uv-suite 0.28.0 → 0.30.0

package/skills/map-stack/SKILL.md

@@ -1,121 +0,0 @@
----
-name: map-stack
-description: >
-  Map an entire tech stack across multiple codebases/services. Shows how services 
-  relate — API calls, shared databases, message queues, shared libraries, deployment 
-  topology. Use when you need to understand how multiple repos/services fit together.
-argument-hint: "[parent-directory-or-service-list]"
-user-invocable: true
-context: fork
-agent: cartographer
-model: claude-opus-4-6
-effort: max
-allowed-tools:
-  - Read(*)
-  - Grep(*)
-  - Glob(*)
-  - Bash(graphify *)
-  - Bash(repomix *)
-  - Bash(find *)
-  - Bash(git *)
-  - Bash(wc *)
-  - Bash(head *)
-  - Bash(ls *)
-  - Bash(cat *)
----
-
-## Target
-
-$ARGUMENTS
-
-If no target specified, scan the current directory for subdirectories that look like services (contain package.json, pom.xml, go.mod, Cargo.toml, requirements.txt, Dockerfile, etc.).
-
-## Mode: Multi-Codebase Stack Mapping
-
-This is NOT a single-repo mapping. You are mapping an entire tech stack — multiple services, how they connect, and the system-level architecture.
-
-## Project context
-
-!`cat CLAUDE.md 2>/dev/null || echo "No CLAUDE.md found"`
-
-## Prior codebase maps (from /map-codebase runs)
-
-!`cat uv-out/map-codebase.md 2>/dev/null | head -80 || echo "No prior codebase map — will scan from scratch"`
-
-## Discover services
-
-```!
-find . -maxdepth 3 \( -name "package.json" -o -name "pom.xml" -o -name "go.mod" -o -name "Cargo.toml" -o -name "requirements.txt" -o -name "setup.py" -o -name "pyproject.toml" \) -not -path "*/node_modules/*" -not -path "*/.git/*" 2>/dev/null | head -30
-```
-
-## Dockerfiles and compose
-
-```!
-find . -maxdepth 3 \( -name "Dockerfile" -o -name "docker-compose*" \) -not -path "*/node_modules/*" 2>/dev/null | head -20
-```
-
-## Infrastructure (Helm, Terraform, K8s)
-
-```!
-find . -maxdepth 4 \( -name "*.tf" -o -name "Chart.yaml" -o -name "values.yaml" -o -name "*.k8s.yaml" -o -name "kustomization.yaml" \) -not -path "*/node_modules/*" 2>/dev/null | head -20
-```
-
-## API contracts (OpenAPI, gRPC, GraphQL)
-
-```!
-find . -maxdepth 4 \( -name "*.proto" -o -name "openapi*" -o -name "swagger*" -o -name "*.graphql" -o -name "schema.graphql" \) -not -path "*/node_modules/*" 2>/dev/null | head -20
-```
-
-## Process
-
-Follow this sequence:
-
-### 1. Inventory every service
-For each directory that contains a build file, identify:
-- Service name
-- Language / framework
-- What it does (from README, main entry point, or package description)
-- How it's deployed (Docker, K8s, serverless)
-
-### 2. Map connections BETWEEN services
-This is the hard part. Look for:
-- **HTTP/REST calls** — grep for base URLs, API client configs, fetch/axios calls referencing other services
-- **gRPC/Protobuf** — shared .proto files, client stubs
-- **Message queues** — Kafka topics, RabbitMQ queues, SQS queues referenced across services
-- **Shared databases** — same DB connection strings or schema references across services
-- **Shared libraries** — internal packages imported by multiple services
-- **Environment variables** — service URLs configured via env vars (SERVICE_A_URL, etc.)
-
-### 3. Identify the data flow
-- Where does data enter the system? (API gateway, webhook, user upload)
-- How does it flow through services?
-- Where does it end up? (database, external API, user response)
-
-### 4. Produce the stack map
-
-Output a **System Architecture Diagram** (Mermaid) showing:
-- Every service as a node
-- Connections between them (labeled: REST, gRPC, Kafka, shared DB, etc.)
-- External dependencies (third-party APIs, managed services)
-- Data stores (databases, caches, queues)
-
-Then a **Stack Inventory Table**:
-
-| Service | Language | Framework | Database | Deploys to | Depends on | Depended on by |
-|---------|----------|-----------|----------|------------|------------|----------------|
-
-Then a **Connection Matrix** showing which services talk to which:
-
-| | Service A | Service B | Service C | DB-1 | Kafka |
-|---|-----------|-----------|-----------|------|-------|
-| Service A | — | REST | — | R/W | produce |
-| Service B | — | — | gRPC | R | consume |
-
-Then **Danger Zones** at the stack level:
-- Single points of failure
-- Services with the most inbound dependencies (change carefully)
-- Shared databases (schema changes affect multiple services)
-- Missing monitoring or health checks
-
-### 5. If Graphify is available
-Run `graphify run [parent-dir] --directed` on the entire parent directory to get a unified knowledge graph across all services. The graph will show cross-service relationships that are hard to find manually.

package/skills/restore/SKILL.md

@@ -1,55 +0,0 @@
----
-name: restore
-description: >
-  Restore the latest checkpoint for the current session — shows what was done,
-  key decisions, current state, and what's next. With no arguments, picks the
-  current `UVS_SESSION_ID`'s most recent checkpoint. Pass a session id prefix
-  or name to restore from a different session.
-argument-hint: "[<session-id-prefix> | <session-name> | list]"
-user-invocable: true
-allowed-tools:
-  - Read(*)
-  - Bash(ls *)
-  - Bash(cat *)
-  - Bash(grep *)
-  - Bash(find *)
-  - Bash(git rev-parse *)
-  - Bash("$CLAUDE_PROJECT_DIR"/.claude/hooks/checkpoint-helper.sh *)
----
-
-## Available sessions with checkpoints
-
-!`"$CLAUDE_PROJECT_DIR"/.claude/hooks/checkpoint-helper.sh list`
-
-(`*` marks the current session.)
-
-## Latest checkpoint for the current session
-
-!`"$CLAUDE_PROJECT_DIR"/.claude/hooks/checkpoint-helper.sh latest`
-
-## Argument
-
-$ARGUMENTS
-
-## Instructions
-
-1. **If `$ARGUMENTS` is empty or "latest"**: read the checkpoint shown above (the
-   current session's `latest.md`). Summarize it in 3-4 sentences: what was
-   done, current state, what's next. Then ask: "Ready to pick up from here, or
-   do you want to take a different direction?"
-
-2. **If `$ARGUMENTS` is "list"**: just show the user the available-sessions
-   list above and ask which one they want to restore.
-
-3. **If `$ARGUMENTS` looks like a session id prefix** (8-char hex / UUID-ish)
-   **or a session name**: match it against the list above. Read the
-   matching session's `latest.md` from
-   `<project>/uv-out/checkpoints/<full-session-id>/latest.md` using the Read
-   tool, then summarize as in (1).
-
-4. If no match is found, list the available sessions and ask the user to
-   pick one.
-
-When summarizing, include the session's name and purpose from the
-frontmatter at the top of the checkpoint — that's the context the next
-session needs to know what it's picking up.

package/skills/security-review/SKILL.md

@@ -1,87 +0,0 @@
----
-name: security-review
-description: >
-  OWASP-informed security review. Uses Semgrep, Gitleaks, and Trivy when available.
-  Falls back to AI-only analysis. Use on code touching auth, payments, data access,
-  or external inputs.
-argument-hint: "[file-or-directory]"
-user-invocable: true
-context: fork
-agent: security
-model: claude-opus-4-6
-effort: high
-allowed-tools:
-  - Read(*)
-  - Grep(*)
-  - Glob(*)
-  - Bash(git diff *)
-  - Bash(semgrep *)
-  - Bash(gitleaks *)
-  - Bash(trivy *)
-  - Bash(npm audit *)
-  - Bash(pip audit *)
-  - Bash(go vuln *)
-  - Bash(cargo audit *)
----
-
-## Target
-
-$ARGUMENTS
-
-## Changes to review
-
-!`git diff --cached --stat 2>/dev/null || git diff --stat 2>/dev/null || echo "Reviewing full project"`
-
-### Full diff
-
-!`git diff --cached 2>/dev/null || git diff 2>/dev/null || echo ""`
-
-## Danger zones
-
-!`cat DANGER-ZONES.md 2>/dev/null || echo "No DANGER-ZONES.md found"`
-
-## Prior analysis
-
-### Codebase map
-
-!`cat uv-out/map-codebase.md 2>/dev/null | head -80 || echo "No codebase map found"`
-
-### Recent code review findings
-
-!`cat $(ls -t uv-out/review-*.md 2>/dev/null | head -1) 2>/dev/null | head -60 || echo "No prior review found"`
-
-### Recent slop check
-
-!`cat $(ls -t uv-out/slop-check-*.md 2>/dev/null | head -1) 2>/dev/null | head -40 || echo "No prior slop check found"`
-
-## Available security tools
-
-```!
-echo "=== Semgrep ===" && semgrep --version 2>/dev/null || echo "not installed (pip install semgrep)"
-echo "=== Gitleaks ===" && gitleaks version 2>/dev/null || echo "not installed (brew install gitleaks)"
-echo "=== Trivy ===" && trivy --version 2>/dev/null || echo "not installed (brew install trivy)"
-```
-
-## SAST scan (Semgrep, if available)
-
-```!
-semgrep --config auto --json --quiet . 2>/dev/null | head -100 || echo "Semgrep not available — will use AI-only analysis"
-```
-
-## Secret detection (Gitleaks, if available)
-
-```!
-gitleaks detect --source . --no-git --report-format json 2>/dev/null | head -50 || echo "Gitleaks not available — falling back to grep"
-```
-
-## Grep-based secret scan (fallback)
-
-```!
-grep -rn "password\s*=\|api_key\s*=\|secret\s*=\|token\s*=" --include="*.ts" --include="*.js" --include="*.py" --include="*.java" --include="*.go" . 2>/dev/null | head -20 || echo "No obvious secrets found"
-```
-
-## Dependency audit
-
-```!
-trivy fs --scanners vuln --format json . 2>/dev/null | head -80 || npm audit --json 2>/dev/null | head -50 || pip audit 2>/dev/null | head -50 || echo "No dependency scanner found"
-```

package/skills/session-end/SKILL.md

@@ -1,100 +0,0 @@
----
-name: session-end
-description: >
-  Cleanly close the current UV Suite session: write a final manual checkpoint
-  (full conversation context), then mark the session as terminated so the
-  Watchtower dashboard flips its lifecycle badge to Terminated. Use before
-  closing the terminal when you want a deliberate end-of-session beat.
-argument-hint: "[optional-label]"
-user-invocable: true
-allowed-tools:
-  - Write(*)
-  - Read(*)
-  - Bash(git status *)
-  - Bash(git diff *)
-  - Bash(git log *)
-  - Bash(git branch *)
-  - Bash(git rev-parse *)
-  - Bash(date *)
-  - Bash(ls *)
-  - Bash(mkdir *)
-  - Bash(cat *)
-  - Bash(echo *)
-  - Bash("$CLAUDE_PROJECT_DIR"/.claude/hooks/checkpoint-helper.sh *)
-  - Bash("$CLAUDE_PROJECT_DIR"/.claude/hooks/session-end-helper.sh *)
----
-
-## Resolve checkpoint directory + session metadata
-
-!`"$CLAUDE_PROJECT_DIR"/.claude/hooks/checkpoint-helper.sh dir`
-
-!`"$CLAUDE_PROJECT_DIR"/.claude/hooks/checkpoint-helper.sh frontmatter`
-
-## Git state
-
-!`git branch --show-current 2>/dev/null || echo "(not a git repo)"`
-
-!`git status --short 2>/dev/null | head -20 || echo "(no git)"`
-
-!`git log --oneline -5 2>/dev/null || echo "(no git history)"`
-
-## Step 1 — Write the final checkpoint
-
-Write a file at `<checkpoint-dir>/final-YYYY-MM-DD-HHMM.md` using the current
-timestamp. **Override** the frontmatter line `checkpoint_kind: auto-mechanical`
-to read `checkpoint_kind: final-manual` so it's distinguishable from the
-auto-checkpoints. Also write/overwrite `<checkpoint-dir>/latest.md` with the
-same content so `/restore` picks it up.
-
-If a label was provided, include it in the filename:
-`<checkpoint-dir>/final-YYYY-MM-DD-HHMM-[label].md`
-
-### Label
-
-$ARGUMENTS
-
-### Body structure (after the frontmatter)
-
-```markdown
-# Final checkpoint: [date] [time] [label if provided]
-
-## What was accomplished
-- Concrete things done across the whole session — files, commits, decisions
-- One bullet per significant artifact; don't pad
-
-## Key decisions made
-- Decision: Why — what was considered, what was rejected
-
-## Current state
-- Branch / uncommitted changes / tests status / blockers
-
-## Open threads
-- Anything left in flight that the next session needs to pick up
-- Pending reviews, awaiting input, deferred work
-
-## Context the next session needs
-- Non-obvious facts, workarounds, "this looks wrong but it's intentional because…"
-```
-
-Be specific. This is the last record before the session closes — anything
-not written here is lost unless it's in code or the auto-checkpoints.
-
-## Step 2 — Mark the session terminated
-
-Once the file is written, run:
-
-!`"$CLAUDE_PROJECT_DIR"/.claude/hooks/session-end-helper.sh`
-
-Show the user the two-line output. Don't add commentary — the file write
-and the termination signal together speak for themselves.
-
-## Notes
-
-- `/session-end` does **not** close the terminal or exit Claude Code. After
-  it runs, the badge flips to Terminated in the Watchtower; the user
-  closes the terminal manually.
-- The final checkpoint uses the live session's full conversation context —
-  higher fidelity than the auto-checkpoint summaries because Claude has
-  everything in working memory at this moment.
-- If you only want to terminate without a checkpoint, run
-  `hooks/session-end-helper.sh` directly from bash and skip this skill.

package/skills/session-init/SKILL.md

@@ -1,45 +0,0 @@
----
-name: session-init
-description: >
-  Label or relabel the current UV Suite session — sets name, kind (long-running
-  vs outcome), purpose, and priority (low/med/high). Metadata appears in the
-  watchtower dashboard. Use when you skipped the launcher prompt or want to
-  rename a session mid-flight.
-argument-hint: "<name> | --kind long|outcome | --purpose <text> | --priority low|med|high | show | clear"
-user-invocable: true
-allowed-tools:
-  - Bash("$CLAUDE_PROJECT_DIR"/.claude/hooks/session-meta.sh *)
----
-
-## Apply /session-init $ARGUMENTS
-
-!`HELPER="$CLAUDE_PROJECT_DIR/.claude/hooks/session-meta.sh"; ARGS="$ARGUMENTS"; if [ -z "$ARGS" ] || [ "$ARGS" = "show" ]; then "$HELPER" show; elif [ "$ARGS" = "clear" ]; then "$HELPER" clear; else FIRST=$(printf '%s' "$ARGS" | awk '{print $1}'); REST=$(printf '%s' "$ARGS" | sed 's/^[^ ]* *//'); case "$FIRST" in --kind) "$HELPER" set-kind "$REST" ;; --priority) "$HELPER" set-priority "$REST" ;; --purpose) "$HELPER" set-purpose "$REST" ;; --name) "$HELPER" set-name "$REST" ;; *) "$HELPER" set-name "$ARGS" ;; esac; fi`
-
-## Instructions
-
-Show the user the output of the command above. Do not add commentary — the
-command itself confirms what changed. The dashboard reflects changes within
-a few seconds (next event refreshes session metadata).
-
-## Usage
-
-```
-/session-init                                  show current values
-/session-init show                             show current values
-/session-init <free-text name>                 set the name (default action)
-/session-init --kind long                      set kind: long-running
-/session-init --kind outcome                   set kind: outcome
-/session-init --priority high                  set priority: low | med | high
-/session-init --purpose <free text>            set the purpose
-/session-init clear                            clear name, kind, purpose, priority
-```
-
-## Notes
-
-- The session id is generated by `uv.sh` at launch and exported as
-  `UVS_SESSION_ID`. If you launched `claude` directly, this falls back
-  to an `ad-hoc-<timestamp>` id.
-- Metadata lives at `.uv-suite-state/sessions/<id>.json`.
-- Persona is captured at launch time and is not editable from here —
-  re-launch with a different `uv` persona to change it.
-- Each invocation sets one field at a time. Run multiple times to set more.

package/skills/slop-check/SKILL.md

@@ -1,40 +0,0 @@
----
-name: slop-check
-description: >
-  Detect AI-generated slop in code, tests, docs, and architecture.
-  Run before merging any AI-generated changes.
-argument-hint: "[file-or-directory]"
-user-invocable: true
-context: fork
-agent: anti-slop-guard
-model: claude-opus-4-6
-effort: high
-allowed-tools:
-  - Read(*)
-  - Grep(*)
-  - Glob(*)
-  - Bash(git diff *)
-  - Bash(git log *)
----
-
-## Target
-
-$ARGUMENTS
-
-## Changes to scan
-
-!`git diff --cached --stat 2>/dev/null || git diff --stat 2>/dev/null || echo "No changes — scan target files directly"`
-
-### Full diff
-
-!`git diff --cached 2>/dev/null || git diff 2>/dev/null || echo ""`
-
-## Prior analysis
-
-### Architecture decisions (check code against stated rationale)
-
-!`cat uv-out/architecture/decisions.md 2>/dev/null | head -40 || echo "No architecture decisions found"`
-
-### Recent review findings
-
-!`cat $(ls -t uv-out/review-*.md 2>/dev/null | head -1) 2>/dev/null | head -40 || echo "No prior review found"`

package/skills/write-evals/SKILL.md

@@ -1,34 +0,0 @@
----
-name: write-evals
-description: >
-  Write evaluations for AI system prompts and inferencing layers.
-  Use when building or modifying LLM-powered features.
-argument-hint: "[prompt-file-or-description]"
-user-invocable: true
-context: fork
-agent: eval-writer
-model: claude-opus-4-6
-effort: high
-allowed-tools:
-  - Read(*)
-  - Grep(*)
-  - Glob(*)
-  - Write(*)
-  - Edit(*)
-  - Bash(npm run eval *)
-  - Bash(pytest *)
----
-
-## Target
-
-$ARGUMENTS
-
-## Existing eval framework
-
-!`find . -name "*eval*" -o -name "*evals*" 2>/dev/null | head -10 || echo "No eval files found"`
-
-## Prior analysis
-
-### Spec (requirements to evaluate against)
-
-!`cat $(ls -t uv-out/specs/*.md 2>/dev/null | head -1) 2>/dev/null | head -60 || echo "No spec found"`

package/skills/write-tests/SKILL.md

@@ -1,54 +0,0 @@
----
-name: write-tests
-description: >
-  Generate meaningful tests that verify behavior. Use after implementing a feature or when
-  coverage is low. Matches project test conventions.
-argument-hint: "[file-or-module-to-test]"
-user-invocable: true
-context: fork
-agent: test-writer
-model: claude-sonnet-4-6
-effort: high
-allowed-tools:
-  - Read(*)
-  - Grep(*)
-  - Glob(*)
-  - Write(*)
-  - Edit(*)
-  - Bash(npm test *)
-  - Bash(npm run test *)
-  - Bash(npx jest *)
-  - Bash(npx vitest *)
-  - Bash(pytest *)
-  - Bash(go test *)
-  - Bash(cargo test *)
-  - Bash(mvn test *)
----
-
-## Target
-
-$ARGUMENTS
-
-## Existing test patterns (match these)
-
-!`find . -name "*.test.*" -o -name "*.spec.*" -o -name "test_*" 2>/dev/null | head -5`
-
-!`cat $(find . -name "*.test.*" -o -name "*.spec.*" 2>/dev/null | head -1) 2>/dev/null | head -40 || echo "No existing tests found"`
-
-## Project test command
-
-!`cat package.json 2>/dev/null | grep -A2 '"test"' || echo "No package.json test script"`
-
-## Prior analysis
-
-### Spec (what to test against)
-
-!`cat $(ls -t uv-out/specs/*.md 2>/dev/null | head -1) 2>/dev/null | head -60 || echo "No spec found — test based on code behavior"`
-
-### Acts plan (current task context)
-
-!`cat uv-out/architecture/acts-plan.md 2>/dev/null | head -40 || echo "No acts plan found"`
-
-### Session checkpoint
-
-!`cat uv-out/checkpoints/latest.md 2>/dev/null | head -40 || echo "No checkpoint"`