lyndonkl/skills/search-corpus
skills/search-corpus/SKILL.md
--- 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, alre
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude skills/search-corpusInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 10:20 AM131.9s1 file scanned
SKILL.md
- 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
- Query forms
- Output format
- Worked example
- 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:
- Topic tag (e.g.,
dropout): grep frontmattertopics:for the tag; fallback to body keyword. - Freeform keyword (e.g.,
kv cache): grep body + title for the phrase. - Structured (e.g.,
{topics: [attention-mechanism], status: published}): direct filter.
Ranking
Rank by:
- Exact tag match > freeform body match.
- Density score descending.
- Recency (created date descending).
- 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
- Read-only. Never mutates seeds.
- Never returns seeds from
corpus/dead/unless query explicitly opts in. - Excerpt is verbatim from body — never a summary.
- If >10 matches, truncate and tell the caller.
- If 0 matches, suggest related searches; do not invent matches.
- 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.
Related Skills
lyndonkl/skills/advisory-edit
testing
VerifiedTrustedCommunity
--- 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
112SKILL.mdUpdated Jun 3, 2026
lyndonkl/strategist-voice
testing
VerifiedTrustedCommunity
Provides the house style for analyst-grade strategist writing — third-person register with sparing first-person, no em dashes, no "not X, not Y, not Z" negation cascades, numbered footnote citations rather than inline source parentheticals, specific opinion-signaling phrases, and topic-forward paragraph structure modeled on voice patterns observed in Damodaran's Musings on Markets and Thompson's Stratechery. Use when consolidating working notes into a finished long-form strategist or analyst report that must read as written by a senior human analyst rather than an AI assistant.
98SKILL.mdUpdated May 17, 2026
lyndonkl/markdown-to-pdf
testing
VerifiedTrustedCommunity
Renders a markdown report to a PDF using pandoc with xelatex (11pt serif body, 1-inch margins, numbered footnotes, formal heading hierarchy). Requires a one-time install of pandoc and a LaTeX engine on the user's machine — basictex on macOS or texlive-xetex on Linux. Does not attempt automatic install. Fails loudly with the exact install commands if pandoc or xelatex is missing on the user's PATH. Use when producing a finished strategist or analyst report PDF from a polished markdown source.
98SKILL.mdUpdated May 17, 2026
lyndonkl/worked-example-walkthrough
testing
VerifiedTrustedCommunity
Produces step-by-step computational walkthroughs of vector and matrix operations as a sequence of numbered "frames", showing the explicit state at each step. The text-equivalent of a 3Blue1Brown animation — each frame shows what changed and why, so the learner can re-trace the operation by hand. Use when the learner needs to *see* a computation unfold (eigenvalue computation, attention with 3 tokens, gradient descent step, SVD on a 2×2, layer norm on a 3-vector, softmax of a small input), when an explanation has been given but the learner needs to ground it in a worked example, or when introducing an operation that's intimidating in symbol form but trivial in pencil-and-paper form.
94SKILL.mdUpdated May 10, 2026