Explore AI Agent Skills & Claude Prompts

Strategy map for what to search WHERE, derived entirely from the candidate profile. The 5 concentric circles (work_mode + relocation) tell you the geographic scope; the 4 source tiers (LinkedIn → ATS aggregators → niche → web) tell you which platforms to drain in order. A scout that searches the wrong tier in the wrong circle wastes its quota and its `scout-coord` partition. Open this skill at boot (after `scout-coord`) and again whenever a circle is exhausted or a `[FEEDBACK]` from the Analyst suggests changing source.

throttle

Pause your loop for N seconds in a tracked way. ALWAYS use this instead of `sleep` whenever you want to slow down your iteration rate to respect the team's rate budget. The duration is read from $JHT_HOME/config/throttle.json (the Captain calibrates per-agent values there); pass --agent <your-name> and the skill resolves the rest. Uses a detached-child pattern that survives any provider tool-call timeout (Kimi 60s, Codex 30s, Claude 120s/600s). Always pair with `jht-throttle-check` before each task to recover if a parent gets killed prematurely. Logs every pause to $JHT_HOME/logs/throttle-events.jsonl. `sleep` for throttle pauses is FORBIDDEN.

cv-disk-audit

Healthcheck periodico (Dottore) per riconciliare CV su disk e cv_pdf_path nel DB. Identifica orfani (file su disk senza riga DB) e ghost (riga DB con cv_pdf_path che punta a file inesistente). Notifica il Capitano sui mismatch così l'utente non perde top PASS invisibili e non vede "CV da scrivere" per CV già scritti.

scout-web-access

Strato web-access cross-provider per gli Scout (F-2). 5 componenti coordinati — anti-bot robust scrape, LinkedIn session + search, email IMAP poll, multi-Scout workspace claim, freshness focus. Usato come stack base per ogni sweep: lo Scout sceglie il livello di accesso più leggero che funziona, e sale solo quando bloccato.

liveness-check

Diagnose whether a team agent's tmux session is alive, in a long turn, or silently dead — and respawn it preserving context if dead. Owned by the Dottore (the team's roving health-check agent), not by the Captain. The core failure mode this skill catches: `jht-tmux-send` returns `exit 0` even when the target CLI has crashed (the message is written into a bare bash, then lost). Without periodic liveness checks the team keeps "talking to a corpse" and the Captain counts on actions that will never happen.

profile-schema

Single source of truth dello SCHEMA del candidate_profile.yml — il formato canonico che TUTTO il team produce e consuma. Modello a 3 livelli: core congelato + blocchi standard + blocchi custom liberi. Definisce i 6 `kind` di blocco che il web sa rendere e la regola di governance (nessun agente inventa il formato). Ogni write del profilo va validato con `jht profile validate`. Riferita da profile-yaml, onboarding-flow, parse-cv, cv-structure.

spawn-doctor

Spawn a fresh DOTTORE on-demand when you (Capitano/Assistente/Sentinella/Mentor) need an immediate health-check round. Use this INSTEAD of writing to the DOTTORE session when the user asks "fai partire il dottore" / "dottora" / "controlla il team", because between scheduled rounds the DOTTORE session is bash residua (one-shot lifecycle, ~10 min active + ~110 min sleeping for next 2h-cycle spawn).

emergency-handling

How to handle rate-limit emergencies and the FATAL cascade when the bridge goes blind. Includes the cooldown-bypass triggers, the L4-SOFT/L5-HARD recovery path, and the RESET SESSIONE handling on a >30-point usage drop.

mentor-output

How the Mentor speaks once a pattern from `mentor-patterns` has crossed the threshold. Three output formats — strategic advice (rare, weighty), weekly digest, on-demand answer — each with strict shape and voice rules. The Mentor's authority comes from how rarely the words come and how heavy each one weighs; this skill enforces that. Owned by the Mentor. Pair with `chat-web` (delivery via jht-send) and `mentor-patterns` (the trigger).