datascience
claudecodexData science project standards - notebook structure, rich output styling, copier scaffolding, and compliance review
20 skills · 15 commands
Project journal management - append-only entries, continuous numbering, verification, and archiving
Plugin journal from marketplace stellarshenson-marketplace in stellarshenson/claude-code-plugins. Commands read from the repo's manifest — 3 days ago.
archiveArchive older journal entries via `journal-tools archive`. Keeps last 20 in main, appends rest to JOURNAL_ARCHIVE.md. Triggers - "archive journal", "prune journal", "compact journal".
articleExtract an oversized journal entry's depth into a standalone article in `docs/` and condense the entry to a Standard-tier summary that links to the article. Use when `journal-tools check` warns that an entry is over the Extended max (400 words) - even Extended caps there, and the rationale belongs i
createInitialise a new `.claude/JOURNAL.md` for a project that doesn't have one yet. Strictly first-time setup — refuses if the file exists. Triggers - "create journal", "init journal", "start journal", "new journal".
journalManage `.claude/JOURNAL.md`. **Auto-triggers on ANY mention of "journal"** — questions about the journal, entry format, word-count tiers, archiving, the `/journal:*` commands, or the `journal-tools` CLI. Also triggers on "update journal", "add journal entry", "log this", "journal this", "record this
standardizeStandardize oversized / mis-marked journal entries via the ACP repair loop. For each offender, the shipped prompt YAML drives a focused `claude -p` subprocess that decides Extended vs Condense vs Drop-marker; the CLI applies the verdict. Triggers - "standardize journal", "fix journal entry tiers", "
updateAppend a new entry to `.claude/JOURNAL.md` OR update the last entry in place when the new work is a small continuation of it. Triggers - "update journal", "add journal entry", "log this", "add entry", "journal this", "record this in the journal".
/journal:archiveArchive older journal entries via `journal-tools archive`. Keeps last 20 in main, appends rest to JOURNAL_ARCHIVE.md. Triggers - "archive journal", "prune journal", "compact journal".
/journal:articleExtract an oversized journal entry's depth into a standalone article in `docs/` and condense the entry to a Standard-tier summary that links to the article. Use when `journal-tools check` warns that an entry is over the Extended max (400 words) - even Extended caps there, and the rationale belongs i
/journal:createInitialise a new `.claude/JOURNAL.md` for a project that doesn't have one yet. Strictly first-time setup — refuses if the file exists. Triggers - "create journal", "init journal", "start journal", "new journal".
/journal:standardizeStandardize oversized / mis-marked journal entries via the ACP repair loop. For each offender, the shipped prompt YAML drives a focused `claude -p` subprocess that decides Extended vs Condense vs Drop-marker; the CLI applies the verdict. Triggers - "standardize journal", "fix journal entry tiers", "
/journal:updateAppend a new entry to `.claude/JOURNAL.md` OR update the last entry in place when the new work is a small continuation of it. Triggers - "update journal", "add journal entry", "log this", "add entry", "journal this", "record this in the journal".
Data science project standards - notebook structure, rich output styling, copier scaffolding, and compliance review
20 skills · 15 commands
SVG infographic creation with grid-first design, CSS theme classes, dark/light mode, validation tools, and 60+ reference examples
7 skills · 6 commands · 1 agent
Critical document analysis with persona-driven risk scoring, iterative scorecard evaluation, and versioned corrections - plus adversarial-review, hostile red-team review of code and artefacts with pluggable expert adversaries
6 skills · 5 commands · 2 agents
Micro project management - acceptance criteria and defects as markdown checklists with permanent ids, author handles, severity triage, and computed reports
6 skills · 5 commands · hooks
Structured document processing with source grounding (lexical-mode default: CPU-only frozen logistic with 3 effort tiers; optional semantic + NLI entailment), uniformization, PDF manipulation, and validation
5 skills · 5 commands
Autonomous build iteration orchestrator with multi-agent review, FSM-driven lifecycle, and YAML-configured workflows
4 skills · 1 command · 1 agent
Claude API and SDK documentation skill for building LLM-powered applications
19 skills
Plugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a first-party row, sent in batches with the session's own credential.
Design fluency for frontend development. 1 skill with 24 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
1 skill · 4 agents · hooks
Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
1 skill
Generate natively editable PPTX from PDF / DOCX / URL / Markdown — real DrawingML shapes, text boxes, charts, and animations. Note: run `pip install -r requirements.txt` inside the installed plugin directory for the Python post-processing scripts to work.
1 skill
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.