Menu
Scan a blog post for unlinked pop culture refs, proper nouns, named theories, and historical figures. Research and apply hyperlinks automatically.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Filter recent Hacker News for live threads on June's topics and hand him the list. Separately, flag the rare subset where work he has already done settles a specific quoted claim, and draft that comment as a plain argument with no link to his own writing. Use when June asks to check HN or find threads worth reading or commenting on.
Scan blog posts for AI writing tics and missed opportunities for human voice. Reports subtractions (AI patterns to remove) and additions (wordplay, arc, and claims to strengthen).
Poll June's Hacker News feeds, report what is new since the last run, and idempotently arm a background watch for replies to his comments. State persists in ~/Documents/sweep/ so it survives across sessions. Use when June asks what is new on HN, whether anyone replied, or to start watching a thread.
Argument-level compression by a strengthened absence test (does the argument stand with the same force, clarity, evidence, scope, pacing, and misreading-resistance?). Removes passages that fail it (self-referential cruft, cross-section restatement, self-recap, re-derivation, scaffolding, expired reader-orientation, stakes inflation, inert hedges, redundant examples); grafts good rhetoric onto an adjacent essential point rather than deleting. Idempotent. The structural cousin of /tighten (word-level) and /not-but (negation).
Audit a technical candidate's resume/CV by verifying its claims against the public contribution graph instead of taking the text at face value. Sorts every claim onto the self/peer/world attestation lattice, applies a cost-and-stake filter so cheap proxies (stars, downloads, backlinks) don't count, runs LIVE checks (GitHub, arXiv, package registries, CVEs), and reports two separate axes — merit (staked acceptance of the candidate's specific work) and attention (timestamped output) — plus a verifiability score in [0,1]. For technical recruiters and hiring managers. Invoke when given a candidate — a GitHub handle, a resume/CV, an arXiv author, a personal site — and asked to verify, audit, vet, or check their claims. Runs at two depths — a quick triage scan or a deep per-claim audit — and elicits which. Checks the provenance of a personal site or self-hosted resume (Internet Archive + git history) as an un-backdatable anti-tailoring anchor. Needs tool access (Bash/curl or WebFetch).
Find and defuse "not X but Y" / "isn't X; it's Y" / "X — not Y" constructions. Deterministic grep for detection (no LLM blind spot), the not-but subagent for triage. Split-or-cut tail negations ("X, not Y") aggressively — promote the point to its own sentence or delete it; recast in place only mid-clause "not X but Y" that genuinely can't be split; keep just the rare iconic thesis line literal.
| name | flavor |
| description | Scan a blog post for unlinked pop culture refs, proper nouns, named theories, and historical figures. Research and apply hyperlinks automatically. |
| argument-hint | <file_path> |
| allowed-tools | Read, Edit, Grep, Glob, WebSearch, WebFetch, AskUserQuestion |
Scan a blog post for pop culture references, proper nouns, named theories, historical figures, and film/book/music references that lack hyperlinks. Research and apply links that give the reader instant context.
L{line}: {type} — "{quoted text}" → [link] {why this link}Pop culture. Films, TV shows, books, albums, characters. Link to a YouTube trailer, clip, or scene when available. Prefer the most recognizable moment. If no YouTube link exists, use Wikipedia or IMDB.
Historical figures and events. People, battles, legislation, court cases. Link to Wikipedia or the most authoritative short summary.
Economic/scientific theories. Named theorems, models, papers. Link to the original paper (DOI preferred), or Wikipedia if the paper is paywalled.
Proper nouns the reader might not know. Companies, products, organizations, places that aren't household names. Link to the company site or Wikipedia.
For each reference, try link types in this order. Use the first one that exists and fits:
Move down the waterfall when higher options don't exist or feel forced. A Vickrey auction deserves Wikipedia, not a YouTube video. A startup deserves its launch post, not a dry Crunchbase page.
Default to "probably leave it alone." The skill should barely run — a typical pass finds one or two genuinely useful links, not five borderline ones. If the candidate fails any of these:
… leave it unlinked. Per-pass yield should taper toward zero by pass two. If a second pass finds another link to add, that's a sign of drift, not of thoroughness — flavor without damping is a slow walk toward link soup. The "a bit" qualifier on /tighten and the narrow-preserving invariant on /sharpen do the same job in their respective skills; flavor needs the same brake to satisfy the monoidal contract flavor(flavor(x)) == flavor(x).