project-crank-engine
Set up aggressive recurring project execution loops (“Crank Engines”) using cron + agent turns, with a strict finish contract. Use when the user asks to keep cranking on a project/sprint (e.g. “set up an aggressive crank engine”, “keep pushing until sprint is done”, “run status every X minutes”), and needs configurable project, recipients, focus scope, quantifiable completion criteria, screenshot evidence, and manager-go/no-go enforcement.
What this skill does
# Project Crank Engine Create repeatable project execution loops that: 1. dispatch focused work/status prompts, 2. run at a user-selected crank intensity (light → aggressive), 3. enforce a measurable finish definition, 4. require visual proof (screenshot) when possible, 5. keep running until completion is truly met. ## Required Inputs Collect these before creating/updating a crank job: - `project`: repo/product name (e.g. SVGMe) - `agentId`: target agent (e.g. `svgme`) - `pace`: `light` | `balanced` | `aggressive` | custom interval - `goal`: explicit sprint objective - `scope`: what to crank on now (epic/story/ticket range) - `recipient`: where updates are delivered (channel + to + account) - `finish_contract`: quantifiable done criteria (must be measurable) If any are missing, ask once in a compact checklist. ## Pace Slider (Preset Profiles) Use these defaults unless the user overrides cadence directly: - **light**: every 30 min, status-first updates, corrective push only for stale/no-progress cycles - **balanced**: every 15 min, execution + status, corrective push on missed cycle goals - **aggressive**: every 8–10 min, execution-heavy, immediate corrective "back in the oven" on any unmet cycle target If user says “aggressive crank engine,” map to aggressive preset. If user says “light crank engine” or “check every half hour,” map to light preset. ## Finish Contract (Non-Negotiable) Never accept vague “done.” Require all of: - **Ticket metric:** e.g. `N/N sprint stories in Done` - **Code metric:** PR merged count / branch state / test pass signal - **Evidence artifact:** screenshot (preferred) + command evidence Minimum evidence set per completion claim: 1. board metric (counts), 2. one screenshot of board/PR state, 3. final command-backed repo state summary. If criteria fail, decision is **NOT DONE** → send corrective prompt and keep crank job active. ## Prompt Template Use `references/prompt-templates.md`. For custom prompts, keep this structure: 1. Mission now 2. Evidence checklist 3. Quantifiable finish contract 4. Decision rule (`DONE` vs `NOT DONE`) 5. Next action if `NOT DONE` Optional helper: - `scripts/render_crank_prompt.py` renders a standardized prompt from parameters. ## Cron Creation Pattern Default to isolated agent turn jobs. - `sessionTarget`: `isolated` - `payload.kind`: `agentTurn` - `schedule.kind`: `every` - `delivery.mode`: `announce` Set interval from pace preset unless user provides explicit cadence. ## Post-Create Verification (Required) After creating/updating crank job: 1. Confirm job exists and is enabled. 2. Confirm `delivery` route is valid (real channel/to/account values, not labels). 3. Force a run once when safe. 4. Verify run history shows `delivered` (not just `status: ok`). If `not-delivered`, fix routing immediately. ## Manager Decision Loop On each crank update: - evaluate against finish contract, - if incomplete: send “back in the oven” corrective direction and continue, - if complete: announce completion with evidence summary and offer to disable/remove job. Do not disable active crank jobs without explicit user approval (unless user asked “run until done, then stop”). ## Decision Authority (Critical) Default behavior is **execute-forward**, not ask-forward. - Crank worker should continue shipping the next concrete slice unless blocked. - Manager (Cack) assumes provisional go-ahead for normal sequencing decisions. - Escalate only for real blockers or high-impact tradeoffs (security/risk/scope). - Do not spam user with repetitive status-only updates lacking progress delta. Required status format each cycle: 1) **Progress delta since last cycle** (what shipped) 2) **Current measurable gap to finish contract** 3) **Next action already started** 4) **Escalation needed?** (yes/no + exact decision if yes) ## Quick Example Trigger User: “Set up an aggressive Crank Engine on project X to finish the sprint.” Execution behavior: - create `every 10m` crank job, - require measurable sprint finish contract, - require screenshot evidence, - keep looping until manager confirms pass.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.