CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

omni-context-rtk

Configure RTK filters, context engineering rules, and context relay settings. Test compression with real prompt samples and manage context transformation pipelines.

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/omni-context-rtk/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

51%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 reasonably lean auto-generated API catalog, but it is a reference list rather than usable guidance: mutating endpoints have placeholder payloads, no workflow or validation steps are given for the capabilities the description promises, and two endpoint descriptions are generator artifacts. It reads as scaffolding awaiting real content.

Suggestions

Replace the empty '-d "{}"' bodies on the PUT config, POST import, and POST test examples with realistic minimal payloads (e.g., an actual RTK filter TOML import body and a compression test body with a sample prompt).

Add explicit workflows with validation checkpoints, e.g. import: POST /import with validate-only → review diagnostics from GET /filters → install; and note how to verify a config change by re-fetching GET /config.

Fix or remove the generator-artifact descriptions ('GET context › rtk › discover', 'GET context › rtk › learn') and either include docs/openapi.yaml in the skill bundle or drop that path, keeping only the live GET /api/openapi/spec pointer.

DimensionReasoningScore

Conciseness

The body is lean — an endpoint listing with curl commands and no explanations of concepts Claude already knows. Minor waste exists: the Overview duplicates the frontmatter description verbatim, and the 'GET context › rtk › discover' / 'GET context › rtk › learn' lines are auto-generated filler that carries no information.

4 / 5

Actionability

GET endpoint curls are copy-paste ready, but every mutating endpoint ships an empty placeholder body — 'curl -X PUT ... -d "{}"' and 'curl -X POST ... -d "{}"' — with no payload fields shown, so the commands run but accomplish nothing without fetching the OpenAPI spec. This is concrete-but-incomplete guidance rather than mostly-executable guidance.

3 / 5

Workflow Clarity

No sequence is described for any of the stated capabilities: import says 'Validate or install an RTK TOML schema v1 filter file' with no validate-then-install order, and the advertised 'test compression with real prompt samples' has no GET config → POST test → interpret-results flow. Mutating operations (PUT config, POST import) have no validation checkpoints at all. Even anchor 3's 'steps listed' bar is not met; this is a bare endpoint catalog.

2 / 5

Progressive Disclosure

Sections are organized (Overview / Authentication / Endpoints / Payloads) and payload detail is deferred to the OpenAPI spec, but the referenced 'docs/openapi.yaml' is not present in the skill bundle, and the ~90-line inline endpoint reference is content that arguably belongs in a separate reference file. Structure exists, but references are not clearly signaled and organization has gaps beyond minor.

3 / 5

Total

12

/

20

Passed

Description

55%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 communicates concrete capabilities but is written in internal jargon rather than user-facing trigger language, and it completely lacks a 'when to use this' clause. Adding natural synonyms and an explicit 'Use when...' clause would lift the two capped dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to compress prompts, shrink context, tune RTK filters, or preview how a prompt will be compressed.'

Include natural user-facing synonyms alongside the jargon — 'compress prompts', 'reduce token usage', 'context filtering' — so users' phrasing actually matches the description.

Briefly expand on what 'context relay settings' and 'context transformation pipelines' cover so the description's scope is distinguishable from other context-management skills.

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'Configure RTK filters, context engineering rules, and context relay settings', 'Test compression with real prompt samples', 'manage context transformation pipelines' — each paired with named domain objects. It falls short of 5 because coverage is not comprehensive and the actions are generic verbs attached to jargon-heavy nouns rather than fully specified capabilities.

4 / 5

Completeness

The 'what' is clear (configure, test, manage RTK/context settings), but there is no 'Use when...' clause or any equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the 'what' half is concrete and multi-part.

3 / 5

Trigger Term Quality

Relevant keywords exist ('RTK', 'compression', 'filters', 'context') but the phrasing leans on technical jargon ('context relay settings', 'context transformation pipelines') rather than the natural phrases a user would say, such as 'compress my prompt' or 'reduce token usage'. Common synonyms and variations are missing, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

'RTK' is a niche term, but broad phrases like 'context engineering rules', 'context', and 'filters' create real overlap risk with sibling context-management skills in what appears to be an API-skill suite. It is somewhat specific but could still be confused with similar context-related skills, matching anchor 3.

3 / 5

Total

13

/

20

Passed

Validation

100%

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/omni-context-rtk/SKILL.md

Reviewed

Table of Contents

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.