CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

app-deploy

Load when asked to cut, ship, or release a kendex version.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/app-deploy/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 exceptionally lean and dense with project-specific, executable rules — near-ideal token efficiency and actionability for an expert-facing operations skill. Its weaknesses are structural: the end-to-end release sequence lives entirely in an external file, and large topic blocks that belong in reference files are inlined in the always-loaded SKILL.md.

Suggestions

Add a short numbered release sequence in SKILL.md (choose version per CHECKS.md rule -> dispatch per workflows/release.md -> move/verify major tag -> confirm publication) with the existing validation checkpoints placed in order, so the multi-step process is coherent without opening the external file.

Move the catalog-compatibility and pre-release/main-channel detail into a reference file (e.g., references/catalog-compatibility.md, references/channels.md) and keep one-line pointers in SKILL.md, keeping the main file a lean overview.

Ensure workflows/release.md and the other referenced paths actually ship in the skill bundle — none are present alongside SKILL.md, leaving the primary instruction unverifiable.

DimensionReasoningScore

Conciseness

The body is a compressed rulebook: every sentence carries project-specific rules, exact commands, or file paths, with zero explanation of concepts Claude already knows and no padding (e.g., "install.sh rests on TLS to kendex.ai and github.com alone, because a fresh machine holds neither the release key nor minisign"). It fully assumes competence — a clean match for anchor 5.

5 / 5

Actionability

Concrete, executable guidance dominates: exact commands ("git rev-parse v<version>^{commit}", "git ls-remote --tags origin v<major>", "tools/guard --released-packages") and exact paths ("crates/core/src/engine/desired.rs", "RETIRED_HOOKS"). It stops short of anchor 5 because the core cut-a-release procedure is deferred to workflows/release.md rather than carried inline, leaving a gap in copy-paste-ready coverage of the main case.

4 / 5

Workflow Clarity

Explicit validation checkpoints exist ("require the returned SHA to equal <SHA>", "Stop on a failed source, ancestry, tree, changelog or tag check", "If GitHub refuses creation, stop and report"), but the release process itself has no sequenced steps in this body — it is organized by concern (major tag, channels, secrets, catalog) with the actual sequence delegated to workflows/release.md. That matches anchor 3 (sequence present but incomplete/implicit) rather than 4, which expects a clear end-to-end sequence.

3 / 5

Progressive Disclosure

References are clearly signaled and one level deep ("To cut a release, follow [workflows/release.md]", CHECKS.md, changelog.d/README.md, DEVELOPMENT.md), but no bundle files exist alongside SKILL.md to verify workflows/release.md ships, and heavy specialized detail (three dense catalog-compatibility paragraphs, pre-release/main-channel internals) is inlined in SKILL.md where a leaner overview with split-out references would fit. This lands on anchor 3 (content that should be separate is inline; organization present but improvable).

3 / 5

Total

15

/

20

Passed

Description

65%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 is a strong, explicit trigger clause with good synonym coverage and a clearly bounded niche, but it functions purely as a 'when' statement. It never states what the skill actually does, delegating that to the summary field.

Suggestions

State the skill's concrete actions in the description itself (e.g., "Releases a kendex version: bumps versions, finalizes the changelog, dispatches the main workflow, and reviews its publication. Use when asked to cut, ship, or release a kendex version.") so both 'what' and 'when' are explicit.

Add natural trigger synonyms such as "publish" or "roll out" to broaden keyword coverage for users who phrase release requests differently.

DimensionReasoningScore

Specificity

The description names the domain and one action — "release a kendex version" — but lists no concrete capabilities of the skill (version bumping, changelog finalization, workflow dispatch appear only in the separate summary field). It matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) rather than 4, which expects several specific actions enumerated.

3 / 5

Completeness

The 'when' is fully explicit ("Load when asked to cut, ship, or release a kendex version") but the 'what' is only weakly implied through the trigger clause's object; the skill's actual actions are not stated in the description field. This is the mirror of anchor 3 (clear what, weak when), and below anchor 4, which requires both what and when with the what actually described.

3 / 5

Trigger Term Quality

"cut, ship, or release a kendex version" gives good natural-phrase coverage of the main synonyms a user would say. It falls short of anchor 5 because common variants like "publish" or "roll out" a version are missing ("publish" is notable since the skill body itself discusses publication).

4 / 5

Distinctiveness Conflict Risk

"kendex version" is a highly specific niche with distinct trigger verbs (cut, ship, release), so conflict risk with unrelated skills is minimal. The only conceivable overlap is with a sibling deploy skill (npm-deploy), which the description does not touch.

5 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 possibly missing (workflows/release.md), 5 suspicious

Warning

Total

14

/

16

Passed

Repository

vanillagreencom/kendex

Path

.agents/skills/app-deploy/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.