skills/writing-well/SKILL.md
Audit and improve user-provided writing for clarity, concision, and impact. Use when the user asks to audit, review, improve, edit, or rewrite text. Apply seven checks (sentence length, clutter, unsupported modifiers, weasel words, jargon/acronyms, "so what", and flow), then return severity-ranked findings and a full rewrite suggestion.
npx skillsauth add ferminrp/agent-skills writing-wellInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill when:
writing-well or writing audit).Run all 7 checks in order. For each finding:
Flag sentences longer than 30 words.
Action: Split or tighten so each sentence carries one idea.
Replace wordy phrases with simpler forms.
| Cluttered phrase | Replace with | |---|---| | with the possible exception of | except | | due to the fact that | because | | totally lacked the ability to | could not | | until such time as | until | | for the purpose of | for | | in order to | to | | it is important to note that | delete or rephrase | | at the end of the day | delete or rephrase | | in terms of | rephrase | | a large number of | many | | in the event that | if | | at this point in time | now | | has the ability to | can | | on a daily basis | daily | | the vast majority of | most |
Also flag any phrase where one word can do the same job.
Flag subjective modifiers without evidence.
Examples:
Common words to flag: significantly, substantially, greatly, very, extremely, considerably, remarkably, tremendously, much, quite, really, incredibly, fairly, pretty (as adverb), a lot.
Action: Ask for a number; if none is available, remove or soften the claim.
Flag non-committal language: would, might, should, could, arguably, nearly, practically, virtually, somewhat, relatively, potentially.
Action: Replace with a concrete commitment, specific number, or explicit uncertainty ("I don't know yet, and I will follow up").
Action: Define once, then use the short form.
For each paragraph, ask if the reader immediately sees relevance.
Action: Add implication, consequence, or numeric impact.
Check whether the text sounds natural when read aloud.
Flag:
Action: Reorder ideas and vary sentence rhythm to match idea complexity.
Use this structure:
## Writing Audit Report
### Summary
[1-2 sentence assessment of strengths and top improvement area]
### Score: X/10
[Score based on how many checks pass cleanly]
### Findings
#### Critical
[Issues that severely hurt clarity or accuracy]
#### Important
[Issues that materially reduce quality]
#### Minor / Polish
[Flow and wording refinements]
### Rewrite Suggestion
[Full rewrite preserving intent and voice]
When text asks a question, prefer one of these forms:
development
Consulta promociones de viajes desde Argentina usando Anduin Promos API. Usar cuando el usuario pida promos de viaje en Argentina, promociones de vuelos, hoteles o paquetes, mejores ofertas del dia, promos a brasil/usa/europa, ranking por score o ultimas promos de promociones-aereas.
development
Consulta riesgo pais de Argentina con serie historica desde Anduin API. Usar cuando el usuario pida "riesgo pais argentina", "ultimo riesgo pais", "serie historica de riesgo pais", "riesgo pais por fecha o periodo", o "evolucion del riesgo pais".
development
Technical guide to integrate mapcn in React + shadcn projects. Use when the user asks to integrate mapcn, add mapcn to a shadcn app, use mapcn MapControls/Markers/Routes/Clusters, implement controlled viewport state, use the useMap hook, or access MapLibre through mapcn.
development
Consulta IPC de Argentina con la serie de inflacion mensual desde Anduin API. Usar cuando el usuario pida "inflacion argentina", "ipc argentina", "inflacion mensual", "ultimo dato de inflacion", "serie historica de inflacion", "inflacion por fecha", "inflacion por periodo" o "variacion mensual ipc".