mjmorales/plan-step
skills/plan-step/SKILL.md
Interactive planning and requirement gathering for a specific task/step from the active run's plan.json. Use when the user wants to dig into a numbered step (e.g., "Let's work on step 1.2.3") to create detailed requirements, make design decisions, identify edge cases, and define test strategies BEFORE implementation.
$ install --global
skillsauthnpx skillsauth add mjmorales/claude-prove plan-stepInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 19, 2026, 4:12 AM4.8s3 files scanned
SKILL.md
- name:
- plan-step
- description:
- Interactive planning and requirement gathering for a specific task/step from the active run's plan.json. Use when the user wants to dig into a numbered step (e.g., "Let's work on step 1.2.3") to create detailed requirements, make design decisions, identify edge cases, and define test strategies BEFORE implementation.
Plan Step Workflow Skill
Interactive planning for a specific step from the active run's plan.json. No code is written during this phase — planning only.
Constraints
- Do not write implementation code during planning. Surface ambiguity instead of assuming.
- Reference existing code patterns from the codebase when discussing approaches.
- Follow
references/interaction-patterns.mdfor AskUserQuestion vs free-form decisions.
Workflow
1. Parse the Step Reference
Extract the step id from the user's request (e.g., 1.2.3). Resolve the active run via the worktree marker, then read the step with:
scripts/prove-run step-info <step-id>
Returns JSON: {task, step, task_state, step_state}. Use it to extract description, acceptance criteria, dependencies.
2. Create Planning Workspace
python3 scripts/init_planning_workspace.py <step_id> "Task Title Here"
Creates .prove/plans/plan_<step_id>/ with 8 template files (overview, requirements, design decisions, open questions, potential issues, implementation plan, test strategy, progress tracker).
Populate 06_test_strategy.md with validators from .claude/.prove.json. See references/validation-config.md.
3. Interactive Planning
- Present the task + step overview (rendered from plan.json)
- Probe for missing requirements
- Present design approaches with tradeoffs
- Surface risks
- Update planning files during discussion
- Keep
progress.mdcurrent (plan-step scratchpad, not state.json)
4. Question Patterns
- Discrete interpretations: AskUserQuestion with options. Include "Research & proceed" when 3 or fewer options (per
references/interaction-patterns.md). - Open-ended: free-form ("What should happen when [edge case]?")
- Validation: "How will we know this works?" / "What does success look like?"
5. Handling Dependencies
Check plan.json tasks[].deps for prerequisites. If deps unmet, discuss whether to plan despite them, document interface assumptions, and consider mocks for testing.
6. Ready for Implementation
Verify: open questions resolved, implementation plan actionable, test strategy covers key scenarios, design decisions documented with rationale.
Use AskUserQuestion with header "Ready" and options: "Begin Implementation" / "Review Plan First".
On proceed: the orchestrator will drive step execution — plan-step does not mutate state.json. Leave that to the orchestrator and its run_state step start / step complete calls.
References
references/planning-patterns.md— risk matrices, requirement patterns, design frameworks, complexity estimationreferences/interaction-patterns.md— AskUserQuestion vs free-form patterns
Committing
Delegate to the commit skill. Do not create ad-hoc commits.
Related Skills
mjmorales/janitor
tools
VerifiedTrustedCommunity
Clean and compact prove's durable memory layers — team Lore, the Codex (scrum decisions), annotations, and contributor artifacts — keeping the tribal knowledge that grows team accuracy and folding away the rot. Triggers on "janitor", "clean the lore", "compact the lore", "compact the codex", "memory cleanup", "clean up team memory", "prune stale decisions", "tidy tribal knowledge", "lore cleanup". You are the driver: the CLI emits inventories and executes writes; the `memory-janitor` agent judges each entry; a per-team batch gate approves; nothing is ever deleted — consolidation, promotion, and supersession only.
2SKILL.mdUpdated Jun 9, 2026
mjmorales/smart-compaction
testing
VerifiedTrustedCommunity
Anchor session context into prove primitives before compaction and rehydrate from them after. Built-in compaction summarizes by recency and drops the claude-prove state an agent needs to reorient; this skill externalizes volatile context into durable anchors (scrum tasks, decisions, run-state, a compact-anchors pointer file) pre-compact, then runs a deterministic reorientation sequence post-compact. Use before a manual /compact, when context is about to auto-compact, or immediately after a compaction. Triggers on "smart compact", "prepare for compaction", "anchor before compact", "context is getting long", "rehydrate", "reorient after compact".
2SKILL.mdUpdated Jun 5, 2026
mjmorales/run-migrate
tools
VerifiedTrustedCommunity
Apply model-driven CONTENT reshaping to stored run artifacts that sit behind the current schema, on explicit operator invocation only. Triggers on "migrate runs", "migrate run artifacts", "run content migration", "reshape run artifacts", "bring runs to current schema". You are the driver: the `run-state migrate-runs` CLI mechanically detects which artifacts are behind and emits a plan naming each one plus its migration-instruction file; you read the instructions and reshape the prose/findings, gated by the operator. The deterministic `schema migrate` handles structural column moves; this skill covers only the content reshaping beyond them. Never run as a background or resident loop — only when the operator asks.
2SKILL.mdUpdated Jun 5, 2026
mjmorales/reasoning-brief
tools
VerifiedTrustedCommunity
Synthesize the 7-section risk-forward Review Brief from a run's reasoning log. Triggers on "reasoning brief", "review brief", "synthesize the brief", "generate the brief", "brief the run", "brief for review", "story brief". You are the driver: the `acb brief` CLI renders a mechanical preservation-safe backbone and proves preservation; you synthesize the narrative prose (summary + changes), single-pass or multipass over episode chunks, then gate it through Stage-1 (mechanical, blocking) and Stage-2 (prose judge, advisory).
2SKILL.mdUpdated Jun 5, 2026