CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gates

Pick the smallest correct verification gate for a change in this repo, and prove it actually ran before calling it green. Use before running any `npm run verify:*` or `check:*` command, before reporting a gate as passing, when a gate finishes suspiciously fast or clean, and before trusting any agent or bot claim that a fix landed.

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

High-quality operational content: extremely lean, repo-specific, and actionable, with explicit validation rules and a reporting checklist. The gaps are minor — a few described-but-not-commanded operations (lease inspection, output grep) and no numbered step sequence for the check-then-report workflow.

Suggestions

Give an exact command for lease inspection (e.g., an `ls` or `cat owner.json` invocation against the documented lease directory) instead of only the path pattern, so the heavy-run precheck is copy-paste executable.

Provide the literal grep pattern for the decisive proof line (e.g., the regex matching "N passed" in Playwright output) rather than describing it, strengthening actionability.

Consider a short numbered checklist at the end of "Pick the smallest gate" tying the sections together (trap check → gate choice → run → quote decisive line → report skipped gates) to make the workflow sequence explicit.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious repo facts (exit code 75 under lock contention, lease directory layout, `verify:full` stopping at first failure, squash-merge ancestry breakage) and teaches no general concepts; the single general-knowledge aside (`${PIPESTATUS[0]}`) is a targeted trap reminder, matching the "every token earns its place" 5 anchor.

5 / 5

Actionability

Concrete commands throughout — `prettier --check`, `docs:check-links`, `test:focused -- --files <paths>`, `npm run format`, `git merge-base --is-ancestor` — plus a change-to-gate mapping table make the guidance mostly executable, but a few operations are described rather than given as commands (lease inspection gives a path pattern, the `N passed` grep has no pattern), fitting 4 rather than fully copy-paste-ready 5.

4 / 5

Workflow Clarity

A clear implicit sequence (check false-green traps → pick the smallest gate → coordinate heavy runs → respect the provider boundary → verify third-party claims → report) with explicit validation requirements ("quote the decisive line", results "void until `npm ci` has run") and a reporting checklist, but steps are never enumerated as a sequence and some checkpoints are stated as policy, fitting 4 rather than the 5 anchor's explicit sequenced validation with feedback loops.

4 / 5

Progressive Disclosure

A single ~100-line file with clear section headers, a gate table, and well-signaled one-level-deep links into repo docs (`AGENTS.md`, `pull-request-workflow.md`); however there is no bundle structure to split content into, and the gate table and lease details are borderline inline-heavy for an overview, fitting 4 rather than the 5 anchor's well-split reference files.

4 / 5

Total

17

/

20

Passed

Description

87%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.

A strong description: it states concrete actions, includes an explicit multi-clause "Use when" trigger list with natural phrasing and command patterns, and occupies a distinct niche. The only weakness is that trigger coverage misses a few common synonyms (tests, CI, lint) and the action list is narrow rather than comprehensive.

DimensionReasoningScore

Specificity

"Pick the smallest correct verification gate" and "prove it actually ran before calling it green" name several concrete actions, but coverage centers on one core behavior rather than comprehensively enumerating capabilities, matching the 4 anchor (several specific actions, minor gaps) rather than the comprehensive 5.

4 / 5

Completeness

It explicitly answers both "what" (pick the smallest correct gate, prove it ran before calling it green) and "when" via a four-clause "Use before..." trigger list with concrete trigger phrases, matching the 5 anchor exactly and clearly exceeding the 4 anchor's less-explicit "when".

5 / 5

Trigger Term Quality

Natural phrases like "reporting a gate as passing", "suspiciously fast or clean", and "agent or bot claim that a fix landed" plus concrete command patterns (`verify:*`, `check:*`) give good keyword coverage, though common synonyms such as "tests", "CI", or "lint" are missing, keeping it below the 5 anchor's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"for a change in this repo" with `verify:*`/`check:*` command triggers carves out a clear repo-specific niche with distinct triggers and minimal conflict risk against generic testing or code-review skills, fitting the 5 anchor.

5 / 5

Total

18

/

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

relative_links

Relative link issues: 2 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 possibly missing (scripts/run-playwright.mjs)

Warning

Total

14

/

16

Passed

Repository

BigSimmo/PsychSift

Path

.claude/skills/gates/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.