claim-matrix-rewriter
Rewrite `outline/claim_evidence_matrix.md` as a projection/index of evidence packs (NO PROSE), so claims/axes are driven by `outline/evidence_drafts.jsonl`…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-23 00:13
13,987 results
Rewrite `outline/claim_evidence_matrix.md` as a projection/index of evidence packs (NO PROSE), so claims/axes are driven by `outline/evidence_drafts.jsonl`…
Use when a review workspace has manuscript text and needs a traceable claim ledger.
Write the survey's front matter files (Abstract, Introduction, Related Work, Discussion, Conclusion) in paper voice, with high citation density and a single…
Audit/regression checks for the evidence-first survey pipeline: citation health, per-section coverage, placeholder leakage, and template repetition.
Use when an approved `evidence-review` protocol needs to be applied to a candidate pool.
Use when a `research-brief` workspace has a small paper set plus outline and needs a compact reader-facing briefing instead of a full survey.
Evaluate fiction against a distilled novel style profile and identify style drift, AI-like prose, and concrete revision targets. Use when the user asks to…
Remove traces of AI generation in Chinese text. Designed for the unique problems of Chinese AI writing: era-setting openings, overuse of connectives, internet slang, translationese, overly formal written language, formulaic structure, clichéd endings. Make the text more natural, more human, and more like something written by a Taiwanese person.
Use this skill when the user wants to review a piece of existing text / document together with the agent: examine logical coherence, structural organization, redundancy and padding, AI tone, style and voice, and (when reference input is provided) cross-document SSOT consistency; multi-model cross-review is also possible. Trigger: "review this document / take a look at it / see if it makes sense / are there any logic problems / is there any repetition /…
Write advisor, mentor, lab-meeting, or collaborator updates. Use for weekly updates, progress memos, decision requests, blocker summaries, and next actions.
Finalize accepted ML/AI papers for camera-ready submission. Use for de-anonymization, rebuttal promises, supplement updates, final LaTeX checks, and release…
Use when making text sound human, removing AI tells, or fixing writing that sounds like ChatGPT. Detects and rewrites AI patterns: overused phrases (testament…
Use when turning a folder of research PDFs into Obsidian notes, even if Obsidian is not named. Writes one templated literature note per paper and extracts…
Generate structured technical documentation artifacts including ADRs, PRDs, and feature specs for a hackathon project.
Render mathematical formulas in Obsidian using LaTeX/MathJax syntax. Use when writing equations, matrices, integrals, summations, or any mathematical notation…
Review offer letters and non-compete/confidentiality clauses—including jurisdiction checks. Substantive rules (non-compete enforceability, working hours system classification, personal information protection) are researched and extracted at each hiring event, not pre-stored. Use when the user says "review this offer letter", "can a non-compete be used here", "check this offer letter", "hiring in [some place]", or attaches an offer letter.
Build or update a long-term bar exam prep (or final exam prep) study plan — phased, weighted by weak subjects, with daily practice scheduling, adaptively adjusted based on practice history in study-plan.yaml. Use when the user says "make a study plan", "plan my bar exam prep", "schedule my review", "how should I review [X]".
Use when writing or modifying Nextflow (.nf) scripts on Nextflow 25.10+ / 26.04+, especially when output may default to legacy untyped DSL2 patterns (tuple…
Write, audit, or improve user-facing product copy across UI and CLI surfaces, including buttons, labels, forms, errors, empty states, tooltips, dialogs,…
Create maintainable Mermaid diagrams for software documentation, including flowcharts, sequence, class, ER, C4, architecture, state, git, gantt, chart, kanban,…
Creates high-quality technical documentation including API documentation, user guides, tutorials, architecture documents, README files, release notes, and…
Turn any codebase into evidence-grounded Markdown docs plus a machine-readable index.json. Every claim cites its source; never invents deployment steps.
The official Digital Speed brand persona, voice, and values. Use when asked to write any content, copy, or communication on behalf of Digital Speed.
Transform AI-sounding writing into natural, human prose. Use when creating or editing any written content—articles, essays, reports, emails, social posts,…