CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

preflight

Load to run, tune, or debug preflight.

Quality

72%

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/preflight/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

93%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 an exemplary lean skill body: executable commands covering all three scopes, unambiguous placement guidance, a concrete remediation rule, and well-signaled one-level references that are real files in the bundle. The only minor gap is that the fix-findings feedback loop lacks an explicit re-run checkpoint.

DimensionReasoningScore

Conciseness

The ~30-line body is lean and efficient: "Run preflight in the validate step, before the project's own validation command", three one-line command examples, one behavioral rule ("Fix what a finding reports; never widen a lane's exclusions to clear it"), and pointers to `--help` and two reference files. No padding, no explanations of concepts Claude already knows — every token earns its place.

5 / 5

Actionability

Three copy-paste-ready commands cover the common scopes (default merge-base, `--staged`, `--all`) with inline comments explaining each, plus a concrete remediation rule and exact pointers for the rest (`preflight --help`, references/lanes.md, references/wiring.md). Fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

Placement is unambiguous ("Run preflight in the validate step, before the project's own validation command") and remediation direction is explicit ("Fix what a finding reports"), but the fix → re-run feedback loop is only implied — there is no "re-run until it passes" checkpoint, and exit codes are deferred to `--help`. Fits "Clear sequence with most checkpoints present; minor validation gaps"; not a 5 because the error-recovery loop is not explicit, and the operation is read-only checking so no destructive/batch cap applies.

4 / 5

Progressive Disclosure

The body is a clear overview with well-signaled, one-level-deep references that verifiably exist in the bundle: lanes/settings/exit codes live in `preflight --help`, diff construction and glob grammars in [references/lanes.md](references/lanes.md), and hook/CI wiring in [references/wiring.md](references/wiring.md) — each reference annotated with what it contains. No nesting, no inlined bulk content; scripts/ and scripts/lib hold the implementation as expected.

5 / 5

Total

19

/

20

Passed

Description

40%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 minimal: it names the skill's domain and three generic actions but never states what preflight does or gives explicit trigger guidance. Distinctiveness is decent by virtue of the tool name, but specificity and completeness are weak for a user deciding whether to load this skill.

Suggestions

State what the skill does concretely, e.g. "Runs diff-scoped validation lanes (unwired test suites, data syntax, edited migrations) against changed lines; fix findings without widening lane exclusions."

Add an explicit trigger clause: "Use when running the project's validate step, wiring preflight into a pre-commit hook or CI, or when a preflight finding or exit code needs debugging."

Include natural trigger terms users would actually say — "preflight", "validate step", "pre-commit", "CI checks", "preflight failed" — to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description is "Load to run, tune, or debug preflight." — it names the domain (preflight) but the actions ("run, tune, or debug") are generic verbs, and it never states what preflight actually does (diff-scoped validation). This matches the anchor "Names the domain but actions are minimal or generic"; it is not a 3 because no concrete capability (e.g., what lanes it checks, what it validates) is stated, and not a 1 because the domain is named.

2 / 5

Completeness

"Load to run, tune, or debug preflight" gives only a vague 'what' (it never says preflight validates changes) and no explicit 'Use when...' clause — the 'when' is only weakly implied by "Load to". Matches "Has a vague 'what' and no 'when'"; the missing-trigger clause caps completeness at 3, and the unstated 'what' pushes it below that to 2.

2 / 5

Trigger Term Quality

Terms present: "run", "tune", "debug", "preflight" — a user who knows the tool would naturally say these, but there are no synonyms or contextual terms (validate, checks, findings, pre-commit, CI). Fits "Some relevant keywords but missing common variations or synonyms"; better than a 2 ("one or two generic keywords") because three natural action phrases plus the tool name are present.

3 / 5

Distinctiveness Conflict Risk

"preflight" is a distinct tool name, so conflict risk with other skills is low, but the bare word is ordinary English (e.g., deployment preflight checks) and the description offers no qualifying triggers. Fits "Mostly distinct; minor overlap risk with closely related skills"; not a 5 because there are no distinct trigger phrases to fully disambiguate.

4 / 5

Total

11

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

vanillagreencom/kendex

Path

.agents/skills/preflight/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.