guerrilla2799
- 41 skills
- 0 followers
- 9 hours ago last updated
- ▌ Story Bank · guerrilla2799Use to build or expand a reusable bank of STAR interview stories, when a user says "build my story bank", "prep my stories", "help me answer behavioral questions", or before interviews start. Interviews the user to extract 8–12 strong stories spanning the common competency areas, writes them to stories/story-bank.md, and flags coverage gaps to fill.
- ▌ Cover Letter · guerrilla2799Use when the user says "write a cover letter," "draft a note for this application," or wants a letter for a specific job. Proposes 2–3 angles, picks one, and drafts a tailored one-page letter addressed to a real hiring manager. No slop, no fabrication.
- ▌ Job Sourcing · guerrilla2799Use when the user wants to find open roles. Trigger phrases: "find me jobs", "source roles", "what's open at my target companies", "check for new postings". Reads profile/target-roles.md and target-companies.md, searches company career pages and ATS boards plus aggregators via web search, dedupes, runs a scam/legitimacy screen, and appends new roles to pipeline/tracker.csv as status=found with stable ids. Never auto-applies.
- ▌ Resume Tailor · guerrilla2799Use when the user says "tailor my resume," "make this ATS-friendly," or points at a specific job. Reworks the master resume to one JD, mirrors real keywords, runs an ATS check, and reports coverage plus unmet must-haves. Zero fabrication.
- ▌ Interview Prep · guerrilla2799Use to prepare for a specific interview, when a user says "I have an interview", "prep me for the [company] screen", "help me get ready for the hiring-manager round", or names an interview stage. Reads the JD, company research, and story bank, builds a stage-specific prep pack (likely questions, mapped stories, positioning, objections, questions to ask), and optionally runs a mock interview with rubric critique. Before the interview only. Afterwards use `interview-followup`, or `interview-debrief` if a transcript exists.
- ▌ Job Fit Scoring · guerrilla2799Use after job-sourcing, or when the user says "score these roles", "which jobs should I go after", "rank my pipeline", "is this one worth applying to". Scores each found role 0–100 against profile/ with a transparent weighted rubric, sets fit_score + priority (A/B/C), moves A/B roles to status=researching, and writes a ranked shortlist. Deal-breakers auto-disqualify. Never inflates fit.
- ▌ Company Research · guerrilla2799Use when the user needs to understand a target company or interviewer before writing a cover letter, prepping for an interview, or deciding whether to pursue a role. Trigger phrases: "research this company", "who is my interviewer", "what should I know about X before I apply/interview", "build me a dossier". Produces a company + interviewer dossier that powers cover-letter and interview-prep.
- ▌ Job Search Setup · guerrilla2799Use FIRST, before any other job-search skill, when a user starts a job search, says "set up my job search", "onboard me", "build my profile", or when workspace/profile/ is empty. Imports the user's resume, interviews them to fill gaps, and writes the profile/ files (profile.md, target-roles.md, target-companies.md) plus documents/master-resume.md that every other skill reads. The one-time foundation. Not the ongoing cadence or next-action routing, which is `search-and-scale-os`.
- ▌ Interview Debrief · guerrilla2799Use when the user recorded an interview and has a transcript. Trigger phrases: "here's the transcript from my interview", "analyze my interview recording", "debrief my Granola/Otter/Fathom transcript", "grade how I did and write the follow-up". Reads the transcript, grades the interview (what went well, what to improve, start/stop/continue, per-answer critique, patterns across rounds), then drafts recruiter and interviewer follow-up emails, both writing-quality and artifact-eval gated, and feeds the findings back into the story bank, interview-prep, tracker, and application record. Requires a transcript. Without one, use `interview-followup`.
- ▌ Linkedin Presence · guerrilla2799Use when the user wants their LinkedIn profile working for the search. Trigger phrases: "optimize my LinkedIn", "fix my headline", "am I findable by recruiters", "should I turn on Open to Work", "what should I post while job hunting", "help me connect with people at target companies". Audits and rewrites the profile for recruiter search, sets a light posting cadence, and builds a targeted-connection plan.
- ▌ Offer Negotiation · guerrilla2799Use when the user has an offer (or competing offers) in hand. Trigger phrases: "I got an offer", "help me negotiate", "should I take this?", "compare these two offers", "how do I counter?". Benchmarks total comp against market, breaks down every component, builds a weighted decision matrix, separates reversible from irreversible terms, and generates a counter-offer script plus a contract red-flags check. Never accepts or sends on the user's behalf.
- ▌ Interview Followup · guerrilla2799Use right after an interview, when a user says "I just finished the interview", "help me write a thank-you note", "debrief me", or "the [company] round is done". Drafts a 24-hour thank-you note (writing-quality gated), runs a structured debrief, and closes the learning loop by feeding new questions/answers back into the story bank, application record, and tracker. After the interview, and the no-recording path, working from memory. Before it, use `interview-prep`. With a transcript, use `interview-debrief`.
- ▌ Application Tracker · guerrilla2799Use when the user says "add this job to my tracker," "update the pipeline," "what's my status," or "what's overdue". Maintains pipeline/tracker.csv and the per-application records, runs an integrity check, and renders a pipeline-health dashboard. The source of pipeline truth.
- ▌ Search And Scale Os · guerrilla2799The front door and operating cadence for the whole job-search OS. Use it to start or resume a search ("help me run my job search", "where am I at?", "what should I do next?", "run my weekly review", "search-and-scale-os"). Reads pipeline state, shows search health, recommends the single next best action, runs the weekly review with volume targets and a retro, and routes to the right one of the 17 skills at every stage. Coaches the rhythm: consistent weekly volume plus referral-first applying beats spray-and-pray. Runs the cadence. Not the first-run profile build, which is `job-search-setup` and must exist first.
- ▌ Networking And Referrals · guerrilla2799Use when the user wants a warm way into a target company. Trigger phrases: "get me a referral", "who do I know at X", "find a warm intro", "reach out to the hiring manager", "is there a path in besides the portal". Maps warm paths into a company/role, ranks them by strength, names the hiring manager and recruiter, and drafts the right personalized outreach message for the human to send.
- ▌ Eval Loop · guerrilla2799Use to run a quality check on any generated artifact, or when the user says "evaluate this", "score this draft", "is this good enough", "run the eval", "review this output", "check it against the rubric". Runs generate, judge, revise, re-judge, approve with the judge in a separate context so nothing grades its own work. Logs every cycle including failures. Writes to workspace/evals/log/. Scores your AI system output against a rubric you wrote. Not for writing that rubric (`eval-spec-authoring`), and not the pre-handoff gate on a deliverable this repo produced, which is `artifact-eval`.
- ▌ Data Hygiene · guerrilla2799Use when the user says "clean this list", "we have duplicates", "dirty data", "data hygiene", "our CRM is a mess", "bounce rate is high", "stale records", "dedup", "normalize this". Runs the pre-paid cleanup pass, builds the ongoing decay and dedup loop, and produces a refresh queue driven by freshness rather than by calendar. Writes workspace/data/hygiene-report.md.
- ▌ Agent Rollout · guerrilla2799Use when shipping an agent to other people, or when the user says "nobody uses it", "roll this out", "how do I distribute this", "adoption", "train the team on it", "package this as a plugin", "version it". Handles packaging, distribution, the first-run experience, accountability, and the adoption metrics that decide whether the build succeeded. Writes workspace/agents/<name>/rollout.md.
- ▌ Agent Scoping · guerrilla2799Use before building any AI agent or skill, or when the user says "should we build an agent for this", "can AI do this", "automate this workflow", "where should we use AI", "build me an agent". Decides what to build, what to refuse, and what to leave manual. Produces an agent brief with a success threshold and a kill criterion. Writes workspace/agents/<name>/brief.md. Scopes one agent. Not the org-level AI policy, data boundary, or readiness question, which is `ai-governance`.
- ▌ AI Governance · guerrilla2799Use before rolling AI to a GTM team, or when the user says "AI policy", "shadow AI", "people are pasting customer data into ChatGPT", "AI governance", "are we allowed to use AI for this", "are we ready to use AI here", "the team is scared AI replaces them", "what data can go into the model", "works council", "AI compliance". Produces the usage policy, the data boundary, the disclosure rules, and the adoption plan that addresses fear rather than ignoring it. Writes workspace/agents/ai-policy.md. Sets policy for the team. Not for deciding whether one specific agent is worth building, which is `agent-scoping`.
- ▌ Artifact Eval · guerrilla2799The output gate for this repo. Runs on any deliverable before it is handed over, and also when the user says "review this deliverable", "is this ready", "check this before I send it", "quality check". Verifies the artifact is complete, honest about its assumptions, and free of the specific failures each artifact type is prone to. Returns a receipt. Gates deliverables this repo produced. To score your own AI system output against a rubric, with a separate judge and a logged cycle, use `eval-loop`.
- ▌ Signal Pipeline · guerrilla2799Use when the user says "buying signals", "intent data", "trigger events", "job change alerts", "we get signals and nothing happens", "is this intent data worth it", "signal monitoring", "hiring triggers". Builds a signal taxonomy with decay windows, dedup, severity thresholds, and an explicit signal-to-play routing table. Includes the backfill discrimination test for vendor renewal. Writes workspace/data/signal-taxonomy.csv.
- ▌ Skill Authoring · guerrilla2799Use when writing or fixing a Claude Code skill, or when the user says "write a skill", "my skill never triggers", "the wrong skill loads", "skill description", "turn this into a skill", "extract a skill", "the skill is too long". Covers anatomy, trigger design, negative boundaries, context economy, and the router pattern for large skill sets. Writes the SKILL.md.
- ▌ Writing Quality · guerrilla2799Runs automatically on any prose this repo produces that a human outside the team will read. Also use when the user says "does this sound like AI", "de-slop this", "clean up this copy", "check the writing", "make this sound human". Strips the machine tells, enforces the banned list, and returns the text with a receipt. Never skipped on external-facing prose.
- ▌ Agent Guardrails · guerrilla2799Use before shipping any agent to another person, or when the user says "guardrails", "the agent did something it shouldn't", "spend limits", "it emailed the wrong person", "safety rails", "what stops it from", "it wrote to the CRM". Defines the refusal set, spend ceilings, mandatory pre-checks, escalation paths, and human gates, then puts the hard ones where persuasion cannot reach them. Writes workspace/agents/<name>/guardrails.md.
- ▌ Eval Calibration · guerrilla2799Use after editing any eval spec, or when the user says "our scores keep going up", "is the rubric still right", "calibrate the spec", "rubric drift", "the eval passes everything now", "recalibrate". Regrades the frozen anchor set, measures drift, and distinguishes a generator that improved from a ruler that stretched. Writes workspace/evals/calibration/<type>-<date>.md. Tests the ruler, not the work. To judge an artifact use `eval-loop`, and to write or rewrite the rubric itself use `eval-spec-authoring`.
- ▌ Ops And Scale Os · guerrilla2799The router for Ops & Scale OS. Use when the user says "ops and scale", "GTM engineering", "AI ops", "build the GTM system", "our data is a mess", or is not sure which skill they need. Reads the situation, names the constraint, and routes to exactly one skill. Also use to orient somebody new to the repo. Front door only. It routes and does not do the work: the audit itself is `gtm-systems-audit`, and scoping one agent is `agent-scoping`.
- ▌ Tam And Sourcing · guerrilla2799Use when the user says "how big is our TAM", "source my market", "build the universe", "pull a list of companies", "market sizing", "where do we find these accounts", "we need more accounts in the funnel". Sizes the addressable universe, then pulls it in cost-controlled pages with dedup against what already exists. Writes workspace/data/universe.csv.
- ▌ Context Portfolio · guerrilla2799Use before building any agent that needs to know how a company operates, or when the user says "the agent doesn't know our positioning", "onboard the agent", "where does the messaging live", "our AI keeps getting the voice wrong", "context for the agent", "operating manual". Builds the ten-module written record every agent reads from, so positioning changes once and propagates everywhere. Writes workspace/agents/context/*.md.
- ▌ Gtm Systems Audit · guerrilla2799Use at the start of any engagement, or when the user says "audit our systems", "where do we start", "what's broken in our GTM", "assess our stack", "we need to fix our operations", "new client onboarding". Scores all four layers 1 to 5, names the single constraint, and returns a sequenced fix plan with gates. Writes workspace/audit/systems-audit.md. Scores all four layers. Not a tool-by-tool inventory of what you pay for, which is `martech-stack-audit`.
- ▌ Icp Scoring Engine · guerrilla2799Use when the user says "build a scoring model", "ICP score", "lead scoring", "our score doesn't work", "fit and intent", "which accounts should reps work", "MQL threshold", "prioritize this list". Builds fit and intent as separate axes, fits thresholds to the real distribution, and runs the discrimination test before shipping. Writes workspace/data/scoring-model.md.
- ▌ Agent Observability · guerrilla2799Use when instrumenting anything before scaling it, or when the user says "how is the agent performing", "we have no visibility", "instrument this", "logging", "telemetry", "cost per run", "is it getting worse", "correction rate". Defines what to log, what to alert on, and the weekly review that catches degradation before a user does. Writes workspace/evals/telemetry-spec.md.
- ▌ Data Model And Sync · guerrilla2799Use before any list build, enrichment run, or CRM integration, or when the user says "what counts as an account", "our data model", "field mapping", "the sync is broken", "records are duplicating", "which system is the source of truth", "parent child accounts". Defines the object model, keys, field-level direction of truth, and sync rules. Writes workspace/data/object-model.md and a data dictionary.
- ▌ Eval Spec Authoring · guerrilla2799Use before building anything whose output needs a quality bar, or when the user says "write a rubric", "eval spec", "how do we score this", "define what good looks like", "quality bar", "grading criteria", "our AI output is inconsistent". Encodes judgment as hard gates plus weighted dimensions with 1-to-5 anchors and a frozen calibration set. Writes workspace/evals/specs/<type>.md. Writes the rubric. Not for running it against an artifact (`eval-loop`) or retesting it against its anchors (`eval-calibration`).
- ▌ Martech Stack Audit · guerrilla2799Use when the user says "audit our stack", "too many tools", "martech spend", "tool consolidation", "what should we cut", "renewal coming up", "our stack is too expensive", "do we need this tool", "CFO wants cuts". Inventories the stack, computes spend against revenue, finds redundancy and dead weight, and returns a KEEP / CONSOLIDATE / CUT / ADD verdict per tool with a defensible savings number. Writes workspace/stack/stack-audit.md.
- ▌ Warehouse And Pipes · guerrilla2799Use when the user says "should we get a warehouse", "reverse ETL", "dbt", "composable CDP", "our data lives in twenty tools", "is our data AI-ready", "ELT", "Snowflake or BigQuery", "single source of truth for GTM data", "the definitions live in five systems". Decides whether a warehouse is justified yet, designs the layers if it is, and names the cheaper fix if it is not. Writes workspace/data/data-architecture.md.
- ▌ Enrichment Waterfall · guerrilla2799Use when the user says "enrich this list", "find emails", "our match rate is low", "which provider should we use", "enrichment is expensive", "build a waterfall", "fill in these fields". Designs a cost-ordered multi-provider waterfall with a free gate in front, verification, graceful exit, and per-tier economics. Writes workspace/data/waterfall-spec.csv.
- ▌ Lifecycle And Routing · guerrilla2799Use when the user says "lifecycle stages", "MQL definition", "lead routing", "round robin", "speed to lead", "leads are sitting untouched", "sales says the leads are bad", "SLA", "handoff", "who owns this lead". Defines stages as exit criteria, sets routing rules and SLAs with real measurement, and fixes the handoff that generates the recurring lead-quality argument. Writes workspace/reports/lifecycle.md.
- ▌ Reporting Architecture · guerrilla2799Use when the user says "our dashboards disagree", "build a scorecard", "board reporting", "what should we report", "metric definitions", "too many dashboards", "nobody trusts the numbers", "what's our source of truth for reporting". Builds the metrics dictionary with one definition and one owner per metric, then a layered reporting stack that stops the recurring definition argument. Writes workspace/reports/metrics-dictionary.csv.
- ▌ Credit And Cost Control · guerrilla2799Use before any run that spends money, or when the user says "credits are burning", "our enrichment bill is too high", "how much will this cost", "forecast credits", "compare providers", "set a spend limit", "we blew through our credits". Runs the pre-flight, forecasts the run, compares providers on cost per usable record, and installs ceilings that fail closed. Writes workspace/data/cost-model.csv.
- ▌ Attribution Architecture · guerrilla2799Use when the user says "attribution", "what did marketing source", "our numbers don't match sales", "multi-touch", "first touch last touch", "campaign influence", "prove marketing ROI", "which channel is working". Defines sourced, influenced, and accelerated with enforceable rules, sets the model and window before the campaign, and kills the double-counting. Writes workspace/reports/attribution-model.md.