Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add fzfclee/consulting-skills --skill affinity-diagramgit clone --depth 1 https://github.com/fzfclee/consulting-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fzfclee/consulting-skills/affinity-diagram)<a href="https://agentmods.dev/skills/fzfclee/consulting-skills/affinity-diagram"><img src="https://agentmods.dev/badge/skills/fzfclee/consulting-skills/affinity-diagram/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fzfclee/consulting-skills/affinity-diagram"><img src="https://agentmods.dev/badge/skills/fzfclee/consulting-skills/affinity-diagram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.00880 |
| Opus 5 | $0.00030 | $0.00440 |
| Sonnet 5 | $0.00012 | $0.00176 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
affinity-diagram scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Affinity Diagram
Use this skill to turn scattered qualitative inputs into clear, evidence-backed theme clusters.
Method Notes
- Affinity diagramming groups raw observations by natural relationship, not by a pre-decided framework.
- It is strongest when the input contains many notes, quotes, feedback items, ideas, symptoms, or concerns.
- The method should preserve traceability from each cluster back to the raw input.
- The output should help the next step: problem framing, prioritization, journey mapping, root-cause diagnosis, or solution design.
Required Inputs
Collect or infer these inputs before execution:
- raw items to cluster
- source or context of each item when available
- purpose of the clustering
- audience or decision context
- any known constraints, such as time, segment, process stage, or stakeholder group
If an input is missing, do not block automatically. Mark it as missing, state the assumption used, and add a validation action.
When Not To Use
Do not use when the categories are already fixed by a required taxonomy, compliance rule, financial chart of accounts, or formal decision criteria. Use mece-framework, decision-matrix, or weighted-scorecard instead.
Step-by-Step Execution
| Step | Required input | How to execute | Output |
|---|---|---|---|
| Define the synthesis question | Purpose, decision context, audience. | State what the clustering needs to clarify. Keep it broad enough for themes to emerge. | Synthesis question. |
| Normalize raw items | Notes, quotes, observations, ideas, risks, requirements. | Split compound items, remove duplicates only when meaning is truly identical, and keep source labels when possible. | Clean item list. |
| Cluster by natural similarity | Clean item list. | Group items that express the same need, friction, cause, behavior, or opportunity. Avoid imposing a favorite framework too early. | Draft clusters. |
| Name each cluster | Draft clusters, representative items. | Give each cluster a plain, specific label that explains the shared meaning. | Cluster names. |
| Test cluster quality | Cluster list, raw items. | Check whether each cluster is internally coherent and distinct from other clusters. Move or split weak clusters. | Refined affinity map. |
| Extract implications | Refined clusters, synthesis question. | Identify what each cluster implies for the decision, diagnosis, or next analysis. | Theme implications. |
| Identify outliers and gaps | Unclustered items, missing sources, thin clusters. | Preserve outliers that may represent weak signals, minority needs, or evidence gaps. | Outlier and gap list. |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 81 lines · 60 tokens per session scan A af3b27c7aafa
affinity-diagram is a skill published in the GitHub repository fzfclee/consulting-skills (4 stars, last pushed 22d ago), licensed Apache-2.0. It adds 60 tokens to every session and 880 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
taxue-solve
A thinking aid that turns a vague problem or difficult choice into a clear plan of action. It first examines what the real problem is, including whether emotions are hiding the main question.
meme-interpreter
An internet-meme and slang interpreter that explains online jokes, expressions, images, group jargon, and references in their real social context.
taxue-calm
A problem-framing guide that turns anxiety, stress, overthinking, low energy, or emotional overwhelm into a specific practical question.
taxue-career-resume
A resume and job-description tool for comparing a person’s experience with a specific job opening. It can create a reusable master resume and tailored versions for individual applications.
taxue-career
A career-planning guide covering the full path from choosing a direction to starting, settling into, changing, or leaving a job.
taxue-industry
A three-level method for understanding an industry: a broad overview, deeper research, and business judgement. It examines the supply chain, competitors, and market structure.