AnkitClassicVision

AnkitClassicVision/Claude-Code-Deep-Research

Agent Claude Code

Use this agent to assemble the final report files in Phase 5 and to apply post-gate fixes in Phase 6 of deep research. The editor formats and structures; it never adds facts.

AnkitClassicVision/Claude-Code-Deep-Research

Agent Claude Code

Use this agent to convert scout branch notes into evidence ledger rows. Run at every checkpoint during Phase 3 of deep research, before the convergence log is updated.

AnkitClassicVision/Claude-Code-Deep-Research

Agent Claude Code

Use this agent on the draft report during Phase 5 of deep research, after synthesis and before the gates. Mandatory for Deep and Exhaustive tiers and for any decision-tier claim.

AnkitClassicVision/Claude-Code-Deep-Research

Agent Claude Code

Use this agent when sources conflict on a finding-tier or decision-tier claim, or when stoprule.py returns ESCALATESTUCK. Classifies the conflict and picks a canonical value or declares it unresolved.

AnkitClassicVision/Claude-Code-Deep-Research

Agent Claude Code

Use this agent to execute one research branch: search, fetch, and summarize sources for a single hypothesis. Launch one scout per branch, in parallel. Use proactively during Phase 3 of deep research.

AnkitClassicVision/Claude-Code-Deep-Research

Agent Claude Code

Use this agent to verify finding-tier and decision-tier claims in the evidence ledger during Phase 4 of deep research. Must run on a different model than the one writing the synthesis.

AnkitClassicVision/Claude-Code-Deep-Research

Skill Claude CodeCodex

Gate-driven deep research pipeline (V4). Use this skill whenever the user asks for deep research, a research report, due diligence, a literature review, a competitive or market landscape, a technology evaluation, "compare X vs Y with sources", "what does the evidence say about", or any question where the answer will…

AnkitClassicVision/agent-automation-creator

Skill Claude CodeCodex

Diagnose any AI agent, automation workflow, or proposed agent build against AAC 2.0 and produce a marketing-grade HTML wellness report (Summary view + Process Map view). Always use this skill when the user asks to evaluate, audit, score, diagnose, map, visualize, or "AgentTwin" an AI agent, automation, workflow…

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Design or audit an agentic AI workflow with process-first guardrails: deterministic spine, evidence, gates, monitoring, and recovery before autonomy. Use when a user is designing an AI workflow, agent flow, workflow automation, vendor AI deliverable, or autonomy review.

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Write specifications precise enough for autonomous AI coding agents to implement without human intervention. Use when: user wants to spec a feature, system, or tool for agent implementation. Do NOT use for: writing code directly (let agents implement), creating skills (use skill-creator).

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Diagnose, score, map, visualize, or accept an AI agent or workflow using a public closed-loop readiness report. Use for agent specs, automation workflows, vendor proposals, and agentic builds.

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Route prompts by task-demand surface before spending tokens. Use when deciding which model, tool lane, verifier, or human gate a task needs; when a task involves local/private models, small/cheap models, coding, agents, long context, media, compliance, or high-stakes verification.

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Universal codebase operations: analyze, organize, and architecturally deepen any repo. Two commands: /organize for read-only analysis and /deepen for multi-agent refactoring. Use when the user wants a codebase scan, deep module scoring, dependency mapping, architectural improvement, or code-to-skill conversion.…

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Build three context layers (structural, semantic, philosophical) for a module or service, producing production-ready artifacts: a module manifest, behavioral contracts, and a decision log. Use when: (1) a dark code audit identifies high-risk modules, (2) proactively documenting any critical service, (3) a module's…

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Relentlessly interview the user to stress-test a plan, design, docs, or existing codebase before building. Use when the user says "grill me", "grill docs", "grill with docs", wants codebase/domain alignment, wants a CONTEXT.md or ADR-backed interrogation, or needs shared language before implementation.

AnkitClassicVision/ankit_shared_skills

Skill Claude Code

Compact the current conversation into a handoff document for another agent to pick up.

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Use when the user asks to "make sense," "make sense of this," "make it make sense," "this doesn't make sense," or otherwise requests structured comprehension of a confusing idea, decision, plan, document, system, unfamiliar domain, or stuck situation. Produces a visible router, a declared artifact shape, trust-marked…

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Universal project conductor. One command, full pipeline. Auto-detects everything.

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Use when a user asks whether a new external thing, idea, article, tool, repo, framework, competitor move, workflow, or opportunity is worth caring about now. Runs a memory-first triage, maps where the thing applies, and returns exactly one verdict: GO-now, PARK, or KILL.

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Comprehension instrument for AI-mediated work. Triggers when the user says "seeit", "show me the shape", "make this visible", or asks to see/understand/visualize a project, codebase, agent workflow, spec, or AI build at a structural level. Use this skill whenever the user wants to understand the SHAPE of something the…

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Turn any repository into a structured, skill-like decomposition that stays alive for context at all times. Invoke during spec diagramming, brownfield exploration, or at any point in a repo's lifecycle. Auto-creates a skill-pack directory with PROJECT.md (repo-as-skill manifest), context layers, and ADRs. Consumed by…

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

AnkitClassicVision/ankit_shared_skills

Skill Claude CodeCodex

Turn the current conversation context into a PRD and produce a PRD artifact that can be pasted into the project issue tracker. Use when user wants to create a PRD from the current context.