all publishers

guerrilla2799

@guerrilla2799 source repo

43 published skills

  1. ▌
    Artifact Eval 2 · guerrilla2799
    The spec-based judge-and-revise loop for job-search artifacts. Use it to grade and improve a resume, cover letter, or outreach message before it's sent ("evaluate this resume", "is this cover letter good enough?", "score my outreach", or automatically inside resume-tailor / cover-letter / networking-and-referrals). Picks the rubric by artifact_type, runs writing-quality DETECT as stage 0, JUDGES against weighted dimensions + hard gates returning PASS/REVISE/FAIL with specific fixes, REVISES surgically, and RE-JUDGES as a fresh pass so nothing rubber-stamps itself. The scored judge. For a slop check on its own with no rubric or score, use `writing-quality`.
    1 repo stars
  2. ▌
    Writing Quality 2 · guerrilla2799
    The anti-AI-slop gate every writing skill runs before its output ships. Use it to check or clean any prose ("does this sound like AI?", "de-slop this", "clean up my cover letter/outreach/LinkedIn post", or automatically as the final pass inside resume-tailor, cover-letter, networking-and-referrals, interview-followup, and linkedin-presence). Two modes: DETECT (name the tells and where they are) and EDIT (rewrite to remove them while preserving every fact and the meaning). The prose pass only. Not the scored rubric judge, which is `artifact-eval` and which calls this as its stage 0.
    1 repo stars
  3. ▌
    Story Bank · guerrilla2799
    Use 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.
    1 repo stars
  4. ▌
    Cover Letter · guerrilla2799
    Use 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.
    1 repo stars
  5. ▌
    Job Sourcing · guerrilla2799
    Use 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.
    1 repo stars
  6. ▌
    Resume Tailor · guerrilla2799
    Use 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.
    1 repo stars
  7. ▌
    Interview Prep · guerrilla2799
    Use 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.
    1 repo stars
  8. ▌
    Job Fit Scoring · guerrilla2799
    Use 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.
    1 repo stars
  9. ▌
    Company Research · guerrilla2799
    Use 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.
    1 repo stars
  10. ▌
    Job Search Setup · guerrilla2799
    Use 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`.
    1 repo stars
  11. ▌
    Interview Debrief · guerrilla2799
    Use 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`.
    1 repo stars
  12. ▌
    Linkedin Presence · guerrilla2799
    Use 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.
    1 repo stars
  13. ▌
    Offer Negotiation · guerrilla2799
    Use 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.
    1 repo stars
  14. ▌
    Interview Followup · guerrilla2799
    Use 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`.
    1 repo stars
  15. ▌
    Application Tracker · guerrilla2799
    Use 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.
    1 repo stars
  16. ▌
    Search And Scale Os · guerrilla2799
    The 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.
    1 repo stars
  17. ▌
    Networking And Referrals · guerrilla2799
    Use 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.
    1 repo stars
  18. ▌
    Eval Loop · guerrilla2799
    Use 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`.
    1 repo stars
  19. ▌
    Data Hygiene · guerrilla2799
    Use 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.
    1 repo stars
  20. ▌
    Agent Rollout · guerrilla2799
    Use 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.
    1 repo stars
  21. ▌
    Agent Scoping · guerrilla2799
    Use 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`.
    1 repo stars
  22. ▌
    AI Governance · guerrilla2799
    Use 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`.
    1 repo stars
  23. ▌
    Artifact Eval · guerrilla2799
    The 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`.
    1 repo stars
  24. ▌
    Signal Pipeline · guerrilla2799
    Use 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.
    1 repo stars
  25. ▌
    Skill Authoring · guerrilla2799
    Use 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.
    1 repo stars
  26. ▌
    Writing Quality · guerrilla2799
    Runs 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.
    1 repo stars
  27. ▌
    Agent Guardrails · guerrilla2799
    Use 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.
    1 repo stars
  28. ▌
    Eval Calibration · guerrilla2799
    Use 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`.
    1 repo stars
  29. ▌
    Ops And Scale Os · guerrilla2799
    The 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`.
    1 repo stars
  30. ▌
    Tam And Sourcing · guerrilla2799
    Use 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.
    1 repo stars
  31. ▌
    Context Portfolio · guerrilla2799
    Use 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.
    1 repo stars
  32. ▌
    Gtm Systems Audit · guerrilla2799
    Use 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`.
    1 repo stars
  33. ▌
    Icp Scoring Engine · guerrilla2799
    Use 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.
    1 repo stars
  34. ▌
    Agent Observability · guerrilla2799
    Use 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.
    1 repo stars
  35. ▌
    Data Model And Sync · guerrilla2799
    Use 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.
    1 repo stars
  36. ▌
    Eval Spec Authoring · guerrilla2799
    Use 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`).
    1 repo stars
  37. ▌
    Martech Stack Audit · guerrilla2799
    Use 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.
    1 repo stars
  38. ▌
    Warehouse And Pipes · guerrilla2799
    Use 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.
    1 repo stars
  39. ▌
    Enrichment Waterfall · guerrilla2799
    Use 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.
    1 repo stars
  40. ▌
    Lifecycle And Routing · guerrilla2799
    Use 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.
    1 repo stars
  41. ▌
    Reporting Architecture · guerrilla2799
    Use 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.
    1 repo stars
  42. ▌
    Credit And Cost Control · guerrilla2799
    Use 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.
    1 repo stars
  43. ▌
    Attribution Architecture · guerrilla2799
    Use 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.
    1 repo stars