Borrowing it
Nothing to install: this file belongs to tbhb/vale-ai-tells. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tbhb/vale-ai-tells/main/.claude/skills/write-pr-description/SKILL.mdgit clone --depth 1 https://github.com/tbhb/vale-ai-tellsWrote 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/tbhb/vale-ai-tells/write-pr-description)<a href="https://agentmods.dev/skills/tbhb/vale-ai-tells/write-pr-description"><img src="https://agentmods.dev/badge/skills/tbhb/vale-ai-tells/write-pr-description/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/tbhb/vale-ai-tells/write-pr-description"><img src="https://agentmods.dev/badge/skills/tbhb/vale-ai-tells/write-pr-description.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00098 | $0.01269 |
| Opus 5 | $0.00049 | $0.00634 |
| Sonnet 5 | $0.00020 | $0.00254 |
| Haiku 4.5 | $0.00010 | $0.00127 |
Grade A, and why
write-pr-description 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write a pull request description
Write PR_AGENTDESC.md at the repository root, then return. You run forked, so the branch diff sits in your context rather than the caller's. Read the material below and write from it.
Arguments
$ARGUMENTS carries the repository root, and after it whatever the caller wants addressed. A first draft arrives with nothing extra. A revision includes the findings review-pr-description returned, or a note that remediation added commits the description hasn't caught up with.
Treat any findings in the arguments as the work. Resolve each one and say so.
Context
!bash ${CLAUDE_SKILL_DIR}/scripts/context.sh
The shape
Write the file in exactly this order.
---
base: <branch this merges into>
draft: <true or false>
labels: [<one or more from the set above>]
reviewers: []
assignees: []
milestone:
---
# <type>(<scope>)?: <description>
## <first template section>
<prose>
Those frontmatter keys and no others. Labels take a flow sequence and an empty one fails the validator, because nobody's filter finds an unlabelled pull request.
The title is a level 1 heading in the Conventional Commits shape. A squash merge turns it into the commit subject on the default branch, so its type has to be one the landing commits use, and it names what the whole branch does rather than what the last commit did.
Then every section the template declares, in the template's order, filled with prose. Replace each instructional comment rather than leaving it in place.
One question per section
The sections answer different questions, so don't let them repeat each other. Summary says what changes. Why says what problem made it necessary. Verification names the commands you actually ran, in backticks. Risk says what breaks if this is wrong and how to back it out. Related points at issues, or says None.
Avoid:
- Restating the diff. A reviewer reads the diff already.
- Counting. No file, line, test, or commit counts.
- Provenance filler. Nothing about requests, sessions, prompts, models, or tools.
- Claims you haven't checked, including verification nobody ran.
- Selling it. Drop
robust,comprehensive,significantly, and their neighbors. - Paths that don't exist. Every backticked path gets resolved against the tree and the diff.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 113 lines · 98 tokens per session scan A 509d1f9c8928
write-pr-description is a skill published in the GitHub repository tbhb/vale-ai-tells (91 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 1,269 once invoked, about $0.0005 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.
Other skills, from other repositories
anti-slop
Remove AI slop from any voice-bearing prose — original posts, threads, articles, long-form, emails, docs, READMEs, marketing copy, bios, scripts. Use when drafting text meant to sound like a specific person or brand, when rewriting text that reads generic, corporate, or AI-generated, or when asked to humanize…
kill-slop
Audit a file or draft for AI slop and off-voice lines against the author's bound voice, report findings with in-voice swaps, then apply approved fixes. Use when the user says "kill slop", "/kill-slop [file]", "find the slop in this", "audit this for slop", or wants a deck, article, page, or draft cleaned to sound like…
humanizer
Humanize and de-slop AI-sounding prose while preserving meaning, specific detail, and genuine human quirks. When a voice sample or style profile is available, rewrite in that writer's actual voice. Remove recurring AI tells such as inflated significance, stock vocabulary, uniform rhythm, excessive hedging, formulaic…
authenticity-check
Score how authentically text reads as a real human author's work, flag spans that read as AI-generated, AI-templated, or generically derivative, and run a separate read-only scan for suspicious Unicode provenance carriers. Return an authenticity band, a 0-100 score, provenance signals, and span-level reasons. Use when…
ai-slop-detector
Universal prose audit. Scores writing on TWO axes — AI-Slop (does this read like AI wrote it?) and Comprehension (can a fresh reader follow this?). Use PROACTIVELY as a mandatory final QA pass on ANY prose generated for humans to read — every email (internal or external), proposal, report, status update, blog post…
humanizer-czech
Odstraň znaky AI-generovaného psaní z českého textu. Použij při editaci nebo revizi textu, aby zněl přirozeněji a lidštěji. Detekuje a opravuje 27 vzorců včetně: nafouklého významu, propagačního jazyka, anglického slovosledu, kalků, nominalizace, monotónního rytmu, nadužívání spojek, typických českých AI klišé…