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 calionauta/stelow --skill stelow-product-job-to-be-donegit clone --depth 1 https://github.com/calionauta/stelowWrote 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/calionauta/stelow/stelow-product-job-to-be-done)<a href="https://agentmods.dev/skills/calionauta/stelow/stelow-product-job-to-be-done"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-product-job-to-be-done/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/calionauta/stelow/stelow-product-job-to-be-done"><img src="https://agentmods.dev/badge/skills/calionauta/stelow/stelow-product-job-to-be-done.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00129 | $0.04658 |
| Opus 5.5 | $0.00052 | $0.01863 |
| Sonnet 5.5 | $0.00026 | $0.00932 |
| Haiku 4.5 | $0.00013 | $0.00466 |
Grade A, and why
stelow-product-job-to-be-done 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 9d 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 — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jobs To Be Done — Complete Skill
Eleven specialized prompts for a JTBD analysis. Every prompt is a slot that must
be answered, never a slot that must be filled. An answer may be
Not applicable or Open; a fabricated answer may not.
What this skill is not
- Not a research method. It structures what the user brings; it does not generate evidence.
- Not an interview service. Prompt 11 is a switch-interview protocol; other interview styles are out of scope.
- Not a prioritization model. The composite score ranks work; it does not estimate demand.
- Not a publisher. Nothing here writes to an external tool.
Prompt map
| # | Prompt | When to use |
|---|---|---|
| 1 | Contextual Segmentation | Segment a market by situation, not demographics |
| 2 | Thinking Styles (Indi Young) | Distinct ways a performer thinks about a purpose |
| 3 | JTBD Discovery | Reframe a solution, action or outcome into jobs |
| 4 | Competitor Discovery | Direct, indirect and hidden competitors |
| 5 | Job Actors | Every role around the job, including the ones that do not exist |
| 6 | Situational Variables | Factors and variables that change the outcome |
| 7 | Functional Needs | Ensure / Avoid success criteria |
| 8 | Financial Needs | Minimize the cost of criteria for the buyer |
| 9 | Emotional & Social Jobs | How the performer wants to feel and be seen |
| 10 | Job Map Steps | Chronological steps, tagged by phase |
| 11 | Switch Interview | Timeline and the four forces behind one switch |
Routing, intake, depth
Intake, before generating. Two batches, never one wall.
Batch 1 — material. Ask before anything else: do you have interviews, notes, support tickets, messages, recordings or links? Three lanes:
| lane | what it means | what changes |
|---|---|---|
| material | the user supplies transcripts, tickets, docs or recordings | read them first; quotes are Input-derived; findings may be Inference — high confidence |
| research | no material, but the web may supply candidate language, context and alternatives | everything is Research-derived or Hypothesis — bet; the web never establishes that a job exists |
| none | nothing to read | hypothesis mode: the most plausible bet at every slot, each with its check |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/00-evidence-policy.md 5.9 KB
- references/01-contextual-segmentation.md 4.2 KB
- references/02-thinking-styles.md 3.1 KB
- references/03-jtbd-discovery.md 4.0 KB
- references/04-competitors.md 2.6 KB
- references/05-job-actors.md 4.8 KB
- references/06-situational-variables.md 3.1 KB
- references/07-functional-needs.md 4.7 KB
- references/08-financial-needs.md 3.6 KB
- references/09-emotional-social-jobs.md 3.0 KB
- references/10-job-map-steps.md 8.8 KB
- references/11-switch-interview.md 3.8 KB
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.
- 9d ago Changed · +134 lines · -41 tokens per session 0980106e2da0
- 14d ago Changed · +6 lines 9300f2ddac94
- 1mo ago Changed 18257e82bf59
- 1mo ago Changed · +6 lines 0c4c4d4d830f
- 1mo ago Changed · +7 lines d6f58b83a541
- 1mo ago Changed · +82 lines 9ae6fb5ecd64
- 1mo ago Changed · +22 lines e3d728f4f2ae
- 2mo ago First seen · 170 lines · 170 tokens per session scan A ea49589c2c24
stelow-product-job-to-be-done is a skill published in the GitHub repository calionauta/stelow (14 stars, last pushed 9d ago), licensed MIT. It adds 129 tokens to every session and 4,658 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
stelow-product-job-to-be-done compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stelow-product-job-to-be-donecalionauta/stelow | Skill | 14 | 9d ago | MIT | A | 129 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |