CtrlK
BlogDocsLog inGet started
Tessl Logo

manifest

Install and configure the Manifest observability plugin for your agents. Use when setting up telemetry, configuring API keys, or troubleshooting the plugin.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

The canonical home for this skill is manifest in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

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.

A well-structured, highly actionable setup guide with executable commands, validation, and troubleshooting. Weaker spots are the stop/install step inconsistency and some redundancy between the trigger, steps, and best-practices sections.

Suggestions

Reconcile Step 5: after 'claude gateway stop' in Step 1, the final step should start (not install) the gateway, or clarify that 'gateway install' also starts it.

Make the Step 6 failure branch explicit — point directly to the Troubleshooting table rows rather than 'check the error messages and troubleshoot'.

Drop 'Best Practices' entries that restate existing steps (stop-before-config, mnfst_ format) to reduce redundancy.

DimensionReasoningScore

Conciseness

Mostly lean with executable commands and minimal concept explanation, but the 'Best Practices' and 'Use this skill when' sections repeat information already stated in the steps and description and could be trimmed.

4 / 5

Actionability

Fully copy-paste-ready bash commands for every step plus a concrete troubleshooting table and two worked examples covering the common basic and custom-endpoint cases.

5 / 5

Workflow Clarity

A clear ordered six-step sequence with a verification checkpoint (log grep for the pipeline-active string) and key-format validation, but Step 5 says 'claude gateway install' after Step 1's 'claude gateway stop', which reads as an install/start inconsistency, and the failure branch ('check the error messages and troubleshoot') is vague.

4 / 5

Progressive Disclosure

Well-organized with clear section headers and no unnecessary external references for a self-contained setup skill, though the modest length and slight redundancy leave minor organization gaps.

4 / 5

Total

17

/

20

Passed

Description

87%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.

A strong description that clearly states both capability and trigger conditions with concrete, natural terms. The main weakness is second-person voice ('your agents'), which the rubric penalizes on specificity.

Suggestions

Rewrite in third person to avoid the specificity penalty: e.g. 'Installs and configures the Manifest observability plugin for agents.'

Add a natural synonym such as 'monitoring' to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Install and configure', 'setting up telemetry', 'configuring API keys', 'troubleshooting the plugin' — giving comprehensive coverage of the skill's scope; reduced by 1 from a base of 5 because the second-person phrasing 'for your agents' violates the third-person voice guideline.

4 / 5

Completeness

Explicitly answers both what ('Install and configure the Manifest observability plugin') and when ('Use when setting up telemetry, configuring API keys, or troubleshooting the plugin') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user-facing terms ('telemetry', 'API keys', 'troubleshooting', 'observability') that a user would plausibly say, though common synonyms like 'monitoring' or 'logging' are absent.

4 / 5

Distinctiveness Conflict Risk

The named 'Manifest' platform and plugin niche give it a clear, distinctive trigger surface with minimal overlap risk against generic observability skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.