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 mahdisanagostar/chef --skill talkcraftgit clone --depth 1 https://github.com/mahdisanagostar/chefWrote 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/mahdisanagostar/chef/talkcraft)<a href="https://agentmods.dev/skills/mahdisanagostar/chef/talkcraft"><img src="https://agentmods.dev/badge/skills/mahdisanagostar/chef/talkcraft/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/mahdisanagostar/chef/talkcraft"><img src="https://agentmods.dev/badge/skills/mahdisanagostar/chef/talkcraft.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 | $0.00054 | $0.01440 |
| Opus 5 | $0.00027 | $0.00720 |
| Sonnet 5 | $0.00011 | $0.00288 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
talkcraft 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TalkCraft
Overview
Use this skill when the user needs a presentation strategy before slides, a stronger talk structure, a ruthless outline review, speaker notes, rehearsal support, or a deck rewrite grounded in presentation craft rather than generic slide advice.
This skill distills Winston-style presentation principles into an agent workflow that works across Codex, Claude, and other instruction-following agents. It produces strategy first, artifacts second.
Use When
Trigger this skill for requests such as:
- "Help me prepare a keynote."
- "Rewrite this deck for an executive audience."
- "Audit my thesis defense."
- "Turn rough notes into a talk outline."
- "Prepare speaker notes and Q&A."
- "Make this technical presentation clearer."
Do not use this skill for purely visual slide polishing with no narrative problem. In that case, use a design or slides skill after the storyline is stable.
Operating Modes
Choose one mode early and say which one you are using:
DesignBuild a talk from scratch from topic, audience, and time.AuditCritique an existing outline, deck, or speaker script against the rubric.RewriteKeep the core content, replace the structure and delivery plan.RehearseBuild trim plans, speaker notes, likely questions, and recovery moves.
Core Outputs
Every serious run should leave behind most of these artifacts:
- Audience and objective statement.
- One-sentence promise.
- One-line slogan or governing idea.
- Time budget.
- Section fences with explicit transitions.
- Evidence plan: example, story, demo, board work, or visual for each fence.
- Opening move.
- Closing recap.
- Q&A prep.
- Rehearsal risks and next iteration.
Workflow
1. Frame Mission
Extract or infer:
- audience
- audience prior knowledge
- decision or learning goal
- allowed duration
- delivery mode: talk, lecture, pitch, review, defense, briefing
- artifact needed: outline, notes, slide plan, full deck copy, rehearsal memo
What ships with it
10 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.
- agents/openai.yaml 288 B
- assets/presentation-brief-template.md 772 B
- assets/rehearsal-checklist.md 526 B
- assets/slide-plan-template.md 406 B
- references/agent-compatibility.md 1.2 KB
- references/framework.md 3.1 KB
- references/rubric.md 1.0 KB
- scripts/audit_outline.py 11 KB runs code
- scripts/quick_validate.py 3.3 KB runs code
- scripts/sync_mirror.py 3.8 KB runs code
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 First seen · 217 lines · 54 tokens per session scan A ecfd758c37ac
talkcraft is a skill published in the GitHub repository mahdisanagostar/chef (2 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 1,440 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
results-report
A workflow for turning completed experiment analyses into a structured research report with findings, limitations, failures, and next steps.
digest
Turn a day of captured Claude Code sessions into a readable Obsidian daily note in the user's notes repo. Use when the user asks to digest a day, build the daily note, or catch up the daily memory. Also run unattended by the nightly digest routine.
synth
Turn a week of Pulse daily notes into one readable weekly note in the user's notes repo. Use when the user asks to synthesize the week, build the weekly recap, or run the weekly synth. Also run unattended by the weekly synth routine.
session-manager
A fallback skill for recording development sessions and restoring project context from an Obsidian vault, a folder of linked notes. It handles explicit resume, handoff, status, and end-of-session requests when automatic capture is unavailable.
dev-research
A research workflow that uses NotebookLM, a tool for asking questions about a selected collection of documents, to answer development questions with citations.
budget-continue
Show 4-option continuation prompt when session budget is low. Options: remind later (CronCreate), auto-continue locally (Desktop task), auto-continue in cloud (Cloud task), continue now. Trigger when: budget warning fires, session limit reached, context is full, user sees budget warning.