CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-gate

Load to report the organization standard or adopt consumer refresh.

Quality

65%

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 ./.agents/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 body is a lean, command-dense operational guide with real, verifiable one-level references and an exemplary numbered bypass procedure including read-back validation. Its main weaknesses are the overloaded refresh-consumer.sh table cell that packs a branching workflow into prose, and one underspecified step (the ruleset-bypass API call).

Suggestions

Move the refresh/refresh-consumer.sh branching behavior out of the scripts table into references/adoption.md (or a dedicated reference) as a numbered sequence, leaving a one-line purpose in the table.

Make the bypass step executable: give the actual API call (e.g. the `gh api` PUT/PATCH for adding a bypass actor to a required-checks/merge-queue ruleset) instead of 'through the API'.

Fix the heading glitch '## 4. Operations' (there are no sections 1-3) and give sections consistent titles so navigation is unambiguous.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — no space is spent explaining known concepts — but the ~250-word refresh/refresh-consumer.sh table cell inlines operational detail that could be trimmed or moved, matching 'efficient; minor instances that could be trimmed' rather than the fully lean anchor 5.

4 / 5

Actionability

Concrete copy-paste commands appear throughout (`scripts/validate-standard.sh`, `fleet repos kendex-refresh`, `gh pr edit <PR#> --add-reviewer @copilot`, `gh pr merge <N> --admin --match-head-commit <SHA>`, `approval-wait <PR#> --request-review --base-checkout PATH`), but the ruleset-bypass step says only 'through the API' with no actual command, a minor gap that keeps it below 5.

4 / 5

Workflow Clarity

The emergency-merge procedure is a numbered sequence with explicit validation checkpoints ('reads both rulesets back' after both add and remove, record on the work item), while the refresh flow's checkpoints (wait for published head, confirm the arm) are present but buried in a conditional prose wall — clear sequence with most checkpoints, minor clarity gaps.

4 / 5

Progressive Disclosure

The body is an overview with one-level-deep, well-signaled references to real bundle files (references/adoption.md with working § anchors for all four cited sections, references/vendored-paths.md) and a scripts table; minor gaps — the refresh-consumer.sh cell inlines detail belonging in a reference, and the stray '## 4. Operations' numbering breaks section organization.

4 / 5

Total

16

/

20

Passed

Description

42%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 what the skill does in two short jargon-heavy clauses but gives no trigger guidance and few natural keywords, so a user (or Claude) would struggle to know when to invoke it. It reads as an internal label rather than an invitable capability statement.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when checking repository review configuration (rulesets, required checks, stale-approval dismissal) or refreshing a consumer install of this package.'

Replace internal jargon with concrete natural terms users would say: 'review rulesets', 'required checks', 'branch protection', 'refresh consumer install' instead of 'organization standard' and 'consumer refresh'.

List the concrete capabilities (run a read-only ruleset report, dispatch scheduled/manual refresh, request Copilot review) so the 'what' is comprehensive rather than two abstract verbs.

DimensionReasoningScore

Specificity

The description names two actions ("report the organization standard", "adopt consumer refresh") plus the loading behavior, matching the '1-2 concrete actions' anchor; it stays at 3 rather than 4 because the action objects are internal jargon rather than several specific, comprehensible capabilities.

3 / 5

Completeness

A 'what' is stated (report the organization standard, adopt consumer refresh) but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3; it is not 2 because the 'what' is present and only mildly vague.

3 / 5

Trigger Term Quality

Only jargon terms appear ("organization standard", "consumer refresh", "report") — phrasing users would naturally say when needing this skill (e.g. review rulesets, required checks, branch protection, refreshing an install) is missing, matching the 'one or two generic keywords' anchor rather than 3 where some relevant natural keywords exist.

2 / 5

Distinctiveness Conflict Risk

The niche (org-standard reporting plus consumer refresh for this package) is somewhat specific, but abstract wording like "report the organization standard" could overlap with generic reporting or standards-related requests; not 4 because the triggers are not distinctive enough to rule out overlap with similar skills.

3 / 5

Total

11

/

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

.agents/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.