Tessl • The management layer for AI agent skills

SkillPublic

cli-contexts

Manage context engineering configurations, RTK filter sets, and conversation sessions from the CLI. Apply context-relay settings and inspect active context pipelines.

Quality

57%

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/cli-contexts/SKILL.md

Quality

Content

42%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 generated command catalog: install steps are concrete and the per-subcommand layout is navigable, but it suffers from duplicated sections with conflicting flags, examples that add nothing beyond the command name, placeholders never shown with real values, and no workflow or validation guidance for destructive operations. It functions as a lookup table rather than an actionable skill.

Suggestions

Deduplicate the repeated sections: 'context-eng config', 'context-eng show', 'context-eng set', and 'context-eng list' each appear twice with different flag sets, which is confusing and incoherent.

Make examples real: show flags with plausible values (e.g., 'omniroute context-eng set --token-budget 8000 --reserve-pct 20') instead of bare command skeletons, and add one-line descriptions to every subcommand.

Split the full command reference into a separate reference file and keep SKILL.md as an overview with the key workflows (add/switch a context, add and test an RTK filter), including a confirm/verify step before destructive operations like 'remove', 'expire-all', and 'migrate'.

Dimension	Reasoning	Score
Conciseness	Every subcommand carries a boilerplate 'Example:' block that merely restates the header command, flags are listed without values, and 'context-eng config/show/set/list' each appear twice (with conflicting flag sets) — noticeably redundant for the information actually delivered.	2 / 5
Actionability	Commands are real and executable ('npm install -g omniroute', 'omniroute sessions list'), but examples are bare skeletons: placeholders like <id>, <name>, and <file> are never instantiated, no example ever shows a flag with a value, and most subcommands have no description of what they do.	3 / 5
Workflow Clarity	Per-subcommand usage is discernible, but there is no task sequencing (e.g., add context then switch to it, add a filter then test it) and no validation or confirmation guidance for destructive/batch operations ('remove', 'expire-all', 'migrate'), which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	The body has section structure (per-subcommand headers, a quick-install section), but ~400 lines of command reference are inlined in SKILL.md that clearly belong in a separate reference file, and no bundle files or links to deeper material exist — matching the 'overview plus 200 lines of API reference that could be in a separate file' anchor.	3 / 5
	Total	11 / 20 Passed

Description

53%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 names a specific domain and a couple of concrete actions in proper third-person voice, but it omits any 'when to use' trigger guidance and lacks the natural phrases or tool name a user would actually say. It reads as a generated capability summary rather than a trigger-optimized description.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions omniroute, context engineering, RTK filters, or wants to switch/manage CLI contexts or expire sessions.'

Name the CLI tool (omniroute) in the description so users who refer to the tool by name surface this skill.

Trade the generic lead verb 'Manage' for the concrete operations the skill supports (list, add, remove, switch contexts; expire sessions) to lift specificity.

Dimension	Reasoning	Score
Specificity	Names concrete domain objects ('RTK filter sets', 'conversation sessions', 'context-relay settings') plus 1-2 concrete actions ('Apply context-relay settings', 'inspect active context pipelines'), but the lead verb 'Manage' is generic and the fuller capability set (list/add/remove contexts, expire sessions) is not shown.	3 / 5
Completeness	The 'what' is clear (manage configurations, filter sets, sessions; apply settings; inspect pipelines), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Relevant domain keywords are present ('context engineering', 'RTK filter sets', 'conversation sessions', 'CLI') but natural user phrasings and synonyms ('switch context', 'add a filter', the tool name) are missing, so keyword coverage stops at 'some relevant keywords'.	3 / 5
Distinctiveness Conflict Risk	Product-specific jargon ('RTK filter sets', 'context-relay') carves out a fairly distinct niche with only minor overlap risk against generic context/session management skills; it falls short of 5 because the tool name is never stated and 'contexts'/'sessions' are broadly used terms.	4 / 5
	Total	13 / 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: diegosouzapw/OmniRoute
Path: skills/cli-contexts/SKILL.md
Revision: 5b3be70

Reviewed: 25 days ago

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.

cli-contexts

Table of Contents

Is this your skill?