Automated summary

This skill deterministically compresses long logs or text into high-signal excerpts to free up space in the context window.

Strengths

Always preserves evidence lines (error, exception, traceback, fail, warning, fatal)
Applies reproducible rules: keep head/tail structure, collapse repeated lines and blocks, annotate omitted ranges
Produces a clear output format reporting source, original line count, and kept line count
Ships with a bundled Python script to automate the compression

Limitations

Rules are purely lexical: an error lacking a recognized keyword may be dropped
Block collapsing can hide subtle differences between seemingly repeated lines
Assumes the Python script is available or that rules are applied manually

When to use it

Use it when a user pastes very long logs, a massive stack trace, or a file too large to read in full.

When not to use it

Avoid it when content must be kept verbatim, such as legal review, line-by-line comparison, or material where every line matters.

Security analysis

Caution

Quality score86/100

The skill does not contain destructive commands, obfuscated payloads, or obvious exfiltration. However, it declares Bash and runs a local Python helper script, which is a powerful execution capability for a legitimate compression workflow. This warrants caution rather than safe, pending inspection of the bundled script.

Findings

•Declares Bash and invokes a local bundled Python script whose contents are not included, so execution behavior cannot be fully audited from SKILL.md alone.
•Uses a hardcoded user-home path (~/.ai-context/skills/token-compressor/scripts/compress_text.py), which could execute whatever exists at that path.

How this analysis is made

Examples

Compress a huge stack trace

Here's a 12,000-line stack trace from our production crash — compress it down so I can actually work with it, but don't lose the real error.

Trim verbose CI logs

The CI build log is enormous. Reduce it to a high-signal excerpt that keeps the failing lines and error context.

Shrink a large log file

Read ~/.logs/app.log and give me a compressed excerpt with the warnings, errors and final failure intact.

version: 1.0.0 name: token-compressor description: Deterministically compresses long logs/text into high-signal excerpts to free context window. allowed-tools: Read, Bash, Grep tags: token, compression

Token Compressor

Name: Token Compressor
Author: Skills Guide Bot

This skill reduces token overhead by compressing bulky inputs (logs, stack traces, long docs) while preserving evidence.

When to Use

The user pastes long logs.
Tool output is huge.
A file is too large to read fully.

Compression Rules (Deterministic)

Apply these tactics in order:

Keep evidence lines
- Always keep lines matching: error, exception, traceback, fail, warning, fatal.
Keep structure
- Keep the first N lines (header/context) and last M lines (final error).
Deduplicate noise
- Collapse repeated consecutive lines.
- Collapse repeated blocks (same line repeated many times).
Summarize the rest
- Replace large omitted blocks with a short note: (… 3,421 lines omitted …).

Tooling

If available, use the bundled compressor script:

python3 ~/.ai-context/skills/token-compressor/scripts/compress_text.py --help

Output Format

## Compressed Context

- Source: …
- Original: X lines
- Kept: Y lines
- Notes: …

```text
…compressed excerpt…


## Anti-Patterns

- Removing the exact error line.
- Keeping only a summary with no evidence.
- Dumping the entire log into the reasoning window.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/token-compressor-mrwakbew/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/token-compressor-mrwakbew' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/token-compressor-mrwakbew/download' --output '.skill-downloads/token-compressor-mrwakbew/SKILL.md.part' && mv '.skill-downloads/token-compressor-mrwakbew/SKILL.md.part' '.skill-downloads/token-compressor-mrwakbew/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Bash, Grep

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code

test -f '.skill-downloads/token-compressor-mrwakbew/SKILL.md' && test -s '.skill-downloads/token-compressor-mrwakbew/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/token-compressor' && cp -R '.skill-downloads/token-compressor-mrwakbew' '.claude/skills/token-compressor'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation

openskills install './.skill-downloads/token-compressor-mrwakbew'

openskills read 'token-compressor-mrwakbew'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/token-compressor-mrwakbew/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

PDF Reader

Productivity

Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.

Claude CodeCursorCodexbeginnerSafe 20,122

Skills Guide Bot