Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Acprk Technique Overview

ASecurity

Use when writing the Technique Overview (a.k.a. "Our Techniques") subsection. Recalls prior routes per paper at a mathematical level, reduces the gap to numbered questions, and answers each with a declarative "Insight" plus one figure, so a reviewer can restate the core idea without reading the body.

78 stars
0 votes
0 copies
0 views
Added 9/26/2026
researchgo

Security Analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned 9/26/2026

$npx -y skills add jiayaoqijia/cryptoskill --skill acprk-technique-overview --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Acprk Technique Overview?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Acprk Technique Overview
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jiayaoqijia-acprk-technique-overview/badge)](https://www.skillsdirectory.com/skills/jiayaoqijia-acprk-technique-overview)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: technique-overview
description: Use when writing the Technique Overview (a.k.a. "Our Techniques") subsection. Recalls prior routes per paper at a mathematical level, reduces the gap to numbered questions, and answers each with a declarative "Insight" plus one figure, so a reviewer can restate the core idea without reading the body.
---

# Technique overview

## Goal test

After reading only the abstract, introduction and overview, a reviewer can:
(a) restate the main idea in two sentences, (b) write down the key formula,
(c) say where each prior work sits relative to it, (d) believe the main theorem is
plausibly true. Ask `reviewer-sim` (generalist persona) to perform exactly this test.

## Procedure

1. **List the prior routes** from `LITERATURE.md` (usually 2, sometimes 3). For each
   paper in each route write: its key identity/formula, its cost, and the one
   factual thing it leaves open. Verify each against the original paper.
2. **Find the common object.** Phrase all routes as acting on the same mathematical
   object or optimising the same objective (Eq. (1) of the introduction). If no common
   object exists, the "unification" story is forced; tell the human author and
   consider a different framing (e.g. "two orthogonal improvements that compose",
   supported by a measured composition).
3. **Reduce to questions.** "Whether the routes compose reduces to two questions:
   (i) ... (ii) ...". Questions must be precise enough that a theorem answers them.
4. **One Insight per question.** Heading = declarative sentence stating the answer.
   Body: observation → reformulation → key formula (copied from the body theorem) →
   conclusion → why the boundary case is tight or where it fails.
5. **Figure.** A grid/axis diagram (prior works as corners/points, ours as the new
   region) or a data-flow diagram of the new algorithm. Ask `figure-artist` for it;
   caption = one sentence stating placement.
6. **Composition paragraph** with the combined identity and cost.
7. **Optional scope extender.** One paragraph showing the technique applies to a
   neighbouring scheme, quantified by formula only (cheap, raises significance). Mark
   it clearly as not implemented if so.
8. **Consistency check**: `grep` each displayed formula in the body; string-compare.

## Style rules

- Describe prior work per paper and mathematically; do not write a tutorial with
  "Why X is needed / Where the cost goes" headings.
- Use "Suppose ..." to introduce hypotheses before derivations.
- For density/asymptotic results: "asymptotic density ..., certified per instance".
- No new claims that the body does not prove; no numbers that the experiments section
  does not contain.
- Keep limitations as short remarks at the end of the relevant insight, not in the
  contribution list.

## Output

`paper/sections/overview.tex` (or inside `intro.tex`), figure request in
`paper/figs/REQUESTS.md`.

Examples: `skills/paper-playbook/sections/05_technique_overview.md`,
`skills/paper-playbook/examples/toy_overview_and_related.md`.

Attribution

jiayaoqijiajiayaoqijia
View sourceSee grades on GitHubMore from jiayaoqijia →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Competitor Analysis

This skill provides comprehensive analysis of competitor SEO and GEO strategies, revealing what's working in your market and identifying opportunities to outperform the competition.

1823 votes

Deep Research

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report co...

502942 votes

Paperclip Distill

Use when an operation issue is a Paperclip cursor-window, distill, or backfill — `operationType: "distill"` or `"backfill"` and the body references a Paperclip source bundle for a project or root issue. Turn raw Paperclip activity into a wiki-insightful project page, decisions log, and history note. This skill exists specifically to replace the stiff, datestamp-heavy templated output that the deterministic distiller produces.

953191 votes

Academic Pipeline

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory, coverage-bounded integrity checks, two-stage peer review, and auditable quality-assurance artifacts. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end p...

502941 votes

Literature Review

Assistance with writing literature reviews by searching for academic sources via Semantic Scholar, OpenAlex, Crossref and PubMed APIs. Use when the user needs to find papers on a topic, get details for specific DOIs, or draft sections of a literature review with proper citations.

6511 votes
View all in research →