Skill Claude CodeCodex
Diagnose a Huntable CTI Studio eval run through the huntable-cti-studio MCP server. Use when asked to diagnose an eval, explain an extractor miss or over-extraction, analyze an eval bundle, or investigate a subagent failure. Diagnosis is agent-side and uses no server-side LLM provider.
Skill Claude CodeCodex
Retrieve and compare Huntable CTI Studio evaluation runs, article eval bundles, and workflow traces through MCP. Use this whenever the user mentions eval bundles, eval runs, config selectors such as v5139a/v5139b, article evaluation traces, CmdlineExtract evaluation, or comparing replicate runs. Start with the…
Agent Claude Code
Reviews schema, config, migration, prompt, and preset changes for drift against this repo's contract sources of truth (src/database/models.py, src/config/workflowconfigschema.py, docs/contracts/.md). Use PROACTIVELY before committing any change that touches models.py, workflowconfigschema.py, scripts/migrate…
Agent Claude Code
Adversarial security review of changes touching authentication, authorization, audit logging, session/CSRF handling, scraper ingestion (SSRF surface), deserialization (pickle/joblib/yaml), or SQL construction. Use PROACTIVELY before committing changes in src/web/ auth/session code, auditservice, scraper/OCR ingestion…
Hook Claude Code
Runs before the agent uses a tool for Edit and Write tool calls, running an inline shell check. From dfirtnt/Huntable-CTI-Studio.
Hook Claude Code
Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From dfirtnt/Huntable-CTI-Studio.
Settings file Claude Code
Agent settings declaring 2 hook events (PreToolUse, PostToolUse).
Skill Claude CodeCodex
Add a new extraction sub-agent to Huntable CTI Studio as a first-class peer of CmdlineExtract, ProcTreeExtract, HuntQueriesExtract, RegistryExtract, ServicesExtract, and ScheduledTasksExtract. Use this skill whenever the user asks to "add a new agent", "create a sub-agent", "wire up a new extractor", "add a new…
Skill Claude CodeCodex
Register a new OpenAI or Anthropic model in CTI Studio so it appears in the Workflow Agent configuration dropdown. Use this skill whenever the user says "add a model", "make gpt-X available", "why isn't model X in the dropdown", "register claude X", "add support for o4", "I want to use gpt-5-pro", or anything about…
Skill Claude CodeCodex
Add a new CTI intelligence source to Huntable CTI Studio for article ingestion. Use this skill when the user says "add a source", "add a feed", "new source", "add this blog", "ingest from ", or wants to configure a new RSS/scraping source for the ingestion pipeline.
Skill Claude CodeCodex
Scaffold, apply, and verify a database schema migration for Huntable CTI Studio following the house pattern (standalone idempotent scripts/migrate.py, NOT Alembic). Use whenever the user asks to "create a migration", "add a column", "add a table", "migrate the schema", "write a migration script", or any schema change…
Skill Claude CodeCodex
Interactive walkthrough for cutting a new release of Huntable CTI Studio. Use this skill whenever the user says "cut a release", "ship a release", "tag a version", "bump the version", "new release", "do the release", "release vX.Y.Z", "ship v5.4.0", "time to release", or otherwise signals they want to move code from…
Skill Claude CodeCodex
Audit and correct the eval fixtures (Eval1 expected counts + Eval2 ground-truth item lists) for one extractor subagent in Huntable CTI Studio: CmdlineExtract, ProcTreeExtract, RegistryExtract, ServicesExtract, ScheduledTasksExtract, or HuntQueriesExtract. Use this skill whenever the user asks to "audit the evals"…
Skill Claude CodeCodex
Full weekly documentation audit and fix cycle for Huntable CTI Studio. Scans all .md and /docs files, validates each against the live codebase, applies factual corrections, and produces a triage summary. Use this skill whenever the user says "huntable-doc-trueup", "weekly doc audit", "true-up the docs", "full doc…
Skill Claude CodeCodex
Verify and refresh the model context-window data in CTI Studio against the latest public developer docs from Anthropic and OpenAI. Use this skill whenever the user says "refresh context windows", "are the context windows accurate", "check model context windows", "update MODELCONTEXTTOKENS", "verify the model catalog"…
Skill Claude CodeCodex
Diagnose and repair troubled CTI intelligence sources in Huntable CTI Studio — sources that ingest 0 articles or rack up recurring fetch failures. Use this skill whenever the user says "heal a source", "fix a broken/failing source", "this source has 0 articles", "why isn't collecting", "diagnose troubled sources"…
Skill Claude CodeCodex
Propagate any change under src/prompts/ (agent prompt files, .txt or extensionless) into all 9 quickstart preset JSONs in config/presets/AgentConfigs/quickstart/. Use this EVERY time a prompt file is edited, created, or renamed — editing src/prompts/ alone silently ships stale prompts to anyone who applies a…
Agent Cursor
Design and product context authority for Huntable CTI Studio. Responds to getdesigncontext and similar requests from ui-designer and other agents. Use proactively when any agent requests design context, brand guidelines, or design system details.
Cursor rule Cursor
Require explicit user approval before running or creating tests that mutate active agent configs.
Cursor rule Cursor
Never docker-compose down -v (preserve volumes); never git commit/push without user confirmation.
Cursor rule Cursor
Fail-closed verification protocol — direct validation required; no speculation; mutable data/config protected.
Cursor rule Cursor
Langchain workflow changes must work regardless of model/provider choice.
Cursor rule Cursor
When the user says lg or LG, you must run the full workflow yourself from hygiene through push to the current branch. Do not stop at commit or ask the user to push manually.
Cursor rule Cursor
Modal UX contract — Escape, click-away, stack, Ctrl/Cmd+Enter.