search-corpus
$
npx mdskill add lyndonkl/claude/search-corpusSearches past seeds to surface prior thinking on any topic.
- Helps writers avoid repeating ideas they have already explored.
- Depends on the substacker corpus containing seeds, drafts, and published work.
- Ranks matches by signal strength before returning results.
- Delivers a ranked list of seeds with metadata and excerpts.
SKILL.md
.github/skills/search-corpusView on GitHub ↗
---
name: search-corpus
description: Answers "what have I already thought about X?" by searching the substacker corpus (seeds, drafts, published) for seeds matching a topic, keyword, analogy, or author. Returns a ranked list of seeds with id, title, status, density score, and a one-line excerpt. Use when another agent (Intuition Builder, Editor) needs prior thinking before generating new material, or when the writer asks "have I written about X." Trigger keywords: search, find, what have I, already thought, prior work, precedent, have I written about.
---
# Search Corpus
## Table of Contents
- [Workflow](#workflow)
- [Query forms](#query-forms)
- [Output format](#output-format)
- [Worked example](#worked-example)
- [Guardrails](#guardrails)
**Related skills:** Called by `intuition-builder` (before generating framings), `editor` (before reviewing a draft to surface prior thinking), writer directly. Read-only — no writes.
## Workflow
```
Search corpus for query:
- [ ] Step 1: Parse query → topic tag, keyword, analogy term, or author
- [ ] Step 2: Grep corpus/{seeds,drafts,published}/**/*.md
- [ ] Step 3: Rank matches by signal
- [ ] Step 4: Format top 10 as a ranked list with id, status, density, excerpt
```
## Query forms
The skill accepts three query shapes:
1. **Topic tag** (e.g., `dropout`): grep frontmatter `topics:` for the tag; fallback to body keyword.
2. **Freeform keyword** (e.g., `kv cache`): grep body + title for the phrase.
3. **Structured** (e.g., `{topics: [attention-mechanism], status: published}`): direct filter.
## Ranking
Rank by:
1. Exact tag match > freeform body match.
2. Density score descending.
3. Recency (created date descending).
4. Status priority: `published > draft > seed > dead`.
Exclude `corpus/dead/` always unless query includes `include_dead: true`.
## Output format
Top 10 matches, one per line:
```
N. {id} | {status} | density={score} | "{first-sentence excerpt, ≤120 chars}"
```
If >10 results, show 10 and append: `... N more matches — narrow the query`.
If 0 results: `No matches. Candidate related searches: {suggest 2-3 alternate topic tags}`.
## Worked example
**Query**: `dropout`
**Matches**:
```
1. 2026-04-21-dropout-as-ensemble-thinned-networks | seed | density=7 | "had a thought while running — dropout is secretly an ensemble method."
2. 2026-02-08-bagging-in-deep-nets | draft | density=6 | "bagging is the thing dropout is trying to be."
3. 2025-11-14-noise-as-regularization | published | density=5 | "adding noise at training time prevents the model from memorizing."
```
**Query**: `KV cache` (freeform)
**Matches**:
```
No matches. Candidate related searches: attention-mechanism, inference, context-engineering
```
## Guardrails
1. Read-only. Never mutates seeds.
2. Never returns seeds from `corpus/dead/` unless query explicitly opts in.
3. Excerpt is verbatim from body — never a summary.
4. If >10 matches, truncate and tell the caller.
5. If 0 matches, suggest related searches; do not invent matches.
6. Respect `manual_edits: true` — do not reveal private-looking content beyond first-sentence excerpt without caller explicitly requesting full seed read.
## Quick reference
- Input: query string or structured filter.
- Output: top-10 ranked matches with id, status, density, excerpt.
- Read-only, no side effects.
More from lyndonkl/claude
- abstraction-concrete-examplesBuilds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.
- academic-letter-architectGuides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
- adr-architectureDocuments significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
- adverse-selection-priorProduces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it. Applies Akerlof market-for-lemons logic -- if they offered it, they believe it is +EV for them, so the prior that it is +EV for us is materially below 50%. Reusable across trade evaluation, waiver drops (another team dropping a player is also adverse selection), job-offer analysis, M&A, and any "someone offered me this" situation. Use when you receive an unsolicited trade/offer/proposal, analyzing incoming trade prior, evaluating why a counterparty proposed a deal, or when user mentions adverse selection, market for lemons, why did they offer this, incoming trade prior, they proposed it, Bayesian adjustment on received offer.
- alignment-values-north-starCreates actionable alignment frameworks that give teams a shared North Star (direction), values (guardrails), and decision tenets (behavioral standards). Enables autonomous decision-making while maintaining organizational coherence. Use when starting new teams, scaling organizations, defining culture, establishing product vision, resolving misalignment, creating strategic clarity, or when user mentions North Star, team values, mission, principles, guardrails, decision framework, or cultural alignment.
- analogy-weight-checkFor every analogy in a substacker draft, verifies it carries mechanical weight — the analogy does real work explaining the mechanism, not merely decorates it. Cross-references analogy-catalog.md for novelty (is this analogy reused from a prior post?) and domain fit (biology > organizational > sports preferred; physics/military disfavored). Use whenever an analogy appears in the draft. Trigger keywords: analogy weight, decorative, mechanical weight, reused analogy, catalog check, metaphor check.
- answer-uncomfortable-questionTakes one strategic question about substacker ("should we launch paid?", "is this section dead?", "are we writing for the wrong audience?") and produces the mandatory evidence + reasoning + downside triad plus a recommendation. Used 3 times per Growth Strategist review. Trigger keywords: uncomfortable question, strategic question, evidence reasoning downside, triad.
- attribute-performanceFor each substacker post that materially over- or under-performs the rolling baseline (|z| ≥ 1.0), produces a plain-English attribution paragraph with calibrated confidence (high / medium / low / unexplained). Considers subject-line effect, topic zeitgeist, external share, day-of-week, length effect, and audience-notes signals. Labels unexplained outliers explicitly rather than fabricating a story. Use after compute-baseline when outlier posts exist. Trigger keywords: attribution, why did this post work, outlier explanation, performance analysis.
- auction-first-price-shadingComputes the optimal shaded bid for a first-price sealed-bid auction given a true private value, an estimate of the number of competing bidders N, and a value-distribution assumption. Implements the `(N-1)/N` equilibrium shading rule for uniform private values, adjusts for log-normal or empirical value distributions, layers a risk-aversion adjustment, and caps output against the bidder's remaining budget. Domain-neutral auction theory reusable across fantasy sports (baseball FAAB, NBA/NHL waiver auctions), prediction-market limit sizing, sealed procurement bids, and any blind-bid context. Use when user mentions "first-price auction bid", "sealed bid shading", "(N-1)/N", "FAAB bid amount", "auction shading", "optimal bid first-price", "bid for sealed-bid", "blind bid sizing", or when downstream logic needs a principled shade factor rather than an ad-hoc heuristic.
- auction-winners-curse-haircutApplies a Bayesian haircut to a bid valuation for common-value auctions where winning is itself evidence the bidder over-estimated. Takes a raw valuation, a value-type classification (common_value / private_value / mixed), the number of informed bidders N, and a signal-dispersion estimate, and returns an adjusted valuation. Domain-neutral and reusable across fantasy FAAB, prediction markets, M&A bids, ad-auction budgets, and any generic bidding context. Use when user mentions "winner's curse", "common value auction", "valuation haircut", "adverse valuation", "Bayesian bid adjustment", or "over-paying in auction".