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 TenWalk/ieee-skills --skill ieee-polishinggit clone --depth 1 https://github.com/TenWalk/ieee-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/tenwalk/ieee-skills/ieee-polishing)<a href="https://agentmods.dev/skills/tenwalk/ieee-skills/ieee-polishing"><img src="https://agentmods.dev/badge/skills/tenwalk/ieee-skills/ieee-polishing/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/tenwalk/ieee-skills/ieee-polishing"><img src="https://agentmods.dev/badge/skills/tenwalk/ieee-skills/ieee-polishing.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 | $0.00152 | $0.01073 |
| Opus 5.5 | $0.00061 | $0.00429 |
| Sonnet 5.5 | $0.00030 | $0.00215 |
| Haiku 4.5 | $0.00015 | $0.00107 |
Grade A, and why
ieee-polishing 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IEEE-Style Language Polishing
Use this skill to bring existing sentences to IEEE journal standard. If the text needs its
argument or structure rebuilt, use ieee-writing first, then polish here.
Core stance
- Preserve meaning; never add claims. Polishing changes wording, not facts. Do not introduce numbers, citations, or assertions the author did not make.
- Clarity over elegance. A plain, precise sentence beats an ornate one. IEEE values verifiable clarity, not literary flair.
- US English by default (IEEE house style):
color,analyze,modeling,behavior,optimize,center,fiber. (This is the opposite of Nature's British spelling.) - Calibrate claim strength to evidence (see hedging ladder below).
- Return plain, copy-pasteable text. Do not wrap output in commentary the user must strip out.
When to open extra files
| File | Open when |
|---|---|
| references/sentence-and-style.md | Sentence length, acronyms, articles, voice, numbers/units, US-English list, words to avoid, citation phrasing |
| references/section-moves.md | Choosing tense and hedging for a specific section (Abstract / Intro / Method / Results / Discussion / Conclusion) |
Hedging ladder (match the verb to the evidence)
strong, directly measured show, demonstrate, establish
inferential indicate, suggest, imply
possible / partial may, can, could, appear to, is consistent with
Over-claim is the most common reviewer irritation. If the evidence is one experiment, do not say "prove" or "in all cases". Downgrade the verb instead of adding qualifiers like "very".
Polishing workflow
- Split into sentences. Inspect each individually — the last sentence of a paragraph fails most.
- Identify the section (it sets tense and hedging; see
references/section-moves.md). - Length and one-idea check. Aim for ≤ ~25 words; break any sentence carrying two ideas.
- Tense audit. Results = past + numbers; method-as-procedure = past; the proposed method as a standing object = present; Introduction background = present / present perfect.
- Edit each sentence for subject-action clarity, articles, and US spelling.
- Vocabulary upgrade. Replace vague verbs ("get", "do", "make") with precise ones; remove filler ("it is worth noting that", "as we all know", "obviously").
- Acronym pass. Define each at first use in the body; do not define in the title; avoid undefined acronyms in the abstract.
- Citation phrasing. Numbered
[n]; for author-prominent sentences useSmith et al. [12], otherwise... has been studied [12]. Do not use[12]as a noun ("in [12], the authors..."). - Overclaim sweep. Flag absolutes, unwarranted causation, scope creep, and unverified "first".
- US-English + house style (units, numbers, hyphenation).
- Proofread for articles, plurals, agreement — the classic non-native slips.
- Return plain text plus a short change log of the substantive edits.
What ships with it
3 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.
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 · 76 lines · 152 tokens per session scan A 77a6e185be17
ieee-polishing is a skill published in the GitHub repository TenWalk/ieee-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 152 tokens to every session and 1,073 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
awesome-ieee-report
Generates IEEE-format LaTeX technical reports from project requirements and codebase evidence, using academic prose, pseudocode-only explanations, BibTeX references, and IEEEtran formatting.
literature-searcher
Search CrossRef, OpenAlex, PubMed, Semantic Scholar, and optional Scopus; deduplicate results, download open-access PDFs by DOI, classify papers, monitor new results, and analyze coverage. Use when asked to search literature, monitor a topic, download an open-access paper, classify papers, or analyze literature gaps.
ieee-acm-paper-writing
Draft, rewrite, compress, structure, calibrate, humanize, or audit engineering manuscripts for IEEE and ACM Transactions, journals, and conferences, with optional self-contained HTML audit maps. Use for abstracts, introductions, related work, system models, mathematical formulations, algorithms, experimental methods…
running-cluster-experiments
Use when planning, budgeting, submitting or resuming a multi-job experiment campaign on a Slurm/HPC cluster — sizing walltime, shaping jobs and arrays, deciding what to submit first, or after a job hit its walltime, produced no results, silently ran the wrong configuration, or got the wrong number of GPUs.
kelly-dog-walk
A dog-walking agent workflow that chooses a daily walking time from a rulebook and checks the decision against real weather data. Changes to the rulebook are submitted for a person to approve rather than applied directly.
explaining-derivations
Use when a proof or derivation needs to be made explicit step by step — expanding a paper's algebra for a reader without formal mathematical training, producing a worked companion document, or establishing whether a derivation can be justified at all. Triggers on "explain this derivation", "walk me through this…