trkbt10/indexion-documentation
Documentation analysis — assess coverage, detect code-to-doc drift with plan reconcile, visualize dependencies with doc graph. Answers "what needs docs?" and "are docs still accurate?"
Documentation analysis — assess coverage, detect code-to-doc drift with plan reconcile, visualize dependencies with doc graph. Answers "what needs docs?" and "are docs still accurate?"
npx skills add https://github.com/trkbt10/indexion-skills/tree/main/skills/indexion-documentationDocumentation analysis — assess coverage, detect code-to-doc drift with plan reconcile, visualize dependencies with doc graph. Answers "what needs docs?" and "are docs still accurate?"
This repo contains 8 individual skills — each has its own dedicated page.
Generate and use a pre-edit structure brief so coding agents learn likely owners, consumer surfaces, and unsafe edit locations before implementing.
Detect and review name/content drift in code using `indexion identity audit`, then plan verified renames, moves, folder changes, or splits.
Debug and inspect KGF specs — view tokenization results, parse trees, and extracted edges from source files. Use when adding/fixing language support or when indexion's analysis output looks wrong.
README construction — initialize template structure, generate per-package READMEs from doc comments, plan writing tasks, assemble root README from docs/ and package READMEs via doc.json config, and verify edits with `plan drift`.
After writing code, detect and clean up duplication at three levels — copy-paste blocks, cross-package shared code, unnecessary wrappers, and concept-level SoT violations. Detect with indexion, fix, and verify.
Generate SDD requirements from RFCs/specs and quantitatively verify implementation conformance. spec draft → spec align → spec verify → automated validation loop with codex/claude. Operate spec-to-impl drift gates as CI checks.
Split text into contextual chunks for RAG/embedding pipelines. Document segmentation and section extraction using window, tfidf, punctuation, or hybrid strategies chosen by intent.
Project wiki lifecycle — create pages, track source changes with ingest, update stale pages, lint structural integrity, detect code-to-doc drift with reconcile, and manage search indexes. A runbook for navigating and maintaining the wiki as an agent.
4 custom Claude Code skills for sales: daily prep, account research, deal review, and prospect decks
Texas county intelligence for water, permits, public evidence, MCP, and field verification.
铁面审计型求职教练。针对 JD 定制简历，编造一条打回一条。升堂→过堂→断案→定稿，全自动。
Custom OpenClaw skills, hooks, and shell scripts for multi-agent ops automation. AI-authored with Claude Code.
Triage Linear or Jira backlogs and run bug sweeps via the Composio CLI. Bulk-fetch issues, dedupe, relabel, reassign, and post summaries — all from the shell without clicking through the UI.
AI Scientist Skills — The complete AI-Scientist-v2 research pipeline reimplemented as a Claude Code skills package, one agent does it all. 将 AI-Scientist-v2 完整科研流程重写为 Claude Code 技能包，单一代理完成从创意到论文的全部工作。