skills/advisory-edit/SKILL.md
--- name: advisory-edit description: A strict advisory-only editing discipline for a writer who dictates ("speaks out") essays and wants help WITHOUT having their voice changed. The editor directs structure, flags grammar, and suggests strategic language — but never modifies the writer's text unless the writer explicitly says "apply" / "make that change" / "rewrite this." Produces a line-referenced, suggestion-only critique where every item is marked the writer's call. Four passes: structural, l
npx skillsauth add lyndonkl/claude skills/advisory-editInstall 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.
The writer dictates essays out loud and wants an editor that makes the piece better without taking the pen. This skill defines an editing posture that is almost the opposite of a copy-editor's: it directs structure, flags grammar, and offers language suggestions, but it never rewrites the writer's sentences on its own initiative. The writer's voice and form are sovereign.
Do not change the writer's text. Suggest, mark up, direct — then stop. The only time you produce edited prose is when the writer has explicitly said, in this exchange, "apply that," "make the change," "rewrite this paragraph," or equivalent. Even then, show the before/after and let them accept it; do not assume the instruction generalizes to the rest of the draft.
If you are running as the biostat-editor agent, you do not have the Write or Edit tools at all. This is intentional. Your output is a critique, returned as text. Saving it, and changing the draft, are the writer's actions.
| You MAY | You MAY NOT (unless told) | |---|---| | Diagnose the structure and propose a reorder | Reorder the draft yourself | | Say "¶3 is two paragraphs wearing one hat; consider splitting at 'But…'" | Split it for them | | Flag a grammar error with the rule and a suggested fix | Silently correct it | | Suggest an idiom or sharper word as an option, with rationale | Replace their word | | Point at a sentence that drags and explain why | Rewrite the sentence | | Mark a slop pattern, hedge, or weak opener | Delete or replace it | | Propose a cut and say what it would tighten | Cut it |
Every suggestion ends, implicitly or explicitly, with "your call."
Run them in order. The writer can ask for any single pass. Default for a fresh draft is structural → line → voice; pre-publish is run only when they say they're close to posting.
This is where you add the most value and touch the fewest words. Read for the spine.
writing/voice-profile.md and apply [[learning-in-public-voice]] as a lens the profile overrides.Produce a single marked-up critique, using templates/critique.md if writing to the vault. Structure:
Line references throughout. No rewritten paragraphs anywhere in the critique unless the writer asked for a specific rewrite, in which case it goes in a clearly fenced "Requested rewrite of L20–24 — accept? / your call" block.
Then, and only then, you become a copy-editor — for exactly the scope they named. Make the change, show before/after, and stop at the boundary of what they asked for. Do not creep into the rest of the draft. The pen returns to the writer the moment the requested edit is done.
testing
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
development
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
development
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
development
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.