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 sruthir28/enterprise-ai-skills --skill synthesisgit clone --depth 1 https://github.com/sruthir28/enterprise-ai-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/sruthir28/enterprise-ai-skills/synthesis)<a href="https://agentmods.dev/skills/sruthir28/enterprise-ai-skills/synthesis"><img src="https://agentmods.dev/badge/skills/sruthir28/enterprise-ai-skills/synthesis/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/sruthir28/enterprise-ai-skills/synthesis"><img src="https://agentmods.dev/badge/skills/sruthir28/enterprise-ai-skills/synthesis.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 | $0.00081 | $0.01993 |
| Opus 5 | $0.00041 | $0.00996 |
| Sonnet 5 | $0.00016 | $0.00399 |
| Haiku 4.5 | $0.00008 | $0.00199 |
Grade A, and why
synthesis 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 12d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis
Most people summarize when they should synthesize. Summary compresses what was said. Synthesis names the pattern and forces the implication. This skill does the second thing.
The test: did the output change how the reader will act? If no, you wrote a summary. Rewrite.
Design choices (why this skill is opinionated)
- 3 insights, never more. If you have 5, you haven't synthesized yet — you have themes. Force-rank to 3.
- Headlines are claims, not topics. "Customers will pay 20% more for self-serve onboarding" beats "Customers care about onboarding."
- Every insight ends with a so-what. A claim without an implication is trivia. The so-what tells the reader what to do differently.
- Evidence is specific. Direct quotes, exact numbers, named sources. No "many customers said" — that's compressed mush.
- Synthesis is reductive. You will throw away 80% of the raw input. That's the job. If you keep all of it, you summarized.
Inputs the skill needs (interview if missing)
- The raw inputs. Interview notes, transcripts, survey data, research, meeting recordings. Paste or link.
- Who's the reader? Exec, peer, team. Changes the so-what.
- What decision is downstream? "Should we build X?" "Cut Y?" "Reorg Z?" The synthesis should serve a specific call.
- What did you go in believing? Your prior hypothesis. (Helps catch confirmation bias and surface true surprises.)
If the decision is unknown, ask before synthesizing. Synthesis without a decision becomes a summary.
The process
1. Cluster (induction, not deduction)
Read everything. Tag each data point with the theme it belongs to. Don't start with themes and force-fit — let themes emerge from the data. You're looking for repeated patterns, not single anecdotes.
2. Force-rank to 3
You'll have 5–10 emerging themes. Cut to 3. Use this rank:
- Frequency (how often did it come up?)
- Severity (how big a deal is it for the decision?)
- Surprise (did it contradict what you went in believing?)
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.
- 12d ago First seen · 167 lines · 81 tokens per session scan A b53d07124199
synthesis is a skill published in the GitHub repository sruthir28/enterprise-ai-skills (139 stars, last pushed 10d ago), licensed MIT. It adds 81 tokens to every session and 1,993 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
lyrik
Security assessment of a codebase — minimal mode for runner validation.
librarian
Read-only retrieval over the daily-digest kept set. Slash-invoke with /librarian ; returns items verbatim with citations.
notes
Create and manage text notes in the workspace.
tdx-assets
Look up staff devices, assets, and locations in TeamDynamix (TDX). Given a list of names, emails, or partial identifiers, resolve each person and return the assets assigned to them with location, model, ownership type, and status. Read-only.
aggregator
Daily fetch from a fixed public allowlist; score against the user's interests file; cluster into themes; push the digest to the configured channel.
file-search
Find files and search content across directories.