Marketing reframe
Skill xinnnxuan/candidate-gtm-pipeline/skills/marketing-reframe
The method behind my Candidate Go-to-Market pipeline — written judgment, failure log, and evidence ledger of a job search run as a live GTM motion.
npx -y skills add xinnnxuan/candidate-gtm-pipeline --skill marketing-reframeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Turns a true workflow into a buyer-relevant Marketing / GTM capability claim only after the mechanism, next action, evidence level, and ownership boundary are explicit.
SKILL.md
6.1 KB, ~1.2k tokens by cl100k_base, as published. Nobody here has run it
Marketing Reframe
Public edition. Re-authored from a production calibration skill. The production version carries private source routes and course references; this edition keeps the judgment contract: how a real mechanism earns Marketing language without being inflated into commercial ownership.
The judgment, in one screen
What this skill prevents: Marketing-washing — adding words such as segmentation, lifecycle, campaign, or attribution to work whose mechanism cannot support them. The opposite failure matters too: leaving a real Marketing judgment hidden behind internal workflow language and making the hiring manager translate it alone.
The calls it hardcodes:
- Name the buyer and next action first. A capability is useful only relative to someone who needs to make a decision: continue reading, invite an interview, change a priority, trust a handoff.
- Recover the mechanism before naming the capability.
signal -> judgment -> action -> state / handoff -> observed result -> next-cycle change. Missing links stay missing; tool names cannot fill them. - Choose the smallest portable capability. One or two precise reads beat a wall of Marketing vocabulary. The mechanism must still make sense after the fashionable noun is removed.
- Label the evidence level. Direct proof, analogous proof, method inspiration, or forbidden claim. Domain, scale, causality, and ownership never rise through wording.
- Translate intent, not just nouns. A valid reframe changes who the work serves, which decision it improves, or which next action becomes possible.
One system, worked (the public run): screening a large job-market pool under a written rubric directly proves qualification and attention-allocation discipline in the candidate's live system. It is analogous proof for commercial segmentation: the judgment shape transfers, but it does not become campaign-targeting ownership. The worked run applies that same test across stakeholder research, positioning, conversion QA, CRM state, and loss learning.
Everything below is the working contract. The public run fills it against the same Candidate GTM system this repository exhibits.
Purpose
Turn a real project, workflow, or experience into a Marketing / GTM capability read that a hiring manager can understand and the operator can defend in twenty seconds. The output is a calibration brief for a public surface or downstream writer — not final copy and not permission to borrow role nouns.
The skill has two modes:
- Proof reframe: what Marketing / GTM capability does this true mechanism demonstrate?
- System-intent calibration: who does this workflow node serve, which action or state should it improve, and where does its output hand off?
The mechanism test
Before naming any capability, reconstruct:
signal / input
-> judgment
-> action
-> state or handoff
-> observed outcome
-> next-cycle change
If the material proves only tracking, call it tracking. If it proves a defined metric, a review rhythm, and a decision consequence, measurement may be defensible. If it proves a loss hypothesis but not causal credit assignment, call it loss learning — not attribution ownership.
Evidence levels
| Level | What it means | Public-language consequence |
|---|---|---|
| Direct proof | Same judgment shape, work object, and outcome were performed | Role-native language is safe within the proven scale and ownership |
| Analogous proof | The judgment transfers, but domain, scale, or ownership differs | Name the portable capability and the analogy; keep the commercial boundary visible |
| Method inspiration | A framework helped design the approach, but execution proof is absent | Keep it in method or learning language, never as an outcome claim |
| Forbidden claim | The wording would require nonexistent ownership, causality, domain, or scale | Do not publish it; wording cannot repair the gap |
Capability families
Use the minimum family that explains the mechanism:
- market / buyer understanding;
- qualification, segmentation, prioritization;
- positioning, value proposition, message QA;
- channel or touchpoint orchestration;
- lifecycle follow-through;
- CRM state and data trust;
- AI-assisted workflow orchestration with human approval;
- measurement and decision learning.
These are lenses, not a checklist. A project does not become stronger by claiming all eight.
Output contract
Target buyer / next action:
Original intent:
Reframed Marketing intent:
| True mechanism | Capability | Evidence level | Natural proof angle |
|---|---|---|---|
Do not borrow:
Downstream handoff:
The brief must let the next writer preserve the mechanism and boundary without copying this framework's vocabulary verbatim.
Quality gate
- Buyer gain: does the reframe identify who uses the work and what decision or action changes?
- Mechanism gain: did the capability grow from a real judgment chain rather than noun substitution?
- Evidence honesty: are domain, scale, causality, and ownership still where the source left them?
- Human story: can the operator explain the signal, judgment, action, and next-cycle change without hiding behind tool names?
- Node fit: does the workflow node own its direct result — targeting accuracy, message clarity, conversion QA, state integrity, or learning — rather than claiming the whole funnel's outcome?
What this skill never does
- Never turns one contact into a persona or a static list into lifecycle ownership.
- Never calls a loss hypothesis formal attribution.
- Never converts a personal CRM workflow into production administration.
- Never converts AI-assisted research and QA into autonomous operation.
- Never replaces the hiring-market read, candidate truth source, or final surface owner.
Gives 0 of the 12 instructions most product growth skills give in ~1.2k tokens
Counted across 728 of the 1,010 authors here whose files we hold, read 2026-08-06
- read product marketing context before asking questionsin 24 of 728, across 15 files
- define the ideal customer profilein 21 of 728, across 3 files
- document a rollback plan before deploymentin 21 of 728, across 12 files
- analyze the codebase to understand the productin 19 of 728, across 1 file
- ask clarifying questions about the value propositionin 19 of 728, across 1 file
- search for companies matching the criteriain 19 of 728, across 1 file
- look for signals of immediate needin 19 of 728, across 1 file
- assign a fit score from one to tenin 19 of 728, across 1 file
- identify the target decision maker rolein 19 of 728, across 1 file
- suggest a personalized contact strategyin 19 of 728, across 1 file
- provide conversation starters for outreachin 19 of 728, across 1 file
- format results in a scannable markdown templatein 19 of 728, across 1 file
Said here and by no other author read
- recover the underlying mechanism before naming capabilities
- choose the smallest portable capability family
- name the target buyer and next action first
- translate intent rather than just swapping nouns
- use the minimum capability family that explains the mechanism
- preserve domain scale causality and ownership boundaries
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.