irrelevant-detail-killer

irrelevant-detail-killer is a skill for Claude Code from kalyvask/winning-writing. It costs 112 tokens per session (1,720 once invoked), scanned A, original, MIT.

An editing guide that removes vivid story details when they distract from the main point. It focuses on whether each detail supports the argument.

In plain words
What is it for?
It is for revising narrative paragraphs and deciding which sensory details, dates, dialogue, or side observations to keep or cut.
Why use it?
It helps a narrative stay focused when interesting descriptions, scene-setting, or background information make the central message harder to see.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the winning-writing plugin — 32 skills shipped together

Good fit It is for revising narrative paragraphs and deciding which sensory details, dates, dialogue, or side observations to keep or cut.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kalyvask/winning-writing/irrelevant-detail-killer
Install

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.

Any agent
npx skills add kalyvask/winning-writing --skill irrelevant-detail-killer
Clone the repo
git clone --depth 1 https://github.com/kalyvask/winning-writing

Made for: Claude Code.

Or install winning-writing, the plugin that ships this one along with the rest of its 32 skills.

Wrote 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.

agentmods badge for irrelevant-detail-killer

README.md
[![agentmods](https://agentmods.dev/badge/skills/kalyvask/winning-writing/irrelevant-detail-killer/github.svg)](https://agentmods.dev/skills/kalyvask/winning-writing/irrelevant-detail-killer)
Your own site
<a href="https://agentmods.dev/skills/kalyvask/winning-writing/irrelevant-detail-killer"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/irrelevant-detail-killer/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.

agentmods 80×15 button for irrelevant-detail-killer

Your own site · 80×15
<a href="https://agentmods.dev/skills/kalyvask/winning-writing/irrelevant-detail-killer"><img src="https://agentmods.dev/badge/skills/kalyvask/winning-writing/irrelevant-detail-killer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,720 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00112 $0.01720
Opus 5 $0.00056 $0.00860
Sonnet 5 $0.00022 $0.00344
Haiku 4.5 $0.00011 $0.00172

Measured 12d ago against content hash 54e7ef353fd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

irrelevant-detail-killer 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.

side-panel-coach/rules/skills/irrelevant-detail-killer/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Irrelevant detail killer

Source: Glenn Kramon's Winning Writing — the rule named explicitly in class as "essential to great writing." The two-word version: eliminate irrelevant detail.

The problem this skill solves

Strong writers know to be cinematic. They put scenes, sensory details, dates, and dialogue into their prose. The danger is the opposite of generic writing: too much cinematic texture, and the details start to distract from the argument the piece is making.

A draft can have vivid detail and still fail to move the reader, because the reader is being asked to absorb sensory information that doesn't lead anywhere. The mechanics outside the gate, the weather, the sounds of the street, the eccentric neighbor — all might be real, all might be memorable, none might serve the piece.

The two questions to ask of every detail in a narrative paragraph:

  1. Does this detail serve the main point?
  2. If I cut it, what is lost — texture, or the argument?

If the answer to 1 is no and the answer to 2 is texture, cut it. If the answer to 2 is the argument, keep it.

When this differs from sibling skills

  • compression cuts words (adverbs, hedges, throat-clearing). This skill cuts whole details — full sensory descriptions, eccentric characters, atmospheric paragraphs.
  • pick-a-lane cuts whole stories. This skill cuts within a story — removing details that survive after you've picked the right story but don't earn their place.
  • vividness --mode scene-level adds cinematic detail to abstract prose. This skill removes cinematic detail when the prose is already concrete but going off-piste.

In a typical workflow:

  1. Run pick-a-lane to choose the story.
  2. Run vividness --mode scene-level to make the chosen story cinematic.
  3. Run this skill to remove the cinematic detail that the second pass over-supplied.

The pattern that wastes texture

Most over-detailed paragraphs follow this shape:

Opens with a specific scene-setting moment (good).

Then describes the street, the weather, the time of day, the people walking past, the building across the way, the mechanic in his shop, the carpenters hammering, the metal workers striking steel, the sparks flashing (all vivid, none related to the point).

Then returns to the actual subject of the paragraph two sentences later.

Read the full file on GitHub · 116 lines

Changes

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.

  1. 12d ago First seen · 116 lines · 112 tokens per session scan A 54e7ef353fd0

Subscribe to this mod's changes

irrelevant-detail-killer is a skill published in the GitHub repository kalyvask/winning-writing (14 stars, last pushed 6d ago), licensed MIT. It adds 112 tokens to every session and 1,720 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

lab-hardware-cad

Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…

K-Dense-AI/scientific-agent-skills · 106 tokens

opentrons-integration

Author, review, migrate, simulate, and troubleshoot official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots. Use for robot-specific liquid handling, deck and labware setup, pipettes, modules, runtime parameters, liquid classes, and Opentrons App analysis. Use pylabrobot instead when one workflow…

K-Dense-AI/scientific-agent-skills · 79 tokens

pylabrobot

Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Use for PyLabRobot protocols or API questions; keep physical execution behind an explicit operator safety gate.

K-Dense-AI/scientific-agent-skills · 49 tokens

offensive-wifi

Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…

SnailSploit/Claude-Red · 183 tokens

offensive-wifi-recon

Wi-Fi reconnaissance methodology — adapter selection, monitor mode and packet injection setup, regulatory domain handling, multi-band airspace mapping, hidden SSID discovery, BSSID/ESSID/channel/PMF/encryption fingerprinting, client probe analysis, vendor OUI lookup, war-driving with Kismet/airodump-ng/Wigle, and…

SnailSploit/Claude-Red · 130 tokens

offensive-z-wave

Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…

SnailSploit/Claude-Red · 113 tokens