deep-code-intelligence
Evidence-driven workflow for hard coding problems, architecture decisions, root-cause analysis, and high-stakes implementation planning in Claude Code
What this skill does
# Deep Code Intelligence Use this skill when the task is too important, ambiguous, or coupled for a fast “implement first” approach. ## Goal Increase solution quality by forcing Claude to gather evidence, expose hidden assumptions, and compare multiple paths before changing code. ## Core loop ### 1. Build a repo fingerprint Collect only the facts that change the decision: - key modules and ownership boundaries - hot paths and integration seams - build/test entrypoints - persistence and migration surfaces - feature flags / config gates ### 2. Extract constraints Split into: - **explicit constraints** — user asks, tests, types, configs, docs - **implicit constraints** — backward compatibility, ordering, idempotency, auth, observability, performance envelopes ### 3. Create a hypothesis ladder Do not settle on one explanation early. Generate: - most likely explanation, - strongest competing explanation, - weird but costly explanation. Prefer the next step that invalidates bad theories quickly. ### 4. Build an evidence matrix Use a compact table: | Topic | Evidence | Confidence | Next check | |---|---|---:|---| | Cause of failure | stack trace + source path + failing test | 0.78 | reproduce with logging | If confidence is low, say so plainly. ### 5. Compare options Every serious recommendation should beat at least one credible alternative. Score options on: - correctness - complexity - blast radius - reversibility - validation speed - long-term maintainability ### 6. Stage validation Front-load cheap validation: 1. static checks / grep / type clues 2. unit or focused tests 3. integration checks 4. runtime observation 5. broad regression sweep ### 7. Capture residual risk End with what is still unknown and what would change the recommendation. ## Heuristics - Prefer narrow fixes when system understanding is weak. - Prefer structural fixes when the same class of defect is likely to recur. - Prefer observability improvements when certainty is low. - Prefer reversible migrations over one-shot transformations. - Prefer behavior-oriented tests over implementation snapshots. ## Escalation guide | Situation | Escalate to | Why | |---|---|---| | Need repo-wide synthesis | `principal-engineer-strategist` | Better architectural judgement and option scoring. | | Need multi-track execution | `team-orchestrator` | Handles parallel work and audit loops. | | Need library or framework truth | `research-orchestrator` + Context7 | Reduces hallucination risk and validates API usage. | | Need final pressure-test | `audit-reviewer` or `/cc-council` | Catches blind spots before delivery. | ## Minimal output standard A good response should include: - problem frame, - evidence summary, - constraints, - at least 2 options, - recommendation, - validation plan, - residual risk.
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.