danmcinerney
- 36 skills
- 0 followers
- 6 hours ago last updated
- ▌ Shotgun · danmcinerney bundleFan out a user's research or codebase-investigation prompt across installed CLI coding agents, then synthesize the best findings. Use when the user says /shotgun, asks for shotgun research, wants multiple agent opinions, wants to compare Codex/Claude/Cursor/Antigravity/Pi/OpenCode/Gemini/Qwen/Aider/Goose/Amp/Copilot or similar CLI agents, or asks Codex to use all available coding CLIs for research before producing a report.
- ▌ Tdd · danmcinerney bundleTest-driven development for factory builders. Use when a ship job implements at the issue's pre-agreed seams — the red -> green loop, one test then one minimal implementation per cycle, never a refactor while RED.
- ▌ To Spec · danmcinerneySpec-writing stage skill for the architect factory: synthesizes the run's conversation, repo evidence, and research findings into `docs/spec/<run>.md` after grounding. Invoked by the strategist subagent the orchestrator dispatches during `/architect` intake — or directly by the orchestrator in `/architect-fast` (that skill's stage-skill deltas apply) — before decomposition into issues.
- ▌ Architect · danmcinerney bundleUse when the user asks to architect, run or continue the autonomous software factory, turn a goal into a hardened tracker issue plan, dispatch builder jobs, grade finished work, diagnose blockers, or finish a factory run.
- ▌ Integrate · danmcinerneyFactory-context integrate stage (end-of-run shipping) for one dedicated builder subagent dispatched by the orchestrator after the fix wave has merged, after a GREEN verdict, or after a recorded ruling skips the review. First step is the docs pass — update product docs from the change-context digest — then end-of-run integration, postflight, PR or markdown finish prep, and a digest DRAFT; returns evidence for the orchestrator to rule on.
- ▌ To Issues · danmcinerneyUse when decomposing a hardened spec into tracker issues: cutting tracer-bullet vertical slices through every layer, ordering structural work first with blocking edges, maximizing the disjoint parallel frontier, publishing producer/consumer interface contracts, and attaching a compact change-skeleton to each issue. Invoked only from an explicit architect dispatch — by the harden strategist subagent in `/architect`, or directly by the orchestrator in `/architect-fast` — after the spec is written; never left to description-trigger discovery.
- ▌ Final Review · danmcinerney bundleUse for the closing whole-run review in the architect factory — the only model review in the loop: dispatched by the orchestrator, at finish, to one fresh strategist subagent that audits the entire run diff for defects only isolated parallel slices can produce, checks the merged whole against the spec, verifies every candidate finding, and delivers a review spec plus draft fix issues and draft graded checks — it never edits product code or the mutable test suite. Never description-triggered or self-invoked mid-run; the orchestrator calls it explicitly once every issue has closed.
- ▌ Frozen Checks · danmcinerneyUse when the strategist drafts per-issue graded checks after decomposition and before builder dispatch. Produces one check file per issue at `docs/checks/<run>/<slice>.md`, frozen in git, read-only after.
- ▌ Architect Fast · danmcinerneyUse when the user asks to architect-fast a change, run the light factory lane, or factory-build a small goal — a few files, roughly one sitting, at most ~3 parallel issues — into a specced plan with parallel builders, one builder-performed closing review-and-fix, and a single PR. Same loop shape as /architect with the per-issue grading machinery removed; for larger, riskier, or many-issue work use /architect instead.
- ▌ Codebase Design · danmcinerney bundleShared vocabulary for designing deep modules and for naming factory concepts consistently. Load before writing a spec, decomposing issues, freezing checks, or reviewing a diff - anywhere "module," "interface," "issue," or "frozen check" need to mean the same thing to every skill, builder, and reviewer. Also covers dependency categories for deepening and the parallel design-it-twice pattern for exploring interfaces before committing to one.
- ▌ Adversarial Review · danmcinerneyUse when the architect factory orchestrator dispatches a fresh strategist subagent to harden a draft spec: falsify it with file:line evidence, fold the surviving findings into a revised spec, decompose it (issues plus checks), and stress-test its own decomposition before returning all drafts. Never commits, touches the tracker, or edits product code.
- ▌ Architect Research · danmcinerney bundleUse when the user asks for discovery-scale research that informs a decision: brainstorming a project or feature, choosing a technology, or requests like "research X", "what's the state of the art", or "deep research". Use this skill to turn broad, uncertain questions into sourced decision evidence and a reusable research handoff. For narrow slice-level fact checks inside the build loop, /architect handles those inline.
- ▌ Orch Work · danmcinerney bundleDelegate a requested result to a fresh native child agent with relevant guidance.
- ▌ Orch Review · danmcinerney bundleDelegate independent review of identified work to a fresh native child who did not make it, without repairs.
- ▌ Orch Self Improve · danmcinerney bundleReview selected native agent history to improve the local environment, custom workflows, or Orchflows itself.
- ▌ Orch Build Workflow · danmcinerney bundleCreate or improve workflows, domain guidance and specializations; try them on representative work and refine from observed use.
- ▌ Orch Dynamic Workflow · danmcinerney bundleCoordinate a requested task and one final independent review.
- ▌ Evolve · danmcinerney bundleIteratively improve any artifact and its improvement harness, inventing evaluation when needed; supports bounded runs, tournaments and continuous resumable search.
- ▌ Design Loop · danmcinerney bundleDevelop a project endgoal through N bounded cycles of brainstorm and research, design, implementation, comparison testing and analysis.
- ▌ Short Video · danmcinerney bundleCreate short videos for any genre or placement, then independently review the actual exports.
- ▌ Search Site · danmcinerney bundleDelegate bounded source collection and return locally ranked inspectable evidence, or a worker handle for composition.
- ▌ Test Increment · danmcinerney bundleIndependently test exact baseline and candidate states against a supplied comparison plan without repairing either state.
- ▌ Rank Evidence · danmcinerney bundleDelegate one independent review of supplied evidence into a globally ranked, cited assessment.
- ▌ Social Search · danmcinerney bundleResearch bounded public source scopes, then return one independent ranked assessment.
- ▌ Design Increment · danmcinerney bundleTurn a project goal, options and research into one scoped implementable increment and an old-versus-new evaluation plan.
- ▌ Research Options · danmcinerney bundleInvestigate bounded uncertainties in proposed project increments and return evidence for choosing a design.
- ▌ Make Short Video · danmcinerney bundleMake an original short video through an editable project and rendered exports using one maker.
- ▌ Analyze Iteration · danmcinerney bundleAnalyze one project increment's design and comparison evidence, recommend adopt or retain, and inform the next brainstorm.
- ▌ Brainstorm Options · danmcinerney bundlePropose a few scoped next increments from an endgoal, current state and prior observations.
- ▌ Review Short Video · danmcinerney bundleIndependently examine the exact exported short video with one fresh reviewer and no repairs.
- ▌ 3d Browser Game · danmcinerney bundleBuild substantial Three.js browser games from mechanics brainstorming through playable experiments, Blender assets, progression, QA and independent agent playtests. Use for a complete game or an explicitly bounded production phase.
- ▌ Brainstorm Research · danmcinerney bundleGenerate project improvement options, then research their decision-relevant uncertainties for design.
- ▌ Implement Increment · danmcinerney bundleImplement one approved-scope design in an isolated candidate and return its exact reproducible state.
- ▌ Research Acquire · danmcinerney bundleAcquire bounded keyless public records through discovery, semantic candidate selection and resumed depth reads.
- ▌ Make Blender Game Assets · danmcinerney bundleCreate original Blender game assets with editable sources, GLB exports and inspection through a game's Three.js loader using one maker.
- ▌ Playtest 3d Browser Game · danmcinerney bundleIndependently play and assess an exact Three.js game build, covering usability, mechanics, QA and rendered assets using one fresh reviewer without repairs.