Name: context-engine
Rating: 69.6 (1 reviews)
Author: alirezarezvani

context-engine

Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context during conversations, and enforces privacy/anonymization rules before external API calls. Use when starting any C-suite advisor session, when context looks stale or missing, or before sending company data to an external service.

Quality

85%

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

The canonical home for this skill is context-engine in alirezarezvani/claude-skills

Quality

Content

78%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 well-structured and highly actionable with concrete prompts and a clear load protocol, but progressive disclosure is undermined by a referenced file that is not present in the bundle. Tightening a few editorial lines would further improve conciseness.

Suggestions

Add the missing references/anonymization-protocol.md file (or inline its rules and drop the reference) so the progressive-disclosure pointer resolves.

Remove softening editorial lines such as 'Context is what turns generic advice into specific insight' and the duplicate Keywords section to tighten conciseness.

Add an explicit validate→fix→retry feedback loop for the context-file update path (e.g., re-read the file after append and confirm the timestamp/field landed correctly) to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — tables, bullet lists, and verbatim prompts assume Claude's competence. Not 5 because a few editorial lines pad it ('Context is what turns generic advice into specific insight', 'Handle gracefully — never block the conversation') and the Keywords section duplicates the description; not 3 because there is no concept over-explanation.	4 / 5
Actionability	Guidance is copy-paste ready: exact file path, exact >90-day threshold, verbatim prompt strings, enumerated parse fields, and explicit 'Never send externally' / 'Safe to use' lists. Not below 5 because the in-body rules and prompts cover the common cases concretely.	5 / 5
Workflow Clarity	The Load Protocol is a clearly sequenced 3-step branch with a confidence/action table, and enrichment includes a 'Never silently overwrite... Always confirm before modifying' checkpoint. Not 5 because there is no structured validate→fix→retry feedback loop; not 3 because checkpoints (staleness, quality signals, confirm-before-write) are present.	4 / 5
Progressive Disclosure	Sections are well-organized and the anonymization detail is correctly pushed to a one-level-deep reference signaled in a dedicated References section, but the referenced file references/anonymization-protocol.md does not exist, so the navigation path dead-ends. Not 4 because a referenced path that fails to resolve is a real navigation defect, not a minor gap.	3 / 5
	Total	16 / 20 Passed

Description

92%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 strong: it states concrete third-person actions, gives explicit 'Use when' trigger scenarios, and occupies a distinct C-suite advisor niche. The only minor gap is keyword/extension coverage versus scenario phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — 'Loads and manages company context', 'Reads ~/.claude/company-context.md', 'detects stale context (>90 days)', 'enriches context', 'enforces privacy/anonymization rules' — giving comprehensive coverage. Not below 5 because no concrete action is missing or generic.	5 / 5
Completeness	Explicitly answers both 'what' (loads/reads/detects/enriches/enforces) and 'when' ('Use when starting any C-suite advisor session, when context looks stale or missing, or before sending company data to an external service') with concrete trigger phrases. Not below 5 because neither axis is missing or vague.	5 / 5
Trigger Term Quality	The 'Use when...' clause gives natural scenario triggers ('starting any C-suite advisor session', 'context looks stale or missing', 'before sending company data to an external service'). Not 5 because it relies on scenario phrases rather than keyword synonyms or file extensions; not 3 because the triggers are natural and several.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche — context management for C-suite advisor skills — with triggers specific to that domain, minimizing overlap with other skills. Not below 5 because the C-suite advisor framing makes it clearly distinguishable.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/context-engine/SKILL.md
Commit: 19392f7

Reviewed: ~2 hours 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.