本文へ移動
cccskills
無料GitHub で公開

goals

Turns a target someone has already committed to (a board plan, an annual plan, a contract) into a plan the team can measure: KPIs in three tiers with a guardrail for each, a baseline from real data, monthly pacing with lag and seasonality, and two or three channels chosen from how your ICP actually searches and buys. Writes context/goals/MMYY-scope.md and context/goals/measurement.md. It never invents the target. Triggers: "set our goals", "what are our KPIs", "revenue target and pacing", "which channels and what targets", "write the scope file", "are we on track". Run after /funnel-strategy. Not for designing funnel stages (use /funnel-strategy).

インストール方法を見る

含まれるファイル(1)

  • SKILL.md5.9 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Goals

Every later piece of marketing work should start from context/goals/. This skill fills it. It takes a number someone has already committed to and works out what to measure, where you stand today, how fast you need to move each month, and which channels will carry it, so anyone can tell by the 10th of the month whether you're on track.

It never invents the target. No committed number, no run: ask for it.

When to use it

  • The last step of the context folder, after /funnel-strategy.
  • A new financial year, a new plan or a new contract.
  • When someone asks "what are we actually trying to hit, and through which channels?"

Don't use it to design funnel stages (/funnel-strategy), or for traction goals before the product has any repeatable way to win customers.

Two modes

Ask once, then proceed.

Company modeEngagement mode
WhoIn-house marketer, founder, head of marketingConsultant or agency, per client
Target fromBoard plan, annual plan, revenue targetContract, statement of work, signed proposal
Baseline fromYour CRM, last 12 monthsThe client's CRM, analytics and reports

Inputs

Required: the target, with a date and its source.

Recommended:

  • a CRM export for the last 12 months (strip names and emails first; keep aggregates only)
  • context/goals/MMYY-funnel.md from /funnel-strategy, for the stages and conversion rates
  • context/icp/, for where buyers search, compare and decide
  • analytics or ad reports, for traffic and channel numbers

Missing inputs don't stop the run. Mark each gap [TBD: collect X] and say what would fill it.

Paths. Write context/goals/MMYY-scope.md and context/goals/measurement.md. Agency or consultant? Swap context/ for clients/<client>/context/ throughout.

Steps

  1. Pin the target. Quote it with its source: "£450k new revenue by 31 Aug 2027 (FY plan, slide 4)". Keep ranges and scenarios as given. Ask how much risk the business will accept and how fast it needs results. That caps how aggressive the pacing can be.

  2. Choose one focus for this period: pipeline, new customers, activation, retention, expansion or a launch. A team that pushes every number at once moves none of them.

  3. Set KPIs in three tiers, three per tier at most:

    • Outcome: the target itself.
    • Drivers: the two or three numbers on the focus that lead to the outcome, taken from the funnel (qualified opportunities and win rate for pipeline; activation rate for activation).
    • Activity: what the team controls week to week, one per channel.
  4. Give every driver and activity KPI a guardrail: the number that must not get worse while you push it. Lead volume versus lead quality. Send volume versus unsubscribes. Discounting versus win rate.

  5. Set baselines. Today's number for every KPI, from its real source, with the count it rests on. Fewer than 20 deals, or under six months of history, is a direction, not a fact: say so next to the number. A new channel has no baseline. Give it a test budget, not a target.

  6. Find the gap and pace it. The gap is the target minus where today's run rate lands. Work it back through the funnel's conversion rates to the volume needed each month. Pace with:

    • the sales cycle lag (pipeline leads revenue by one typical cycle)
    • seasonality from the company's own history
    • a ramp for new channels
    • low, medium and high scenarios

    Don't put the gap-closing work in the last month, where it can't land in time.

  7. Pick channels from ICP behaviour. From context/icp/, list where buyers search, compare and decide. Shortlist two or three channels. Give each one job, one metric and the activity KPI it owns, and name the constraint likely to cap it (budget, people, content, sales capacity). Every channel must trace to a line in the ICP file, not to habit.

  8. Write measurement.md. One entry per KPI and guardrail: the source, the exact counting rule, the cadence and the owner. A KPI with no possible source moves to open questions.

  9. Hand off in three lines: the target and the gap, the focus and its drivers, the channels.

Output shape

MMYY-scope.md:

  1. Target with source, and the gap.
  2. Focus.
  3. KPI table: tier, KPI, guardrail, baseline (with count), target.
  4. Monthly pacing table with low, medium and high.
  5. Channels: job, metric, constraint, ICP evidence.
  6. Open questions.

measurement.md: KPI, source, counting rule, cadence, owner.

What good looks like

  • The target is quoted, not estimated.
  • Every KPI has a guardrail, a baseline and a source.
  • Small samples are flagged once.
  • Pacing respects lag and seasonality instead of a flat line to the target.
  • Nobody has to ask how a number is counted.

Mistakes to avoid

  • Inventing or "suggesting" the target.
  • Rates as outcomes. The outcome is a total, such as revenue or customers.
  • KPIs with no guardrail, which get gamed.
  • Channels picked because the team already uses them, not because buyers do.
  • Personal data in the saved files.

Chain

The final step of the suggested chain: /company-context → /icp-research → /competitor-research → /win-loss → /expert-pov → /tov-guidelines → /brand-kit → /positioning → /messaging → /funnel-strategy → goals.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

brand-kit

無料

Extracts a company's visual identity from screenshots (best) or its website (fallback) and writes a DESIGN.md brand file: machine-readable tokens for colours, typography, spacing, corner radius and logo usage, plus short prose explaining how and when to use each, and a list of do's and don'ts. Any later page, deck, carousel or ad can read the tokens instead of guessing. Triggers: "brand kit", "brand guidelines", "extract our brand", "design tokens", "colours and fonts from", "visual identity", "DESIGN.md". Not for tone of voice (use /tov-guidelines) or messaging (use /messaging).

日本語の概要は準備中です。原文の説明を表示しています。

matteotitta/repo-structure-in-house632026年10月14日 更新

Researches a company from its website and public sources and writes a company profile: what it sells, who buys it, traction, funding, team, hiring, tech stack, key people, red flags and the gaps you still need to fill, every claim tagged with a source and a confidence level. Use it as the first file in a marketing context folder, or to prep a discovery call or qualify a prospect. Triggers: "company research", "company background", "company context for", "qualify this prospect", "discovery call prep", "account brief", or a company URL handed over for research. Not for competitor analysis (use /competitor-research) or customer profiles (use /icp-research).

日本語の概要は準備中です。原文の説明を表示しています。

matteotitta/repo-structure-in-house632026年10月14日 更新

Researches one B2B SaaS competitor across 13 dimensions (company, product, ICP, pricing, reviews, content, launches, search and AI visibility, tech stack, hiring, go-to-market, social, paid ads) and writes a sourced dossier with an executive summary, a threat level, strengths and weaknesses, and a data gaps section. Run it once per competitor, then compare. Triggers: "competitor analysis", "competitor research on", "what is [competitor] doing", "compare us to", "competitive landscape", "battlecard prep". Run after /company-context and /icp-research. Not for researching your own company (use /company-context).

日本語の概要は準備中です。原文の説明を表示しています。

matteotitta/repo-structure-in-house632026年10月14日 更新

Draws out a founder's or expert's point of view: what they believe about their market that others don't, the hot takes they'd defend, the stories behind them, and their taste. Generates interview questions, works from answers, a live call or existing content, and ends with ranked One Big Idea candidates for thought leadership and positioning. Triggers: "expert POV", "founder POV", "one big idea", "OBI", "contrarian beliefs", "what makes our founder different", "thought leadership foundation", "founder interview questions". Feeds /positioning and /tov-guidelines. Not for writing posts or articles, and not for brand voice rules (use /tov-guidelines).

日本語の概要は準備中です。原文の説明を表示しています。

matteotitta/repo-structure-in-house632026年10月14日 更新

Works out a company's go-to-market motion (product-led, sales-led or hybrid) from its website and pricing, then maps the funnel stage by stage: a definition, strategy, leading inputs the team controls, lagging outputs with targets, cadence and owner for each stage, MQL, SQL and PQL criteria, post-sale stages, closed-lost re-entry paths and backward funnel maths from a revenue target. Triggers: "funnel strategy", "funnel stages", "pipeline stages", "PLG vs SLG", "lead qualification criteria", "map our sales process", "how do leads flow". Feeds /goals. Not for setting the target itself (use /goals).

日本語の概要は準備中です。原文の説明を表示しています。

matteotitta/repo-structure-in-house632026年10月14日 更新

Builds an ideal customer profile from evidence: case studies, testimonials, customer logos, solutions pages, reviews and any sales notes you have. Produces market sizing layers, firmographic segments, a champion and an economic buyer persona, a negative ICP, intent signals, customer proof points and a voice-of-customer section in the buyers' own words, every claim sourced. Triggers: "ICP research", "ideal customer profile", "who are our customers", "customer segments", "buyer personas", "who should we target". Run after /company-context. Not for competitor analysis (use /competitor-research) or call transcript patterns (use /win-loss).

日本語の概要は準備中です。原文の説明を表示しています。

matteotitta/repo-structure-in-house632026年10月14日 更新

matteotitta のスキルをすべて見る

このスキルの問題を報告する