F001
to see project overviewklondike status
Quick Decision Tree
Starting work? → klondike status → klondike session start --focus "F001 - desc" Working on feature → klondike feature start F001 Feature complete? → Test E2E → klondike feature verify F001 --evidence "..." Blocked? → klondike feature block F001 --reason "..." Ending session? → klondike session end --summary "..." --next "..."
Session Lifecycle
1. Session Start (Always Do First!)
klondike status # See project state klondike validate # Check artifact integrity klondike session start --focus "F001 - Login UI" # Begin session klondike feature start F001 # Mark feature in-progress
2. During Work
- One feature at a time (tracked by
)feature start - Commit after each meaningful change
- Test incrementally, not at end
- If blocked:
klondike feature block F001 --reason "..."
3. Session End (Before Leaving!)
klondike feature verify F001 --evidence "test-results/F001.png" klondike session end --summary "Done" --next "Implement logout"
Core Commands
| Action | Command | Notes |
|---|---|---|
| Status | | Always start here |
| Add feature | | --notes is critical |
| Start feature | | One at a time |
| List features | | Never read JSON directly |
| Show details | | View single feature |
| Verify | | E2E test first |
| Block | | When stuck |
| Start session | | Begin work |
| End session | | Before leaving |
Essential Rules
Always:
- Start every session with
to see project stateklondike status - Use
when adding features (gives future agents critical context)--notes - Capture evidence (screenshots, logs) before
feature verify - Run pre-commit checks before every commit
- End sessions with
session end --summary ... --next ...
Never:
- Use
orklondike --help
(wrong syntax - see Common Mistakes)klondike feature --help - Read or edit
files directly (use CLI commands).klondike/*.json - Edit
manually (auto-generated, edits are lost)agent-progress.md - Verify features without E2E testing (unit tests aren't enough)
- Commit code with failing tests, lint errors, or build failures
Pre-Commit Checks
Detect project type and run checks. Never commit if any fail.
Python (uv):
uv run ruff check src tests && uv run pytestNode.js:
npm run lint && npm run build && CI=true npm testRust:
cargo clippy && cargo testGo:
golangci-lint run && go test ./...
Reference Files (Load As Needed)
Load these only when you need specific details:
- commands.md: Full CLI reference with all options/flags
- workflows.md: Multi-session patterns, worktrees, complex scenarios
- troubleshooting.md: Error recovery and corrupted state fixes