CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

github-repository-settings

Load to preview, render or check a repository's selected review instruction files and local review pointer.

Quality

67%

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 ./.agents/skills/github-repository-settings/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 commendably lean and provides concrete, executable commands with a clear validation vocabulary (dry-run, check, exit codes). Its weaknesses are structural: no explicit ordered workflow, a referenced settings example file absent from the bundle, and dense unsectioned paragraphs that mix operation, configuration, and dependency housekeeping.

Suggestions

Present an explicit ordered workflow (e.g. numbered steps: set GITHUB_STANDARD_CHECK_LOCATION → adopt --dry-run → adopt → render → check) so the prerequisite precedes the commands.

Ship or fix the link to kendex.settings.toml.example, since the body's "[settings example]" pointer resolves to no file in the bundle.

Add section headings (e.g. Commands, Configuration, Dependencies) to break up the five dense unstructured paragraphs, and trim non-operational notes like the KEN-2362 transition and catalog release policy into a maintenance section.

DimensionReasoningScore

Conciseness

The body is dense and lean with no padding or explanation of known concepts ("Exit codes: 0 clean, 1 findings, 2 could not complete"), but includes minor non-operational housekeeping such as the "KEN-2362" transition note and catalog release policy that could be trimmed.

4 / 5

Actionability

Four copy-paste-ready commands are given along with concrete behavior contracts ("adopt --dry-run" preview, exit codes, "--help"), but key operational detail is delegated to external files and the prerequisite setting is described only in prose, leaving minor gaps.

4 / 5

Workflow Clarity

The intended sequence (choose GITHUB_STANDARD_CHECK_LOCATION, preview with adopt --dry-run, adopt via bot-instructions, render, check) exists only implicitly across scattered paragraphs, with the prerequisite stated after the commands; validation tools exist (dry-run, exit codes, check --staged) but are not wired into an explicit ordered workflow.

3 / 5

Progressive Disclosure

References are one level deep and clearly signaled, and the referenced script exists, but "kendex.settings.toml.example" is missing from the bundle, several links point to external packages, and the body's ~25 dense lines carry only two headings with no sectioning of operational, configuration, and dependency content.

3 / 5

Total

14

/

20

Passed

Description

58%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 states three concrete actions on a specific domain, but omits any "when to use" trigger guidance and leans on project-specific jargon ("local review pointer") that users would not naturally say. It is mostly distinct from sibling skills but shares trigger vocabulary with the bot-instructions dependency.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to preview, apply, or verify GitHub repository review settings or review instruction files."

Replace or gloss project jargon ("local review pointer", "selected review instruction files") with natural user-facing terms such as "review files" or "repo review configuration".

Briefly state what each action yields (e.g. render writes outputs, check reports findings) to round out capability coverage.

DimensionReasoningScore

Specificity

"preview, render or check" names three concrete actions on a specific target ("a repository's selected review instruction files and local review pointer"), but coverage has minor gaps — what each action produces or consumes is not stated.

4 / 5

Completeness

The "what" is clear (preview, render or check review instruction files), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

"repository", "preview", "render" and "check" are natural terms, but "selected review instruction files" and "local review pointer" are project jargon users would not naturally say, and common variations or synonyms are missing.

3 / 5

Distinctiveness Conflict Risk

The niche (repository review settings) is mostly distinct, but vocabulary like "review instruction files" overlaps with the closely related bot-instructions skill, creating minor conflict risk.

4 / 5

Total

14

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 missing, 2 suspicious

Warning

Total

13

/

16

Passed

Repository

vanillagreencom/kendex

Path

.agents/skills/github-repository-settings/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.