lyndonkl/skills/compute-baseline
skills/compute-baseline/SKILL.md
--- name: compute-baseline description: Computes substacker's rolling 4-week baseline for open rate, click rate, views-per-send, and weekly subscriber delta using corpus/stats/ archived CSVs. Produces per-metric z-scores of the current week against the baseline and flags cold-start windows where fewer than 4 prior weeks exist. Use after ingest-substack-csv each Monday. Trigger keywords: baseline, rolling median, z-score, cold start, per-metric comparison. --- # Compute Baseline ## Workflow ``
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude skills/compute-baselineInstall 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: May 1, 2026, 12:46 AM156.7s1 file scanned
SKILL.md
- name:
- compute-baseline
- description:
- Computes substacker's rolling 4-week baseline for open rate, click rate, views-per-send, and weekly subscriber delta using corpus/stats/ archived CSVs. Produces per-metric z-scores of the current week against the baseline and flags cold-start windows where fewer than 4 prior weeks exist. Use after ingest-substack-csv each Monday. Trigger keywords: baseline, rolling median, z-score, cold start, per-metric comparison.
Compute Baseline
Workflow
Per week:
- [ ] Step 1: Load last 4 weekly CSVs from corpus/stats/
- [ ] Step 2: For each metric (open_rate, click_rate, views_per_send, weekly_sub_delta):
- Compute 4-week median
- Compute trimmed median (drop 1 outlier)
- Compute IQR
- [ ] Step 3: z-score = (current - median) / IQR
- [ ] Step 4: If <4 weeks in history, return baseline: not-yet-established
- [ ] Step 5: Emit baseline object per metric with confidence flag
Baseline object schema
{
"open_rate": {"current": 0.47, "median_4w": 0.49, "trimmed_median": 0.49, "iqr": 0.03, "z": -0.67, "confidence": "medium"},
"click_rate": {...},
"views_per_send": {...},
"weekly_sub_delta": {...},
"cold_start": false
}
Confidence: high if 4+ weeks and low IQR. medium if 4+ weeks and typical IQR. low if N<4.
Guardrails
- Only compare writer's own trajectory. Never pull external benchmarks.
- Below N=4, return cold-start flag. Report writes "baseline not yet established" rather than noisy averages.
- IQR-based comparisons (not σ-based) for robustness at small N.
- Outlier handling: use trimmed median to blunt a single extreme week.
- |z| ≥ 1.0 is the "material move" threshold used downstream by
attribute-performance. - Don't recompute baselines for prior weeks. Each week's baseline is from that week's trailing 4.
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