.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/leopu00/job-hunter-team
home/skills/leopu00/job-hunter-team
leopu00 avatar

leopu00/job-hunter-team

59 skills

View on GitHub
$npx skills add leopu00/job-hunter-team
SkillInstalls
agent-emergencyCapitano — gestisce un agente sospettato BLOCCATO IN UN LOOP ATTIVO (vivo e che genera turni, ma ripete lo stesso ciclo senza produrre: ping-loop di ACK con un…—application-flowDB + filesystem contract every Scrittore follows when taking a position from `scored` (≥50) to `ready`/`excluded`.—blind-reviewThe Critic's full review protocol — receive PDF + JD, run a blind review (no profile access), produce a structured verdict with score 1-10 + 7 fixed sections +…—bridge-mailboxDrain pending bridge verdicts at the START of every Captain turn — MANDATORY first action before doing anything else.—bridge-pacingTranslate a `[BRIDGE PACING]` 15-min calibration tick into per-agent throttle adjustments.—cache-pruneReclaim disk on the shared JHT caches (`uv` wheel cache + `codex` SQLite log) every ~24h.—captain-diaryDaily handoff diary for the Captain. The Captain is restarted often (context-refresh, new work window, reboot) and otherwise loses the day's hard-won pacing…—chat-webReply to the user when they message you from the JHT web chat.—check-usage-httpCheck provider usage via HTTP fast path (~2s, zero CLI tokens). PRIMARY action when the bridge fails to read usage.—check-usage-tuiCheck provider usage via TUI worker (~30s, costs CLI tokens). FALLBACK when `check-usage-http` returns RATE_LIMIT or fails.—circles-and-sourcesStrategy map for what to search WHERE, derived entirely from the candidate profile.—critic-loopRun the mandatory 3-round CV review loop with the Critico — autonomously, without going through the Capitano.—cv-disk-auditHealthcheck periodico (Dottore) per riconciliare CV su disk e cv_pdf_path nel DB.—cv-structureWrite the CV markdown that will be PDF'd and reviewed by the Critico.—daily-restart-wavePre-emptive mass-restart of every team agent once per 24h for context freshness. Owned by the Dottore.—db-insertInsert NEW records into the JHT DB (positions / scores / applications / companies / position_highlights).—db-queryQuery the JHT SQLite DB (positions, applications, stats). Use it whenever you need position status, per-agent queues, scores, match rate, or record counts.—db-updateUpdate existing records in the JHT DB (positions / applications).—decision-throttleReference table mapping `proj` (projected usage at reset) to a Sentinel state and a throttle level (0-4).—email-monitorDay-start sourcing dalla casella email DEDICATA del team (l'utente vi inoltra i propri job alert).—emergency-handlingHow to handle rate-limit emergencies and the FATAL cascade when the bridge goes blind.—expiration-trackingEstrae deadline dal JD (helper deadline_extract) e produce alert utente quando una candidatura READY sta per scadere (helper expiration_alerts, idempotente).—feedback-queryRead user feedback (like/dislike/hide/star) for a given position from the cloud.—first-run-burstThe first half-hour a brand-new user ever watches the team work.—format-timeConvert UTC timestamps to the user's timezone before showing them in chat, charts, Telegram, or any user-facing output.—game-reply-optionsOffer 2-5 context-specific clickable reply buttons in the JHT game chat when they genuinely make the user's next decision easier.—graceful-shutdownClose the working day on request from the user. Triggered by a `[SHUTDOWN]` message from @utente.—liveness-checkDiagnose whether a team agent's tmux session is alive, in a long turn, or silently dead — and respawn it preserving context if dead.—location-enrichmentStandardize positions.location free-text into structured loc_*/work_*/role_family columns BEFORE marking any position as `checked`.—logo-extractionExtract the company logo for a company in the companies table and store it as a small base64 data-URI (max ~35KB, min 32px).—maintainer-sweepLo sweep di manutenzione INFRA del Mantenitore 👷‍♂️ (gemello del Dottore, scope infrastruttura non agenti).—memory-stateState variables the Sentinel must keep across ticks (last order sent, freeze flag, FATAL streak, per-state counters, emergency history, cooldowns).—mentor-outputHow the Mentor speaks once a pattern from `mentor-patterns` has crossed the threshold.—mentor-patternsThe five patterns the Mentor hunts in the records to decide WHEN to speak. Silence is the default; only a real, recurring pattern earns a word.—notify-useroffice-geocodingonboarding-flowparse-cvpipeline-triageposition-insertprofile-schemaprofile-summariesprofile-yamlpy-tools-auditrate-budgetrecheck-livenessresiliencesalary-estimatescaling-calcscout-coordscout-web-accesssentinel-orderssession-refreshspawn-agentspawn-doctortelegram-sendthrottletmux-senduser-reply-check