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 swan-gtm/gtm-skills --skill skillifygit clone --depth 1 https://github.com/swan-gtm/gtm-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/swan-gtm/gtm-skills/skillify)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/skillify"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/skillify/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/swan-gtm/gtm-skills/skillify"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/skillify.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 | $0.00035 | $0.02334 |
| Opus 5.5 | $0.00014 | $0.00934 |
| Sonnet 5.5 | $0.00007 | $0.00467 |
| Haiku 4.5 | $0.00003 | $0.00233 |
Grade A, and why
skillify 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 1mo 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
When this applies
Only skillify work that is repeatable and already proven. The conversation has to have produced a real procedure with a real outcome — not a half-finished attempt, not a one-off task. If the conversation mostly wandered, say so and ask what to capture.
Shapes that skillify well: a qualification rubric just used on an inbound, a research pattern that should run on the rest of the list, a scoring approach, an outreach framework, a triage flow for a signal. Shapes that don't: ad-hoc questions, one-time data pulls, debugging sessions.
Procedure
1. Reconstruct the three load-bearing pieces.
- Trigger — the specific repeatable situation. "When an inbound demo request comes in" beats "the user asked about a lead."
- Outcome — the concrete deliverable. A scored list, a draft sequence, a research brief, a CRM cleanup, a Slack handoff.
- Procedure — the steps the agent actually ran, in order, pulled from the transcript. Do not invent steps the agent did not run. Do not add tools that "might be useful next time."
If any of the three is fuzzy, ask one focused question. Do not guess.
2. Strip the specifics. Generalize the pattern.
The work was done for one company, one contact, one list. The skill has to work for the next one.
- Real company / contact names → "the target company," "the buying-committee persona," "the account on the list."
- Hard-coded filter values, segment definitions, list IDs, stage names → load from org knowledge. "Load the ICP." "Pull funnel stages." "Check org memory."
- Hard-coded copy, weights, thresholds → defer to the customer's voice. "Pull past approved messages and match the style." "Load the sender's voice." Do not paste the exact subject line that worked once.
Exception: if the user explicitly says the skill is locked to one account or campaign (rare — usually a named-account play), keep the specifics and call it out in the description.
3. Capture the judgment, not just the steps.
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.
- 1mo ago First seen · 111 lines · 35 tokens per session scan A fc5f9bc805de
skillify is a skill published in the GitHub repository swan-gtm/gtm-skills (221 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 2,334 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
adoption-leaderboard
Scores a rep's or a team's recent sales calls against a fixed set of five winning-behavior checklists (rapport, upsell signals, renewal risk, customer experience, value realization), then ranks reps lowest-adoption-first so the highest-leverage coaching targets lead. Use when running a team calibration, prepping 1:1…
deep-discovery
Audits an early-stage B2B sales discovery call transcript against a nine-dimension discovery rubric and credits only what the buyer actually said, or sweeps a CRM deal export for missing discovery fields. Use when the user asks to review a discovery call, score discovery quality, coach a rep on discovery, find what…
meddicc
Audits a B2B sales call transcript against the MEDDICC qualification framework (Metrics, Economic buyer, Decision criteria, Decision process, Identify pain, Champion, Competition) and credits only what the buyer said, or sweeps a CRM export for deals missing MEDDICC fields. Use when the user asks to qualify an…
meddpicc
Audits a B2B sales call transcript against the MEDDPICC qualification framework (Metrics, Economic buyer, Decision criteria, Decision process, Paper process, Identify pain, Champion, Competition) and credits only what the buyer said, or sweeps a CRM export for deals missing MEDDPICC fields. Use when the user asks…
sandler
Audits a B2B sales call transcript against the Sandler Selling System submarine (Bonding and Rapport, Up-Front Contract, Pain, Budget, Decision, Fulfillment, Post-Sell), or sweeps a CRM export for deals missing Sandler-relevant fields. Use when the user asks whether a rep pitched before earning the right to, whether a…
bant
Audits a B2B sales call transcript against the BANT qualification framework (Budget, Authority, Need, Timeline) and credits only what the buyer said, or sweeps a CRM export for deals missing BANT fields. Use when the user asks to qualify a lead, run a BANT check, decide whether to advance a deal past a first call, or…