Sweep Stale Seeds
Identifies substacker seeds older than 30 days with status=seed and no incoming related_seeds links, flags them for writer review, and recommends keep / promote-to-draft / kill based on density score. Does NOT auto-execute any action. Emits a review list to ops/librarian/YYYY-MM-DD-stale-sweep.md. Run at session start after ingest, once per day max. Trigger keywords — stale, sweep, review, old seeds, cleanup, gardener, corpus hygiene.
Install
/plugin marketplace add lyndonkl/claudeThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add lyndonkl/claude --skill sweep-stale-seedsgit clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/sweep-stale-seeds ~/.claude/skills/sweep-stale-seedsPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Sweep Stale Seeds
## Table of Contents
- [Workflow](#workflow)
- [Recommendation rules](#recommendation-rules)
- [Output format](#output-format)
- [Worked example](#worked-example)
- [Guardrails](#guardrails)
**Related skills:** Called by Librarian agent's pipeline step 2. Output consumed by the writer and by `curator` on its monthly-ish cycle.
## Workflow
```
Sweep the corpus for stale seeds:
- [ ] Step 1: If ops/librarian/{today}-stale-sweep.md exists, skip (daily idempotency)
- [ ] Step 2: Glob corpus/seeds/*.md
- [ ] Step 3: For each seed, parse frontmatter
- [ ] Step 4: Apply stale criteria: status=seed AND created < today-30d AND no related_seeds referencing this seed
- [ ] Step 5: For each stale seed, compute recommendation
- [ ] Step 6: Write the review list to ops/librarian/{today}-stale-sweep.md
```
### Step 4: Stale criteria
A seed is stale if ALL of:
- `status: seed` (not yet promoted to draft)
- `created` is > 30 days before today
- No other seed's `related_seeds` includes this seed's id (orphan test)
- `manual_edits: false` (writer-edited seeds are never in the sweep)
## Recommendation rules
| If... | Recommend |
|---|---|
| `density >= 7` | `promote-to-draft` (high-quality material sitting stale is the real loss) |
| `density <= 3` | `kill` (low-density AND stale = not going to improve) |
| else | `keep` (mid-density — more time to mature) |
## Output format
`ops/librarian/YYYY-MM-DD-stale-sweep.md`:Details
- Skill name
sweep-stale-seeds- Repository
- lyndonkl/claude
- Path
skills/sweep-stale-seeds/SKILL.md- Repo updated
- 1 September 2026
FAQ
What does the Sweep Stale Seeds skill do?
Identifies substacker seeds older than 30 days with status=seed and no incoming related_seeds links, flags them for writer review, and recommends keep / promote-to-draft / kill based on density score. Does NOT auto-execute any action. Emits a review list to ops/librarian/YYYY-MM-DD-stale-sweep.md. Run at session start after ingest, once per day max. Trigger keywords — stale, sweep, review, old seeds, cleanup, gardener, corpus hygiene.
How do I install the Sweep Stale Seeds skill?
Claude Code plugin: /plugin marketplace add lyndonkl/claude. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Sweep Stale Seeds popular?
It lives in lyndonkl/claude, which has 200 GitHub stars and 25 forks.
Related skills
Abstraction Concrete Examples
200lyndonkl/claude
Builds 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 Architect
200lyndonkl/claude
Guides 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 Architecture
200lyndonkl/claude
Documents 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.
Translation Reframing Audience Shift
200lyndonkl/claude
Adapts content for different audiences while preserving core accuracy, changing tone, depth, emphasis, and framing to match audience expertise and goals. Use when technical content needs business framing, strategic vision needs tactical translation, expert knowledge needs simplification, formal content needs casual tone, long-form needs summarization, internal content needs external framing, or cross-cultural adaptation is needed. Use when user mentions "explain to", "reframe for", "translate for [audience]", "adapt for [executives/engineers/customers]", or "same content, different audience".
Summarize Signal
200lyndonkl/claude
Given a candidate item from the substacker Trend Scout fetch, WebFetches the full post or arXiv abstract and produces a one-line "teaches X" summary plus signal_type classification (mechanism / empirical / tool / opinion / announcement / benchmark). Distinguishes teaching-content from capability-announcement explicitly. Use during the weekly run, after fetching and before ranking. Trigger keywords — summarize, signal type, mechanism vs announcement, teaching content.
Update Analogy Catalog
200lyndonkl/claude
Appends an entry to substacker shared-context/analogy-catalog.md when the writer PUBLISHES a post that uses a new analogy. Not invoked on seed or draft — only on publish. Records source, target, post, freshness, mapping, where-it-breaks, and why-it-worked. Prevents silent recycling in future Intuition Builder runs. Use at publish time for any post that contains a non-trivial analogy. Trigger keywords — catalog, analogy catalog, update catalog, publish, analogy archive.
Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.