agentleFS
HimadriTryingHimadriTrying/ai-job-search-agent/.claude/skills/company-research/SKILL.md

company-research

Skill1 starsChanged 3 months agoMITView on GitHub

Research a company before applying or interviewing — from a quick pre-application summary to a full interview-prep dossier (4-track web sweep). On demand, and MANDATORY at deep level once an interview process starts.

33 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use business-health-diagnostic, derisk-measurement-advisor and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • nandanosqlSkill

    business-health-diagnostic

    Run a comprehensive business health check across revenue, unit economics, product metrics, and market position — identifying strengths, weaknesses, and the single most important metric to fix.

    Also in 4 projects that use this

  • DIAL-StudioSkill

    derisk-measurement-advisor

    Identify what to measure, test, or track to de-risk a product or AI idea. Use when stress-testing an idea across internal (DUFV) and external (PESTEL) dimensions.

    Also in 3 projects that use this

  • DIAL-StudioSkill

    organic-growth-advisor

    Identify which organic growth path to pursue — new segments, geographies, channels, or products. Use when diagnosing where a growth constraint lives and which McKinsey growth level to act\

    Also in 3 projects that use this

  • nandanosqlSkill

    prioritization-advisor

    Guide PMs in choosing the right prioritization framework — RICE, ICE, Kano, MoSCoW, Value vs Effort, Cost of Delay — by asking adaptive questions about product stage, team context, and data availability.

    Also in 4 projects that use this

  • +8 more from nandanosql

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Public-cover discipline: only publicly sourced facts enter the dossier → everything in it is safe to say aloud.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 25 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

company-research

Two levels. Pick by stage:

  • Level 1 — quick scan (pre-application, feeds cover-letter and the job-scout fit-check): the lightweight summary below.
  • Level 2 — deep dossier (an interview process exists): the 4-track sweep below. Gate rule: a process folder is not prep-ready until its dossier exists. If the private repo is synced (private/), the canonical protocol lives at private/processes/_company-research-protocol.md — follow that version if present; this file is the public, generic mirror.

Inputs

Company name / URL, the JD, web search — in English AND the company's home-market language. Optionally Harmonic MCP (enrich_company) if connected.

Level 1 output — quick scan

  • What they do and how they make money (plain language)
  • Recent news / trajectory / funding or earnings signal
  • Culture signals (from JD language, reviews, public posts)
  • JD decoding (hiring-side inversion): read writing-job-descriptions logic to tell what a requirement really signals vs. boilerplate — what they're actually anxious about.
  • 3-5 things to reference in a cover letter or interview

Level 2 — deep dossier (4-track parallel web sweep)

Fan out four research tracks (parallel agents if available), each returning dated facts with source URLs:

  1. Business trajectory — history, funding, ownership, growth datapoints over time (AUM/revenue/users), headcount, layoffs/expansions, awards, leadership changes, strategy statements, negative coverage.
  2. Products & releases — product ladder evolution, launch dates and volumes, partnerships, pricing, app-store presence + review themes (PM-interview gold), tech stack from job ads, category/market context.
  3. Communications — the company's own channels (podcast/blog/webinars), every findable exec interview 2–3 years back with each person's RECURRING MESSAGES synthesized, PR coverage arc by year, last-6-months news (freshest = best in the room).
  4. Retrospective counterpart — the candidate's current/former employer's PUBLIC trajectory, so any contrast narrative rests entirely on citable sources.

Dossier structure (one file per process, beside the role-prep notes; in the synced private repo: private/processes/<company>/company-research.md): corrections-vs-prior-beliefs → timeline → business performance table → products & releases → competitive context → communications layer → people (public layer) → employer retrospective → interview ammo (talking points, smart questions, a speakable 60-second company story) → morning-of verification list.

Rules:

  • Public-cover discipline: only publicly sourced facts enter the dossier → everything in it is safe to say aloud. Mark facts that independently confirm something known from confidential sources as [PUBLIC COVER]; confidential material never migrates in.
  • Namesake check first — verify the name isn't shared with an unrelated firm before trusting aggregators.
  • Single-source numbers are flagged "don't assert," never averaged. Registry > press > review portals > data vendors.
  • Refresh before every human round; keep a short list of volatile facts to re-verify the morning of.

Feeds cover-letter, interview-coach, and the fit-check in job-scout.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.