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 Haohaha-11/Paper-Writing --skill results-writergit clone --depth 1 https://github.com/Haohaha-11/Paper-WritingWrote 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/haohaha-11/paper-writing/results-writer)<a href="https://agentmods.dev/skills/haohaha-11/paper-writing/results-writer"><img src="https://agentmods.dev/badge/skills/haohaha-11/paper-writing/results-writer/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/haohaha-11/paper-writing/results-writer"><img src="https://agentmods.dev/badge/skills/haohaha-11/paper-writing/results-writer.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 | $0.00000 | $0.00588 |
| Opus 5 | $0.00000 | $0.00294 |
| Sonnet 5 | $0.00000 | $0.00118 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
results-writer 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.
This is a copy
86% identical to track-trends — 209 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Results Writer
Purpose
Turn verified experimental outputs into a precise Results narrative. This skill helps authors state what the results show, what they do not show, and how figures/tables support the paper's claims.
When To Use
- Writing result paragraphs from tables and figures.
- Revising overclaimed result text.
- Aligning Results with Abstract and Introduction claims.
- Preparing figure/table callouts.
Inputs
Required:
- tables and figures;
- metric definitions;
- baseline names;
- key numerical findings;
- claim-evidence matrix.
Optional:
- statistical tests;
- seed variance;
- qualitative examples;
- failure cases.
Procedure
- Identify the claim each table/figure supports.
- State the comparison before interpreting the number.
- Report exact metrics and conditions when central.
- Distinguish main results, ablations, qualitative results, and failure cases.
- Avoid causal explanations unless the experiment isolates the cause.
- Add caveats for small datasets, high variance, or missing baselines.
- Ensure result statements match Abstract/Introduction wording.
Rubric
| Dimension | Strong | Weak |
|---|---|---|
| Specificity | Names metric, baseline, setting | Says "better" |
| Claim alignment | Supports stated contribution | New claims appear only in Results |
| Interpretation | Explains what result means | Repeats table values |
| Scope | Notes limitations | Generalizes beyond setup |
| Visual linkage | Figures are referenced meaningfully | Figures are decorative |
Venue Adaptation
- ICLR/NeurIPS/ICML: connect results to hypotheses, ablations, and robustness.
- CVPR/ECCV: balance quantitative results with qualitative examples and failure cases.
- AAAI: keep result interpretation accessible to broad AI reviewers.
- TMI: avoid clinical utility claims unless validation supports them; report cohort/protocol limits.
- arXiv: include complete result context and artifact availability.
Output Contract
Return:
Result narrative:
Table/figure claim map:
Overclaimed statements:
Missing caveats:
Suggested paragraphs or patch plan:
Residual risks:
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 · 97 lines · 0 tokens per session scan A 23ab9bc07da4
results-writer is a skill published in the GitHub repository Haohaha-11/Paper-Writing (3 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 588 tokens. A static security scan graded it A with 0 findings. It is 86% identical to track-trends, differing in 209 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…