acontext-installer

Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./landingpage/public/SKILL.md

Quality

Content

65%

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

The body is highly actionable with concrete, executable commands and a well-organized section structure, but it is a long monolithic document with implicit validation in the primary install flow and no progressive disclosure into reference files. It is strong on actionability and moderate on the other dimensions.

Suggestions

Tighten the document and remove the self-referential 'Save this skill for reuse' blockquote, which is not core task content, to improve conciseness.

Add inline validation checkpoints to the core installation flow (e.g., verify the CLI with 'acontext version', verify login with 'acontext whoami') rather than deferring verification to the troubleshooting section.

Split the dense CLI and per-platform plugin reference tables into separate reference files (e.g., CLI_REFERENCE.md, PLUGIN_CONFIG.md) with a concise overview in SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense, actionable reference material (commands and tables) rather than concept explanation, but the ~237-line monolithic doc, the dual Claude Code + OpenClaw duplication, and the self-referential 'Save this skill for reuse' blockquote could be tightened, so it does not earn a 3.	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands throughout ('curl -fsSL https://install.acontext.io \| sh', 'acontext login', 'acontext skill upload ./my-skill-dir --user alice@example.com') plus concrete config JSON and flag tables, matching the 'fully executable, specific examples' anchor.	3 / 3
Workflow Clarity	Installation is clearly sequenced (1 Install CLI, 2 Login, 3 Add to Agent) and project management includes a ping verification, but the core install flow lacks inline validation checkpoints after each step and relies on a separate troubleshooting section for feedback loops, fitting the 'steps listed but checkpoints implicit' anchor.	2 / 3
Progressive Disclosure	No bundle files exist and the entire ~237-line reference is inline in SKILL.md; sections are well-organized with clear headers, but content that should be split (CLI reference, per-platform plugin configs, troubleshooting) is monolithic, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 names concrete, product-specific actions but relies on imperative voice, omits any 'Use when' trigger guidance, and carries generic memory concepts that create overlap risk. It is adequate but not distinctive or trigger-complete.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when setting up Acontext memory for an agent, or when the user mentions Acontext, agent memory, or persistent context') to raise completeness and distinctiveness.

Rewrite in third-person voice (e.g., 'Installs Acontext, logs in and initializes a project, and adds skill memory to an agent') instead of imperative form, per the third-person guideline.

Incorporate common natural trigger terms such as 'agent memory', 'persistent context', and 'knowledge base' to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description lists three concrete, named actions ('Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent'), which would anchor at 3, but it is written in imperative/second-person voice ('Install', 'Login', 'Add') rather than third person, so the voice penalty reduces specificity by 1.	2 / 3
Completeness	It clearly states what the skill does (install, login/init project, add skill memory) but includes no 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	The product name 'Acontext' (repeated) plus 'Install', 'Login', 'Skill Memory', and 'Agent' provide some natural triggers, but common variations a user might actually say ('agent memory', 'persistent context', 'sessions', 'knowledge base') are absent from the description.	2 / 3
Distinctiveness Conflict Risk	The named product 'Acontext' gives it a niche, but the generic 'Add Skill Memory to Agent' phrasing overlaps with the broad category of agent-memory skills and, with no explicit trigger clause, it could still trigger for the wrong memory skill.	2 / 3
	Total	8 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: memodb-io/Acontext
Path: landingpage/public/SKILL.md
Commit: 259d73b

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.