context-engineering

Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.

Quality

70%

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/context-engineering/SKILL.md

Quality

Content

82%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 an actionable, well-structured reference rich in concrete commands, tables, and copy-paste snippets, with only minor motivational prose and no explicit validation feedback loops holding it back from the top tier.

Dimension	Reasoning	Score
Conciseness	The body is dominated by token-efficient tables, numbered patterns, and code blocks rather than padding, with only minor motivational prose ("Four operations control everything..."; "Every irrelevant token dilutes attention") that could be trimmed, so it sits at efficient-but-not-fully-lean.	4 / 5
Actionability	It provides copy-paste-ready, executable guidance throughout: specific commands (`/compact focus:`, `claude -w`, `/btw`, `/resume`), the `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE=50` setting, a complete PostCompact hook JSON, and a ready-to-paste CLAUDE.md snippet covering the common cases.	5 / 5
Workflow Clarity	Numbered workflows (scratchpad, progressive retrieval, subagent delegation) and the phase-budget table with "Action If Over" checkpoints give a clear sequenced structure, but there is no explicit validate→fix→retry feedback loop, so it stops below 5.	4 / 5
Progressive Disclosure	The single SKILL.md is well-organized with clear section headers, tables, and one-level patterns; there are no nested or buried references and no bundle files, but at ~150 lines some detail (budget tables, the CLAUDE.md template) could arguably be split out, so it is good-but-not-ideal.	4 / 5
	Total	17 / 20 Passed

Description

58%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 clearly states what the skill does and lists several concrete operations, but it lacks any explicit "Use when..." trigger guidance and leans on technical jargon over natural user phrasings.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g. 'Use when managing context in long AI sessions, hitting token limits, or needing to compact/compartmentalize work').

Include common synonyms and concrete trigger phrases users would actually say ('running out of context', 'compact the conversation', 'token budget', 'split work across subagents').

Drop the motivational closer 'to keep AI sessions sharp and efficient' in favor of a concrete when-condition to tighten the description.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete operations ("Write, Select, Compress, Isolate"; "Manage token budgets, compaction strategies, and context partitioning"), with only minor gaps; the closing "keep AI sessions sharp and efficient" is mild fluff, so it stops just short of comprehensive.	4 / 5
Completeness	It has a clear "what" (the four operations and what they manage) but no explicit "when"/"Use when..." trigger clause, so per the missing-trigger guidance completeness is capped at 3 rather than rising to 4.	3 / 5
Trigger Term Quality	Relevant technical terms ("context engineering", "token budgets", "compaction", "context partitioning") appear, but common natural user phrasings and synonyms (e.g. "manage context", "compact context", "running out of tokens") are missing, so it is not a 4.	3 / 5
Distinctiveness Conflict Risk	The named four-operations framing carves a fairly distinct niche with minimal conflict risk against other skills, though it stays broad enough to risk minor overlap with general coding/productivity skills, so not a 5.	4 / 5
	Total	14 / 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: rohitg00/pro-workflow
Path: skills/context-engineering/SKILL.md
Commit: 7f7209d

Reviewed: 3 days 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.