القائمة
Logs, categorizes, and prioritizes tech debt as it's incurred. Not a shame exercise -- a managed backlog with pay-down window recommendations and priority scoring.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Master orchestrator for the Solo Dev Suite — a collection of lifecycle skills (scope guardian, sprint planner, pricing architect, launch readiness, ADR generator, security audit, integration mapper, auto-docs, tech debt register, testing strategy) that share a central Project Profile. Triggers on requests like "solo dev suite", "run the suite on {project}", "set up a project profile", "what suite skills apply here", "show my projects", or any direct invocation of a child skill by name when no profile exists yet. Not for one-off tasks with no ongoing project — those stay as standalone skills.
Generates and maintains Architecture Decision Records (ADRs) in the Michael Nygard format -- numbered, sequentially stored Markdown docs capturing context, options considered, decision, and consequences. Triggers on "generate an ADR", "record this decision", "log architecture decision", "why did I choose X", "add an ADR", or "list my ADRs". Part of the solo-dev-suite -- loads the project profile via the orchestrator. Not for runtime config changes (those are just code) or meeting notes (use a wiki).
Generates and maintains project documentation (README, SETUP, ARCHITECTURE, CHANGELOG) by pulling from the profile and sibling sidecars. Re-runnable at every milestone so docs stay current without being a full-time job.
Scans a codebase for local-to-cloud migration blockers -- hardcoded paths, LAN URLs, dev-only bypasses, missing deploy configs -- and produces a scored readiness report. Triggers on "deploy readiness", "ready to deploy", "can I host this", "cloud migration check", "scan for local stuff", "deployment blockers". Part of the solo-dev-suite -- loads the project profile via the orchestrator. Unlike security-audit (a checklist), this skill actually reads code.
Generates a customized design-exploration loop prompt for an existing project by discovering its stack, domain, and aesthetic, then tailoring references and constraints accordingly. Triggers on requests like "design loop on {project}", "refine the UI of this project", "explore design directions for {project}", "make this look more polished", "visual refresh", "modernize the UI", or "UI audit". Not for greenfield design, CSS debugging, or single-component tweaks — requires a target directory with an existing UI surface to analyze.
Comprehensive feature-enhancement discovery skill. Points at any codebase — the current Claude Code workspace, a local source folder, or a Forgejo/Git repo URL — scans the full stack, inventories existing features, surfaces incomplete/stub work, then researches comparable apps and platforms to generate a prioritized list of value-add enhancements. Outputs a structured FEATURE_ENHANCEMENTS.md report. Trigger whenever the user says: "feature enhancement", "what features are we missing", "analyze my codebase for improvements", "compare to competitors", "what should I add next", "audit my app", "run the enhancement skill", "scan for TODOs and features", "what else should this do", or points at a project and asks for improvement ideas. Also triggers when user wants to know how their app stacks up against similar tools or what features competitors have that they don't.
| name | tech-debt-register |
| version | 1.0.0 |
| description | Logs, categorizes, and prioritizes tech debt as it's incurred. Not a shame exercise -- a managed backlog with pay-down window recommendations and priority scoring. |
log.Every item is tagged with one or more: design, code, infra, docs, dependencies, security, ui-ux, testing, performance.
priority = (impact_rank * urgency_rank) / effort_rank
Where impact: low=1, medium=2, high=4, critical=8; urgency: never=0, when-it-bites=1, post-launch-90d=2, post-launch-30d=3, pre-launch=4, now=5; effort: S=1, M=2, L=3, XL=4.
Higher score = pay down first. list --recommend sorts by this.
Reopening moves any status back to open.
Log a new debt item. Sidecar is auto-created on first log.
echo '{"title":"No tests on builder","description":"Shipped without coverage","categories":["testing"],"impact":"high","effort":"L","urgency_window":"post-launch-30d"}' \
| python scripts/debt_tool.py log <slug> --from-stdin
Required: title, description. Defaults: impact=medium, effort=M, urgency=when-it-bites, categories=["code"].
List items with optional filters and recommendation sorting.
python scripts/debt_tool.py list <slug>
python scripts/debt_tool.py list <slug> --recommend
python scripts/debt_tool.py list <slug> --status paid-down
python scripts/debt_tool.py list <slug> --category testing
Show full details of a single item.
python scripts/debt_tool.py show <slug> --id TD01
Mark as paid-down with resolution notes.
python scripts/debt_tool.py resolve <slug> --id TD01 --resolution-notes "Added unit tests"
Mark as won't-fix with required rationale.
python scripts/debt_tool.py accept <slug> --id TD01 --reason "Not worth the effort for this feature"
Move resolved/accepted back to open.
python scripts/debt_tool.py reopen <slug> --id TD01
Generate TECH_DEBT.md with summary, recommendations, open/resolved/accepted sections.
python scripts/debt_tool.py render <slug>
Remove the sidecar. No generated files to clean up.
python scripts/debt_tool.py delete <slug> --yes
| File | Purpose |
|---|---|
scripts/debt_tool.py | CLI with all subcommands |
templates/techdebt.schema.json | Sidecar JSON Schema |
templates/TECH_DEBT.md.tmpl | Rendered doc template |
# 1. Log two items
echo '{"title":"No tests on workout builder","description":"Shipped without tests","categories":["testing"],"impact":"high","effort":"L","urgency_window":"post-launch-30d"}' \
| python scripts/debt_tool.py log my-project --from-stdin
echo '{"title":"Stripe webhook not idempotent","description":"Duplicate deliveries cause duplicate charges","categories":["code","infra"],"impact":"critical","effort":"S","urgency_window":"pre-launch"}' \
| python scripts/debt_tool.py log my-project --from-stdin
# 2. List + recommend (TD02 should rank first: critical/S/pre-launch)
python scripts/debt_tool.py list my-project --recommend
# 3. Resolve TD02
python scripts/debt_tool.py resolve my-project --id TD02 --resolution-notes "Added event_id tracking"
# 4. List open only (should show TD01 only)
python scripts/debt_tool.py list my-project --status open
# 5. Render
python scripts/debt_tool.py render my-project
# 6. Delete
python scripts/debt_tool.py delete my-project --yes