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 agentmods add skills/veigap/talksmith/pptx-diffnpx skills add veigap/talksmith --skill pptx-diffgit clone --depth 1 https://github.com/veigap/talksmithWhat 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 | $0.00093 | $0.01436 |
| Opus 5 | $0.00046 | $0.00718 |
| Sonnet 5 | $0.00019 | $0.00287 |
| Haiku 4.5 | $0.00009 | $0.00144 |
Grade A, and why
talksmith:pptx-diff 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 2d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
talksmith:pptx-diff — Explain what changed in the deck
The middle stage of the reverse pipeline. Given the original deliverable final.md and the finalpptx.md reconstructed from the edited deck by talksmith:pptx-extract, this skill produces a precise, reviewable list of every text and image change so the presenter can decide what to reincorporate.
| The caller does | This skill does |
|---|---|
Provides final.md + finalpptx.md (+ optional inventory) |
Aligns slides, computes text/image deltas, writes the report + diff JSON |
| Reads the report and decides which changes to accept | Never edits any file; classification of accept/reject is the merge step's job |
When to use
Run after talksmith:pptx-extract has produced finalpptx.md, and before talksmith:pptx-merge. Also useful standalone to answer "what did the presenter change in the deck?"
Inputs
| Input | Required? | Notes |
|---|---|---|
--final |
yes | The Talk's original final.md (pre-edit deliverable). |
--pptx |
yes | The reconstructed reconcile/finalpptx.md. |
--talk |
optional | Talk root (default: parent dir of --final). Image refs on both sides resolve against this — needed because finalpptx.md lives under reconcile/ while its refs are Talk-root-relative. |
--inventory |
optional | reconcile/finalpptx.inventory.json — enriches image classification. |
--human / --json |
optional | Report format on stdout. The reconcile/finalpptx.diff.json sidecar is always written. |
Subcommand
python3 ${CLAUDE_PLUGIN_ROOT}/skills/pptx-diff/align_md.py \
--final talks/<Talk>/final.md --pptx talks/<Talk>/reconcile/finalpptx.md \
--talk talks/<Talk> [--inventory talks/<Talk>/reconcile/finalpptx.inventory.json] --human
Alignment
Slides align by (section_key, slide_num) primary, with a normalized-title SequenceMatcher ≥ 0.6 fallback (handles renumbering and lightly-edited titles), greedy best-ratio within the match set. Matches with ratio 0.6–0.75 are tagged ⚠ low-confidence so the Editor double-checks before accepting.
What ships with it
1 file 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.
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.
- 2d ago First seen · 75 lines · 93 tokens per session scan A f322693a7c42
talksmith:pptx-diff is a skill published in the GitHub repository veigap/talksmith (10 stars, last pushed 4d ago), licensed MIT. It adds 93 tokens to every session and 1,436 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…