CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gate-check

Ready to advance between development stages? PASS/CONCERNS/NOT ASSESSED/FAIL with blockers and required artifacts. 'Can we move to production?'

Quality

77%

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 ./.claude/skills/gate-check/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

This is a well-engineered orchestrator skill: the body stays lean and routes all phase mechanics to one-level-deep reference files that all exist, with a clearly numbered workflow, mandatory confirmation, and verdict-gated writes. The only room for improvement is trimming the dense qa.level prose and the repeated compaction note. Strong result — no suggestions needed.

DimensionReasoningScore

Conciseness

The body is a lean orchestrator that assumes competence and reserves its lines for project-specific config semantics (workflow, qa.level, team.size) Claude could not know. Not 5 because the qa.level paragraph is winding and could be tightened or moved to a reference, and "Read it again if the conversation was compacted or resumed" is repeated verbatim in six sections; not 3 because there is no generic concept explanation or padding.

4 / 5

Actionability

Concrete, executable guidance throughout: an exact bash invocation for config resolution, a table mapping each gate transition to its definition file, a copy-paste confirmation prompt with option labels, and exact write targets ("set `project.stage: <new-stage>`" plus "write the new stage name to `production/stage.txt` (single line, e.g. `Production`)"). Not 5 because the core checking mechanics (Sections 2b-7) are delegated to reference files, so the body alone does not carry the executable validation steps; not 3 because what is written inline is specific and directly executable.

4 / 5

Workflow Clarity

A clearly sequenced 1-7 process (parse arguments -> tier adjustment -> run check -> assessment -> verdict -> update stage -> next steps) with explicit validation checkpoints: a mandatory user confirmation ("Do not skip this confirmation step"), a verdict-gated stage write, and a feedback loop ("the stage stays where it is until a re-run passes"). Matches the anchor's clear sequence, explicit validation, feedback loops, and checklists (per-gate checklist files).

5 / 5

Progressive Disclosure

The body is a pure overview: a table routes each gate to its definition file, and each phase section is an explicit one-line pointer ("Read references/3-run-gate-check.md now and follow it"). All 12 referenced files exist in the bundle and none reference further files, so references are exactly one level deep and clearly signaled, including re-read guidance after compaction. Not 4 because there is no organization gap to point to — the split is appropriate end to end.

5 / 5

Total

18

/

20

Passed

Description

62%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 concise and distinct, with a clear "what" and a usable trigger question, but it undersells the skill's mechanics and keyword coverage. Adding the verbs of what the skill does and broader natural trigger phrases would lift it. Suggestions target the two 3-scored dimensions.

Suggestions

Name the concrete actions the skill performs, e.g. "Validates required artifacts and quality standards against a phase-gate checklist and issues a PASS/CONCERNS/NOT ASSESSED/FAIL verdict with blockers."

Broaden trigger coverage beyond the single production example: add natural phrases users would say such as "phase gate", "readiness review", "are we ready to move to the next stage", or "sign-off".

State the when-clause explicitly across all transitions, e.g. "Use when the team asks whether the project can advance from systems design through release" rather than relying on one quoted question.

DimensionReasoningScore

Specificity

"PASS/CONCERNS/NOT ASSESSED/FAIL with blockers and required artifacts" names the output format concretely, but the description stops there — it lists only 1-2 concrete actions and omits what the skill actually does (validate artifacts, run a review panel, write the new stage). Not 4 because it does not list several specific actions; not 2 because the verdict vocabulary is concrete rather than generic.

3 / 5

Completeness

The "what" is explicit (verdict with blockers and required artifacts) and a "when" is present via the quoted question 'Can we move to production?', which functions as a concrete trigger phrase. Not 5 because the when-clause covers only a single transition example and lacks an explicit "Use when..." formulation spanning the other stage transitions; not 3 because trigger guidance is explicitly present, not merely implied.

4 / 5

Trigger Term Quality

"advance between development stages", "blockers", "required artifacts", and the quoted "Can we move to production?" are natural phrases, but common variations users would say — "phase gate", "readiness review", "sign-off", "are we ready" — are absent. Not 4 because keyword coverage is thin, not 2 because the terms present are relevant rather than generic filler.

3 / 5

Distinctiveness Conflict Risk

The four-value verdict vocabulary (PASS/CONCERNS/NOT ASSESSED/FAIL) and gate framing carve out a distinct niche compared to generic review or QA skills. Not 5 because "development stages" is broadly applicable and could mildly overlap with release-readiness or milestone-review skills; not 3 because the verdict scheme and quoted gate question are unlikely to trigger the wrong skill.

4 / 5

Total

14

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

Donchitos/Claude-Code-Game-Studios

Path

.claude/skills/gate-check/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.