CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-gate

Load to report the organization standard or adopt consumer refresh.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/review-gate/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 content is dense, operative, and well-wired: every section points to real scripts or anchored reference sections, commands are copy-paste ready, and risky operations (emergency merge) come with verification and rollback steps. The main weaknesses are the overloaded refresh-consumer table cell and refresh workflow branching that would read better as sequenced steps or a reference page.

DimensionReasoningScore

Conciseness

The body is lean and operative throughout — e.g. "Run `scripts/validate-standard.sh` for a read-only report" — with zero padding or explanation of known concepts. Not 5 because the `refresh/refresh-consumer.sh` table cell compresses ~25 operational rules into one run-on paragraph where brevity starts to sacrifice clarity.

4 / 5

Actionability

Concrete, executable commands are given: `gh pr edit <PR#> --add-reviewer @copilot`, `gh pr merge <N> --admin --match-head-commit <SHA>`, `fleet repos kendex-refresh`, plus a numbered 4-step bypass procedure. Not 5 because the `refresh/*.sh` scripts lack exact invocation syntax (arguments, checkout steps) and depend on external skill docs for orch/github paths.

4 / 5

Workflow Clarity

Validation checkpoints are explicit — "reads both rulesets back" after adding and removing bypasses, "Confirm that the arm enabled auto-merge", "Wait for GitHub to show the published head" — and error paths are enumerated ("A failed direct merge reports `refresh-error=merge`"). Not 5 because the refresh workflow's branching conditions (bypass-present vs not, armed/disarmed states) are compressed into prose and a table cell rather than a clearly sequenced step list.

4 / 5

Progressive Disclosure

The body is an overview with well-signaled, one-level-deep references to real files: [references/adoption.md](references/adoption.md) with specific section anchors (all verified present), [references/vendored-paths.md](references/vendored-paths.md), and a scripts table pointing to actual bundle scripts. Not 5 because the refresh-consumer behavior spec is inlined in a table cell rather than split to a reference, and several paths point outside the bundle (release checkout, orch/github skills).

4 / 5

Total

16

/

20

Passed

Description

46%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 two real operations but relies on organization-internal jargon, omits any 'Use when' trigger clause, and never hints that the domain is GitHub review rulesets and approvals. It is distinguishable but weak on natural discoverability.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for a report on review rulesets/required checks or wants to refresh a consumer install of kendex."

Include natural keywords users would actually say: "review rules", "approvals", "required checks", "rulesets", "merge queue", "consumer refresh".

Clarify what the "organization standard" covers (GitHub review rulesets, approval policies, review-thread resolution) instead of leaving it implicit in the body.

DimensionReasoningScore

Specificity

Names the domain and two actions — "report the organization standard" and "adopt consumer refresh" — matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. Not 4 because only two terse actions are listed with no elaboration of what the standard or refresh actually cover.

3 / 5

Completeness

A 'what' is present ("report the organization standard or adopt consumer refresh") but there is no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the guidelines. Not 2 because the 'what' names two concrete operations rather than being extremely vague; not 4 because 'when' is entirely absent.

3 / 5

Trigger Term Quality

"organization standard" and "consumer refresh" are internal jargon; a user needing this skill would more naturally say "review rules", "approvals", "rulesets" or "refresh the consumer install" — none appear. Fits anchor 2 ('One or two generic keywords; missing the natural phrases users say') rather than 3, which requires a broader set of relevant keywords.

2 / 5

Distinctiveness Conflict Risk

The niche is genuinely specific (org-standard reporting plus a named consumer-refresh flow), so overlap risk with other skills is minor — anchor 4. Not 5 because no concrete distinct trigger phrases are given and "organization standard" could superficially overlap generic standards/compliance skills.

4 / 5

Total

12

/

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

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

13

/

16

Passed

Repository

vanillagreencom/kendex

Path

skills/review-gate/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.