CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deploy

Review PsychSift deployment configuration, environment parity, build and boot behavior, workers, migrations, health checks, and rollback readiness. Use for deployment changes, hosting configuration, runtime failures, or production setup.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

An extremely lean, well-sequenced safety-conscious procedure whose main weakness is actionability: it tells Claude what to examine and gate but never names concrete manifests, commands, or check definitions to execute. A short feedback loop for failed checks would also strengthen the workflow.

Suggestions

Name the concrete artifacts to inspect (e.g., Procfile, heroku.yml, docker-compose.yml, CI workflow files) and give example commands for the static config, offline build/boot, and environment-parity checks in step 3.

Define what the 'checks selected by risk' actually are, or move the per-risk check list into a references/ file and link it from step 3.

Add an explicit feedback loop: when a step-3 check or step-4 compatibility check fails, state that Claude should diagnose, fix, and re-run the check before reporting blockers in step 6.

DimensionReasoningScore

Conciseness

Six terse numbered lines with zero padding and no explanation of concepts Claude already knows — every token ("without printing secrets", "approval-required", "exact gated deployment action") earns its place.

5 / 5

Actionability

Steps like "Run static config, offline build/boot, and environment-parity checks selected by risk" are high-level hints: no commands, no named manifests or file paths (e.g., Procfile, heroku.yml, docker-compose.yml), and no definition of what the checks actually are, so the specific steps to execute are missing.

2 / 5

Workflow Clarity

The 1–6 sequence is coherent (map → inspect → check → verify ordering → gate → report) with written checkpoints (step 3 checks, step 6 reports proof/blockers, step 5 gates live actions), but there is no explicit fix-and-re-run feedback loop when a check fails.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files (references/, scripts/, assets/ are absent), and its single heading plus well-ordered numbered procedure is appropriately organized for a skill this size, so no external references are needed.

5 / 5

Total

16

/

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 in third-person voice that clearly states a comprehensive set of review responsibilities and an explicit 'Use for' trigger clause. The only weakness is that all capabilities hang on one verb and a few natural synonyms (release, outage, pipeline) are absent.

DimensionReasoningScore

Specificity

"Review PsychSift deployment configuration, environment parity, build and boot behavior, workers, migrations, health checks, and rollback readiness" names seven concrete review areas, but relies on the single verb "Review" rather than multiple distinct actions, leaving minor gaps versus the comprehensive multi-action anchor.

4 / 5

Completeness

The description explicitly answers both questions: what it does ("Review PsychSift deployment configuration, environment parity, build and boot behavior, workers, migrations, health checks, and rollback readiness") and when to use it ("Use for deployment changes, hosting configuration, runtime failures, or production setup") with concrete trigger phrases.

5 / 5

Trigger Term Quality

"deployment changes", "hosting configuration", "runtime failures", "production setup", "migrations", and "rollback" are natural phrases a user would say, but common synonyms like "release", "outage", or "deploy pipeline" are missing.

4 / 5

Distinctiveness Conflict Risk

"PsychSift deployment configuration" carves out a clear project-specific niche with distinct deployment/hosting/rollback triggers, so conflict risk with other skills is minimal.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

BigSimmo/PsychSift

Path

.agents/skills/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.