CtrlK
BlogDocsLog inGet started
Tessl Logo

django-verification

Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

The canonical home for this skill is tdg-personal/django-verification

SKILL.md
Quality
Evals
Security

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete commands across a well-sequenced 12-phase pipeline, but it is over-long for a single file and lacks explicit validation feedback loops for destructive steps like migrations. Splitting the CI example, output template, and detailed checklists into reference files would improve both conciseness and progressive disclosure.

Suggestions

Add explicit validation checkpoints for destructive/batch phases (e.g., 'Only run `migrate` after `migrate --plan` and `makemigrations --check` pass; stop and resolve any conflict before proceeding') to lift workflow_clarity above 2.

Move the GitHub Actions workflow, the full Output Template, and the Pre-Deployment Checklist into separate reference files (e.g., CI.md, OUTPUT_TEMPLATE.md) linked from a concise overview, reducing the inline wall of text and improving progressive_disclosure.

De-duplicate content (e.g., `python manage.py check --deploy` appears in both Phase 2 and Phase 5) and trim 'Common issues' bullets that restate knowledge Claude already has, to tighten conciseness.

DimensionReasoningScore

Conciseness

The body is largely executable commands, but ~470 lines carry redundancy (`python manage.py check --deploy` repeats in Phase 2 and Phase 5) and 'Common issues' bullets restating facts Claude knows (missing type hints, PEP 8 violations); it is mostly efficient but could be tightened, so it does not reach the lean level-3 anchor.

2 / 3

Actionability

Guidance is concrete and copy-paste ready — `pytest --cov=apps ...`, `mypy . --config-file pyproject.toml`, `ruff check . --fix`, `bandit -r . -f json` — meeting the fully-executable anchor rather than the pseudocode/incomplete level 2.

3 / 3

Workflow Clarity

Twelve phases are clearly sequenced with a closing checklist and output template, but validate→fix→retry checkpoints are mostly implicit (only 'If environment is misconfigured, stop and fix'); since migrations are destructive/batch operations lacking explicit feedback loops, workflow clarity is capped at 2 per the rubric guidance.

2 / 3

Progressive Disclosure

Sections are well organized but the skill is a monolithic ~470-line SKILL.md with the full CI workflow, output template, and per-phase checklists inline and no external reference files; content that should be split out remains inline, matching the level-2 anchor rather than the well-signaled multi-file level 3.

2 / 3

Total

9

/

12

Passed

Description

100%

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 specific, third-person, and provides both concrete capabilities and an explicit activation trigger, hitting the top anchor on every dimension. It is concise yet complete with no notable weaknesses.

DimensionReasoningScore

Specificity

Enumerates five concrete actions — 'migrations, linting, tests with coverage, security scans, and deployment readiness checks' — matching the anchor for multiple specific concrete actions, rather than the partial domain-only level 2.

3 / 3

Completeness

States what it does (verification loop with enumerated actions) and when to use it ('before release or PR'), satisfying the explicit-trigger requirement that would otherwise cap completeness at 2.

3 / 3

Trigger Term Quality

Natural user-facing terms are well covered: 'Django projects', 'migrations', 'linting', 'tests', 'security scans', 'release', and 'PR' — phrasings a developer would actually say, not jargon-only.

3 / 3

Distinctiveness Conflict Risk

Scoped tightly to 'Django projects' with framework-specific triggers (migrations, manage.py-style checks, PR/release gates), giving it a clear niche unlikely to conflict with other skills.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
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.