Beads Documentation Style Guide
gastownhall/beads
Sets the house style for the beads user docs: the canonical concept model, required terminology, prose and diagram conventions, and checks before docs work is done.
Summarizes very long texts (books, handbooks, biographies, codebases) using hierarchical multi-pass extraction with cheap model armies.
Install Very Long Text Summarization
$ npx skills add curiositech/some_claude_skills --skill very-long-text-summarization -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install curiositech/some_claude_skills very-long-text-summarization --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/very-long-text-summarization .claude/skills/very-long-text-summarization && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "very-long-text-summarization" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/very-long-text-summarization into .claude/skills/very-long-text-summarization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "very-long-text-summarization", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/very-long-text-summarizationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add curiositech/some_claude_skills --skill very-long-text-summarization -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install curiositech/some_claude_skills very-long-text-summarization --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/very-long-text-summarization .agents/skills/very-long-text-summarization && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "very-long-text-summarization" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/very-long-text-summarization into .agents/skills/very-long-text-summarization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "very-long-text-summarization", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add curiositech/some_claude_skills --skill very-long-text-summarization -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install curiositech/some_claude_skills very-long-text-summarization --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/very-long-text-summarization .cursor/skills/very-long-text-summarization && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "very-long-text-summarization" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/very-long-text-summarization into .cursor/skills/very-long-text-summarization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "very-long-text-summarization", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/curiositech/some_claude_skills.git --path .claude/skills/very-long-text-summarization--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add curiositech/some_claude_skills --skill very-long-text-summarization -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install curiositech/some_claude_skills very-long-text-summarization --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/very-long-text-summarization .gemini/skills/very-long-text-summarization && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "very-long-text-summarization" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/very-long-text-summarization into .gemini/skills/very-long-text-summarization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "very-long-text-summarization", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install curiositech/some_claude_skills very-long-text-summarizationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add curiositech/some_claude_skills --skill very-long-text-summarization -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/very-long-text-summarization .github/skills/very-long-text-summarization && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "very-long-text-summarization" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/very-long-text-summarization into .github/skills/very-long-text-summarization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "very-long-text-summarization", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add curiositech/some_claude_skills --skill very-long-text-summarization -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install curiositech/some_claude_skills very-long-text-summarization --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/curiositech/some_claude_skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/very-long-text-summarization .opencode/skills/very-long-text-summarization && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "very-long-text-summarization" agent skill from https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/very-long-text-summarization into .opencode/skills/very-long-text-summarization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "very-long-text-summarization", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
very-long-text-summarization- GitHub stars
- 243
- Token cost
- ~2.2k tokens
- SKILL.md length
- 633 words
- Files
- 3
- Skills in repo
- 95
- Repo updated
- First seen
- Licence
- MIT
At a glance
Summarizes very long texts (books, handbooks, biographies, codebases) using hierarchical multi-pass extraction with cheap model armies.
- Processing 50+ page documents
- SKILL.md covers When to Use, Architecture: Three-Pass…, Chunking Strategy and Output Modes, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Professional handbooks
What it does
Very Long Text Summarization is an agent skill from curiositech/some_claude_skills. Summarizes very long texts (books, handbooks, biographies, codebases) using hierarchical multi-pass extraction with cheap model armies. Produces structured knowledge maps, not just summaries. Use when processing 50+ page documents, professional handbooks, career biographies, or any text too large for a single context window. Activate on "summarize book", "summarize handbook", "long document", "extract knowledge", "distill text", "professional biography". NOT for short text summarization (<10 pages), real-time…
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `.claude-plugin/plugin.json` and `CHANGELOG.md`).
It sits in Writing & Content, covering Summarization, Context engineering and Technical documentation. The repository describes itself as: Claude skills that make my life easier. The licence is MIT.
When your agent uses it
- Processing 50+ page documents
- Professional handbooks
- Career biographies
- Any text too large for a single context window
Example prompts
- “summarize book”
- “summarize handbook”
- “long document”
- “/very-long-text-summarization”
Requirements
- Python 3
- Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Grep, Glob
What it can do on your machine
Read from SKILL.md and the folder at commit 6713fc7. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditBashGrepGlob
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml, mermaid and python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Very Long Text Summarization loads about 2.2k tokens when it runs. Until then it costs about 153 tokens; SKILL.md has 633 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Read, Write, Edit, Bash, Grep, Glob
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from curiositech/some_claude_skills at commit 6713fc7, republished under its MIT licence (© curiositech). 633 words, ~2,231 tokens.
Download SKILL.mdSave it as
.claude/skills/very-long-text-summarization/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- very-long-text-summarization
- description
- Summarizes very long texts (books, handbooks, biographies, codebases) using hierarchical multi-pass extraction with cheap model armies. Produces structured knowledge maps, not just summaries. Use when processing 50+ page documents, professional handbooks, career biographies, or any text too large for a single context window. Activate on "summarize book", "summarize handbook", "long document", "extract knowledge", "distill text", "professional biography". NOT for short text summarization (<10 pages), real-time chat summarization, or code documentation (use technical-writer).
- allowed-tools
- Read, Write, Edit, Bash, Grep, Glob
- argument-hint
- [file-path-or-url] [output: summary|knowledge-map|skill-draft]
- metadata.category
- Content & Writing
- metadata.tags
- very, long, text, summarize-book, summarize-handbook
Very Long Text Summarization
Processes texts too large for a single context window using hierarchical multi-pass extraction with armies of cheap models. Produces structured knowledge maps, indexed summaries, and skill drafts — not just prose compression.
When to Use
✅ Use for:
- Professional handbooks and textbooks (100-1000+ pages)
- Career biographies and memoirs (extracting expertise patterns)
- Large codebases (architecture-level understanding)
- Research paper collections (synthesizing findings across papers)
- Any text exceeding a single context window (~100K tokens)
❌ NOT for:
- Short documents (<10 pages) — just read them directly
- Real-time conversation summarization (use auto-compact patterns)
- Code documentation generation (use
technical-writer) - Simple TL;DR requests (not worth the multi-pass overhead)
Architecture: Three-Pass Hierarchical Extraction
flowchart TD
D[Document] --> C[Chunk into segments]
C --> P1["Pass 1: Haiku army\n(parallel extraction)"]
P1 --> I[Intermediate summaries]
I --> P2["Pass 2: Sonnet synthesis\n(merge + structure)"]
P2 --> S[Structured knowledge map]
S --> P3["Pass 3: Opus refinement\n(optional, for skill drafts)"]
P3 --> O[Final output]Pass 1: Chunked Extraction (Haiku Army)
Split the document into overlapping chunks (~4K tokens each, 500 token overlap). Deploy one Haiku call per chunk in parallel. Each extracts:
extraction_template:
summary: "2-3 sentence summary of this section"
key_claims: ["list of factual claims or assertions"]
processes: ["any step-by-step procedures described"]
decisions: ["any decision points or heuristics mentioned"]
failures: ["any failures, mistakes, or anti-patterns described"]
aha_moments: ["any insights, realizations, or conceptual breakthroughs"]
metaphors: ["any metaphors or mental models used"]
temporal: ["any 'things changed when...' or 'before X, after Y' patterns"]
quotes: ["notable direct quotes worth preserving"]
references: ["any citations, links, or cross-references"]Cost: ~$0.001 per chunk. A 300-page book (~150K tokens) = ~38 chunks = ~$0.04 total for Pass 1.
Parallelism: All chunks run simultaneously. A 300-page book completes Pass 1 in ~3 seconds (wall clock), not 3 minutes.
Pass 2: Synthesis (Sonnet)
Feed all Pass 1 extractions into one or more Sonnet calls. Sonnet merges, deduplicates, and structures the knowledge.
synthesis_template:
document_summary: "1-2 paragraph executive summary"
knowledge_map:
core_concepts:
- concept: "name"
definition: "what it means in this domain"
relationships: ["connects to concept X because..."]
processes:
- name: "process name"
steps: ["ordered steps"]
decision_points: ["where choices are made"]
common_mistakes: ["what goes wrong"]
expertise_patterns:
- pattern: "what experts do differently"
novice_mistake: "what novices do instead"
aha_moment: "the insight that bridges the gap"
temporal_evolution:
- period: "date range"
paradigm: "what was believed/practiced"
change_trigger: "what caused the shift"
key_metaphors:
- metaphor: "how practitioners think about X"
maps_to: "the underlying structure it represents"
index:
- topic: "topic name"
chunk_ids: [3, 7, 12] # Which original chunks cover this
summary: "1 sentence"Cost: ~$0.02-0.05 depending on extraction volume. The index preserves traceability back to specific book sections.
Pass 3: Refinement (Opus, Optional)
For skill-draft output mode: Opus takes the knowledge map and produces a SKILL.md following the skill-architect template. This is the "crystallize skill from handbook" pipeline.
Cost: ~$0.10. Only run when the output is a skill draft.
Chunking Strategy
Semantic Chunking (Preferred)
Split on document structure — chapter boundaries, section headings, paragraph breaks. Preserves semantic coherence within each chunk.
def semantic_chunk(text: str, max_tokens: int = 4000, overlap: int = 500) -> list[str]:
"""Split text on structural boundaries with overlap."""
# Split on headings, then merge short sections
sections = split_on_headings(text) # ##, ###, etc.
chunks = []
current = ""
for section in sections:
if count_tokens(current + section) > max_tokens:
chunks.append(current)
# Overlap: keep the last ~500 tokens
current = get_last_n_tokens(current, overlap) + section
else:
current += section
if current:
chunks.append(current)
return chunksFixed-Size Chunking (Fallback)
For unstructured text without headings. Split on paragraph boundaries, targeting ~4K tokens with 500-token overlap.
Why Overlap?
Concepts that span chunk boundaries need to appear in both chunks to be extracted. Without overlap, you lose cross-boundary knowledge.
Output Modes
Mode 1: Summary
Produces a structured summary with executive overview, key concepts, and index.
Use for: Quick understanding of a long document. Reading a handbook before a meeting.
Mode 2: Knowledge Map
Produces the full knowledge map: concepts, processes, expertise patterns, temporal evolution, metaphors. Machine-readable (YAML/JSON) for downstream processing.
Use for: Feeding into skill creation, domain meta-skill development, or cross-document analysis.
Show full SKILL.md (262 more words)Show less
Mode 3: Skill Draft
Produces a SKILL.md following the skill-architect template, with the handbook's expertise encoded as decision trees, anti-patterns, and shibboleths.
Use for: Converting professional handbooks into Claude skills. The KE pipeline.
Cost Model
| Document Size | Pages | Chunks | Pass 1 (Haiku) | Pass 2 (Sonnet) | Pass 3 (Opus) | Total |
|---|---|---|---|---|---|---|
| Article | 10 | 4 | $0.004 | $0.01 | — | $0.014 |
| Chapter | 30 | 10 | $0.01 | $0.02 | — | $0.03 |
| Handbook | 300 | 38 | $0.04 | $0.05 | $0.10 | $0.19 |
| Textbook | 800 | 100 | $0.10 | $0.10 | $0.10 | $0.30 |
| Encyclopedia | 2000+ | 250+ | $0.25 | $0.20 | $0.10 | $0.55 |
Processing time is dominated by the longest single Haiku call (~2-3s). With full parallelism, even a 2000-page text completes Pass 1 in under 5 seconds.
Anti-Patterns
Single-Pass Summarization
Wrong: Feed the entire document into one Opus call. Why: Exceeds context window, or attention dilution produces weak extraction on such long input. Right: Hierarchical multi-pass. Cheap parallel extraction → expensive synthesis.
Summarization Without Structure
Wrong: Produce a 2-paragraph prose summary of a 300-page handbook. Why: The structure IS the knowledge. A flat summary loses the decision trees, failure patterns, and temporal evolution that make skills valuable. Right: Structured knowledge map with indexed access back to source sections.
Skipping Overlap
Wrong: Chunk on hard boundaries with no overlap. Why: Cross-boundary concepts get split and lost. Right: 500-token overlap between chunks. Each chunk includes the tail of the previous chunk.
Ignoring Source Traceability
Wrong: Produce extractions without tracking which chunk they came from.
Why: When a claim seems wrong, you need to verify it against the source. Without traceability, you can't.
Right: Every extraction carries a chunk_id linking back to the original text segment.
© curiositech, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files in .claude/skills/very-long-text-summarization of curiositech/some_claude_skills.
- SKILL.md
- .claude-plugin/plugin.json
- CHANGELOG.md
Open the folder on GitHubat commit 6713fc7
Compare with similar skills
Very Long Text Summarization next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Very Long Text Summarization this skillcuriositech/some_claude_skills | 243 | — | ~2.2k | Automated safety check: Notes | MIT | |
| Beads Documentation Style Guidegastownhall/beads | 28k | — | ~3.2k | Automated safety check: Pass | MIT | |
| JavaScript Concept Page Workflowleonardomso/33-js-concepts | 67k | — | ~3.9k | Automated safety check: Pass | MIT | |
| Technical Writing Standardcursor/plugins | 10k | 10 repos | ~2.4k | Automated safety check: Pass | None | |
| Heym Documentation Articlesheymrun/heym | 1.4k | — | ~780 | Automated safety check: Pass | Custom licence | |
| JavaScript Concept Page Writerleonardomso/33-js-concepts | 67k | — | ~14k | Automated safety check: Pass | MIT |
Similar skills
JavaScript Concept Page Workflow
leonardomso/33-js-concepts
Orchestrates five skills to produce a complete JavaScript concept documentation page, from resource curation through writing, tests, fact-checking and SEO.
- Official
Technical Writing Standard
cursor/plugins
Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.
Heym Documentation Articles
heymrun/heym
Creates and updates documentation articles for the Heym platform: category choice, manifest entry, markdown file and cross-links from existing pages.
JavaScript Concept Page Writer
leonardomso/33-js-concepts
Writes or reviews documentation pages for the 33 JavaScript Concepts project, following its structure, a beginner-friendly voice and rules against AI-sounding language.
Technical Writing Workflow
tokenbender/agent-guides
A skill your agent uses for planning, researching, drafting, revising, or auditing technical write-ups, textbooks, papers, reports, READMEs, research notes, PR narratives, and public technical prose.
More from curiositech/some_claude_skills
All 95 skills in this repoCrisis Detection Intervention AI
curiositech/some_claude_skills
Detect crisis signals in user content using NLP, mental health sentiment analysis, and safe intervention protocols.
Form Validation Architect
curiositech/some_claude_skills
End-to-end form handling with react-hook-form, Zod schemas, validation patterns, error messaging, field arrays, and multi-step wizards.
GitHub Actions Pipeline Builder
curiositech/some_claude_skills
Build production CI/CD pipelines with GitHub Actions. An agent skill from curiositech/some_claude_skills.
Background Job Orchestrator
curiositech/some_claude_skills
Expert in background job processing with Bull/BullMQ (Redis), Celery, and cloud queues.
Competitive Cartographer
curiositech/some_claude_skills
Strategic analyst that maps competitive landscapes, identifies white space opportunities, and provides positioning recommendations.
Computer Vision Pipeline
curiositech/some_claude_skills
Build production computer vision pipelines for object detection, tracking, and video analysis.
Related
Categories
Questions about Very Long Text Summarization
What does Very Long Text Summarization do?
Summarizes very long texts (books, handbooks, biographies, codebases) using hierarchical multi-pass extraction with cheap model armies. Very Long Text Summarization is an agent skill from curiositech/some_claude_skills. Summarizes very long texts (books, handbooks, biographies, codebases) using hierarchical multi-pass extraction with cheap model armies.
When should I use Very Long Text Summarization?
Very Long Text Summarization fits situations like: processing 50+ page documents; professional handbooks; career biographies; any text too large for a single context window.
How do I install Very Long Text Summarization in Claude Code?
Run `npx skills add curiositech/some_claude_skills --skill very-long-text-summarization -a claude-code`. Or copy the skill folder (.claude/skills/very-long-text-summarization in curiositech/some_claude_skills) into .claude/skills/very-long-text-summarization in your project. Claude Code loads it when a task matches its description.
How do I install Very Long Text Summarization in Codex?
Run `npx skills add curiositech/some_claude_skills --skill very-long-text-summarization -a codex`. Or copy the skill folder (.claude/skills/very-long-text-summarization in curiositech/some_claude_skills) into .agents/skills/very-long-text-summarization in your project. Codex loads it when a task matches its description.
Can I use Very Long Text Summarization in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add curiositech/some_claude_skills --skill very-long-text-summarization -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/very-long-text-summarization, .gemini/skills/very-long-text-summarization, .github/skills/very-long-text-summarization and .opencode/skills/very-long-text-summarization in your project.
What does Very Long Text Summarization need to run?
SKILL.md names no scripts, command-line tools or credentials: Very Long Text Summarization is instructions for the agent only. Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, Grep, Glob.
Does Very Long Text Summarization access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Very Long Text Summarization safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Very Long Text Summarization use?
Very Long Text Summarization is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Very Long Text Summarization use?
About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Very Long Text Summarization?
Skills that share tags, products or a category with Very Long Text Summarization: Beads Documentation Style Guide (gastownhall/beads, 28k stars), JavaScript Concept Page Workflow (leonardomso/33-js-concepts, 67k stars), Technical Writing Standard (cursor/plugins, 10k stars) and Heym Documentation Articles (heymrun/heym, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Very Long Text Summarization?
curiositech (a GitHub organization) maintains it in curiositech/some_claude_skills, which has 243 GitHub stars. The repository holds 95 skills in this directory. The repository was last updated on September 6, 2026.
Source: curiositech/some_claude_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.