kramme-cc-workflow/skills/kramme:siw:continue/SKILL.md
Entry point for the Structured Implementation Workflow (SIW) — a local, markdown-based workflow for planning, tracking, and implementing multi-step work. Resumes in-flight SIW runs by reading siw/LOG.md and siw/OPEN_ISSUES_OVERVIEW.md, or routes new work to the right SIW subcommand. Triggers on "SIW", "structured workflow", or when siw/LOG.md and siw/OPEN_ISSUES_OVERVIEW.md files are detected.
npx skillsauth add abildtoft/kramme-cc-workflow kramme:siw:continueInstall 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.
A local, markdown-based workflow for planning, tracking, and implementing multi-step work without external services.
This skill is the SIW entry point. When invoked, it:
siw/LOG.md, siw/OPEN_ISSUES_OVERVIEW.md, and the spec document.references/phase-0-resuming.md (read LOG.md "Current Progress", check open issues, continue the next task).It does not directly create, modify, or close SIW documents; that is delegated to the SIW subcommands listed in the Commands Reference table.
siw/LOG.md is present.NOT for: Small bug fixes (<1 day), trivial updates, simple refactoring.
Issues use prefix-based numbering:
G-XXX — General issues (standalone, non-phase)P1-XXX, P2-XXX, etc. — Phase-specific issues| Document | Purpose | Persistence |
| --- | --- | --- |
| siw/[YOUR_SPEC].md | Main specification (single source of truth) | PERMANENT |
| siw/supporting-specs/*.md | Detailed specifications by domain | PERMANENT |
| siw/DISCOVERY_BRIEF.md | Greenfield discovery output before siw:init creates the full workflow | Temporary |
| siw/SPEC_STRENGTHENING_PLAN.md | Refinement discovery output waiting for review or --apply | Temporary |
| siw/AUDIT_IMPLEMENTATION_REPORT.md | Spec compliance audit findings from /kramme:siw:implementation-audit | Temporary |
| siw/AUDIT_SPEC_REPORT.md | Spec quality audit findings from /kramme:siw:spec-audit | Temporary |
| siw/OPEN_ISSUES_OVERVIEW.md + siw/issues/*.md | Work items to implement | Temporary |
| siw/LOG.md | Session progress + decision rationale | Temporary |
Specification (PERMANENT):
Supporting Specs (PERMANENT, optional):
00-overview.md, 01-data-model.md, etc.Issues (TEMPORARY):
siw/LOG.md (TEMPORARY):
┌──────────────────────────────────┐
│ /kramme:siw:issue-define │ Create general work items (G-XXX)
│ /kramme:siw:generate-phases │ Create phase-based issues (P1-XXX, P2-XXX)
│ → siw/issues/ISSUE-{prefix}-XXX-*.md │
└──────────────┬───────────────────┘
│ Implementation
↓
┌──────────────────────────────────┐
│ /kramme:siw:issue-implement │ Work on issues
│ → siw/LOG.md (progress + decisions) │
└──────────────┬───────────────────┘
│ Decisions migrated
↓
┌──────────────────────────────────┐
│ siw/[YOUR_SPEC].md │ ⚠️ PERMANENT - single source of truth
│ (updated via sync step) │
└──────────────────────────────────┘
/kramme:siw:issue-implement)| Command | Purpose |
| --- | --- |
| /kramme:siw:init | Initialize SIW documents (spec, siw/LOG.md, siw/issues) |
| /kramme:siw:discovery | Deep discovery interview — works pre-spec (greenfield) or on existing specs (strengthening). Probes until 95% confident about actual wants. |
| /kramme:siw:issue-define | Define a new work item with guided interview (creates G-XXX issues) |
| /kramme:siw:generate-phases | Break spec into atomic phase-based issues (P1-XXX, P2-XXX, G-XXX) |
| /kramme:siw:issue-implement | Start implementing a defined issue (accepts G-001, P1-001, etc.) |
| /kramme:siw:product-audit | Product critique of specs/plans — evaluates target user, problem/solution fit, user state modeling, and scope correctness |
| /kramme:siw:spec-audit | Audit spec quality (coherence, completeness, clarity, scope, actionability, testability, value proposition, technical design) before implementation |
| /kramme:siw:implementation-audit | Audit codebase against spec for discrepancies, naming misalignments, and missing implementations |
| /kramme:siw:resolve-audit | Resolve audit findings one-by-one with executive summaries, alternatives, and SIW issue creation. Add --auto to let the model choose each resolution without pausing for confirmation. If both audit reports exist, pass the report path to keep the run scoped. |
| /kramme:siw:issue-reindex | Remove DONE issues and renumber remaining within each prefix group |
| /kramme:siw:reset | Reset workflow state (migrate log to spec, clear issues) |
| /kramme:siw:close | Close SIW project, generate docs in docs/<feature>/, remove temporary files |
| /kramme:siw:remove | Clean up all SIW files after completion |
When SIW files already exist, check the current state:
ls siw/LOG.md siw/OPEN_ISSUES_OVERVIEW.md siw/AUDIT_IMPLEMENTATION_REPORT.md siw/AUDIT_SPEC_REPORT.md siw/SPEC_STRENGTHENING_PLAN.md siw/DISCOVERY_BRIEF.md siw/*SPEC*.md siw/*SPECIFICATION*.md siw/*PLAN*.md siw/*DESIGN*.md siw/issues/ 2> /dev/null
| State | Action |
| --- | --- |
| No files exist | Run /kramme:siw:init to set up |
| Discovery brief exists, but no spec yet | Run /kramme:siw:init siw/DISCOVERY_BRIEF.md to turn the brief into a full SIW workflow |
| Discovery brief + strengthening plan, but no spec yet | Review siw/SPEC_STRENGTHENING_PLAN.md, fold accepted changes into siw/DISCOVERY_BRIEF.md, then archive/remove the plan before running /kramme:siw:init siw/DISCOVERY_BRIEF.md. Or run /kramme:siw:init to discard the plan and continue from the brief |
| Spec-strengthening plan exists without a spec | Review or archive the plan first, or run /kramme:siw:init to decide whether to discard it before starting fresh |
| Files exist, resuming | Read siw/LOG.md "Current Progress" section first |
| Spec feels weak or underspecified | Run /kramme:siw:discovery to probe what you actually want and strengthen the spec |
| Starting a new project, want to think it through | Run /kramme:siw:discovery in greenfield mode before creating any spec |
| Need new work item | Run /kramme:siw:issue-define |
| Ready to implement | Run /kramme:siw:issue-implement {number} |
| Spec written, want product validation | Run /kramme:siw:product-audit to evaluate product thinking before implementation |
| Spec written, not yet validated | Run /kramme:siw:spec-audit to check spec quality before implementing |
| Implementation done | Run /kramme:siw:implementation-audit to verify spec compliance |
| Audit report ready | Run /kramme:siw:resolve-audit to triage findings and create issues one-by-one, or add --auto for a non-interactive pass. If both audit reports exist, pass the report path to avoid resolving both. |
| Iteration complete | Run /kramme:siw:reset to start fresh |
| Project complete, want docs | Run /kramme:siw:close to generate documentation and clean up |
| Project complete | Run /kramme:siw:remove to clean up |
When existing SIW files are detected, follow the targeted reading flow in references/phase-0-resuming.md. In short: read the "Current Progress" section of siw/LOG.md, scan siw/OPEN_ISSUES_OVERVIEW.md for status, then either continue the IN PROGRESS issue or pick up the next READY one with /kramme:siw:issue-implement.
┌─────────────────────────────┐
│ (shortcut when confident) │
▼ │
┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐ │
│ READY │ ───────► │IN PROG │ ─────► │IN REVIEW│ ───────► │ DONE │ │
└─────────┘ └────┬────┘ └─────────┘ └─────────┘ │
└──────────────────────────────────────────────┘
Issue States:
When an issue is completed:
## Resolution section/kramme:siw:issue-implement)IN REVIEW (uncertain solution) or DONE (confident solution)All workflow files live in the siw/ folder in the project root:
/
├── siw/
│ ├── [YOUR_SPEC].md ⚠️ PERMANENT (name chosen at init)
│ ├── supporting-specs/ ⚠️ PERMANENT (optional, for large projects)
│ │ ├── 00-overview.md
│ │ ├── 01-data-model.md
│ │ ├── 02-api-specification.md
│ │ └── 03-ui-specification.md
│ ├── AUDIT_IMPLEMENTATION_REPORT.md ⏳ Temporary (audit output)
│ ├── AUDIT_SPEC_REPORT.md ⏳ Temporary (audit output)
│ ├── DISCOVERY_BRIEF.md ⏳ Temporary (greenfield discovery output)
│ ├── SPEC_STRENGTHENING_PLAN.md ⏳ Temporary (refinement handoff artifact)
│ ├── OPEN_ISSUES_OVERVIEW.md ⏳ Temporary
│ ├── issues/ ⏳ Temporary directory
│ │ ├── ISSUE-G-001-setup.md # General issues
│ │ ├── ISSUE-G-002-docs.md
│ │ ├── ISSUE-P1-001-feature-a.md # Phase 1 issues
│ │ ├── ISSUE-P1-002-feature-b.md
│ │ └── ISSUE-P2-001-bug-fix.md # Phase 2 issues
│ └── LOG.md ⏳ Temporary
Use siw/supporting-specs/ when:
Naming convention: NN-descriptor.md (e.g., 01-data-model.md, 02a-cms-ui.md)
When manually creating documents, use the templates in this skill's assets/ directory:
| Document | Template |
| ------------------ | --------------------------- |
| siw/[YOUR_SPEC].md | assets/spec-guidance.md |
| siw/LOG.md | assets/log-template.md |
| siw/issues | assets/issues-template.md |
Tip: Using /kramme:siw:init and /kramme:siw:issue-define is preferred over manual creation.
For detailed guidance on specific phases, read:
| Phase | Resource |
| ---------------------- | ------------------------------------- |
| Resuming existing work | references/phase-0-resuming.md |
| Planning from scratch | references/phase-1-planning.md |
| Handling blockers | references/phase-2-investigation.md |
| Executing tasks | references/phase-3-execution.md |
| Completing work | references/phase-4-completion.md |
development
Compare an existing PR's title and body against the actual branch diff and report drift — false claims, missing major changes, stale scope, missing risk callouts. Use after pushing changes to a branch with an open PR, or before requesting review. Read-only by default; add --fix to delegate to kramme:pr:generate-description for an updated description. Complements kramme:pr:code-review (which checks description accuracy as one signal among many code-quality checks) by being a fast, focused, single-purpose check that runs in seconds.
tools
Reviews plugin skills for focused scope, progressive disclosure, portability, safety, retry behavior, and documentation quality. Use when auditing a SKILL.md, skill directory, or proposed skill text against skill-authoring standards. Not for creating new skills, editing skills, or reviewing ordinary application code.
tools
Reviews recent agent session transcripts to find repeated manual workflows or repeated user asks, then proposes and optionally scaffolds only useful new skills or custom subagents. Use when the user asks to inspect recent sessions, find automation opportunities, or create reusable workflows from repeated work. Not for summarizing one session, general retrospectives, or codebase refactoring.
data-ai
Remove all DONE issues and renumber remaining issues within each prefix group. Not for editing live issue content, archiving still-open issues, or moving issues between prefix groups.