ac-context-optimizer

Optimize context usage for autonomous coding. Use when managing context window, prioritizing information, reducing token usage, or improving efficiency.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ac-context-optimizer/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a clean, concise stub with executable quick-start code and a properly signaled one-level reference to a real script. It is held back by undefined placeholder arguments, total deferral of API detail to the script, and lack of guidance on when to use each method.

Suggestions

Show concrete example inputs for the Quick Start code (e.g. a representative current_context value and items list) so the snippet is copy-paste ready rather than relying on undefined placeholders.

Briefly state when to call optimize_context versus prioritize_information and the expected sequence, so the single-action workflow is fully unambiguous.

Inline 1-2 key method signatures or return shapes from context_optimizer.py so the API Reference section adds value beyond 'see the file'.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, but the intro line and the 'Purpose' section near-duplicate each other ('Optimize context window usage...' vs 'Manages and optimizes context usage...'), a minor redundancy that could be trimmed.	4 / 5
Actionability	Quick Start provides concrete code with a real import and real method names (optimize_context, prioritize_information) referencing an actual bundle script, but arguments are undefined placeholders (project_dir, current_context, items) and method signatures are deferred entirely to the script file.	4 / 5
Workflow Clarity	As a simple skill the single usage pattern (instantiate optimizer, call optimize_context/prioritize_information) is reasonably unambiguous, but it is not explained when to use optimize_context versus prioritize_information or in what sequence.	4 / 5
Progressive Disclosure	Content is organized into clear sections (Purpose, Quick Start, API Reference) with a single one-level-deep, well-signaled reference to scripts/context_optimizer.py (a real bundle file); the body is thin enough that it reads more as a stub than a developed overview, keeping it just below a 5.	4 / 5
	Total	16 / 20 Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is well-formed with an explicit 'Use when...' trigger clause covering multiple natural phrases, clearly answering both what and when. Its main weakness is that the named actions are abstract categories rather than concrete, distinctive operations.

Suggestions

Replace abstract action verbs ('managing', 'prioritizing', 'improving efficiency') with more concrete operations the skill actually performs (e.g. 'summarize conversation history', 'drop low-value messages', 'compact tool outputs').

Add common user synonyms to the trigger clause such as 'context too long', 'trim context', or 'fit within token limits' to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Optimize context usage for autonomous coding') and lists several actions via the trigger clause ('managing context window, prioritizing information, reducing token usage'), but these are abstract categories rather than concrete operations like 'extract text' or 'fill forms'.	3 / 5
Completeness	Explicitly answers both what ('Optimize context usage for autonomous coding') and when ('Use when managing context window, prioritizing information, reducing token usage, or improving efficiency') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes reasonably natural phrases users would say ('context window', 'token usage', 'reducing token usage'); coverage is good though a few natural synonyms (e.g. 'context too long', 'trim context') are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a fairly distinct niche (context/token optimization for autonomous coding) with specific triggers, but could overlap marginally with general coding-efficiency or memory-management skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: fernandezbaptiste/Skrillz
Path: skills/ac-context-optimizer/SKILL.md
Commit: 93ed392

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.