django-celery

Django + Celery async task patterns — configuration, task design, beat scheduling, retries, canvas workflows, monitoring, and testing. Use when adding background jobs, scheduled tasks, or async processing to a Django app.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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.

Highly actionable, executable content with excellent error-handling patterns and a clear production checklist. Its main weakness is structural: it is a monolithic 450-line document with no progressive disclosure, inlining detailed material (canvas, testing, DB schedules) that belongs in one-level-deep reference files.

Suggestions

Split detailed material into one-level-deep reference files (e.g., references/canvas.md for chain/group/chord workflows, references/testing.md for eager-mode and retry tests) and keep SKILL.md as a concise overview with clearly signaled links, as the body currently inlines ~450 lines with zero references.

Add an explicit verification checkpoint to the setup workflow (e.g., after starting the worker, run `celery -A config inspect ping` or send the debug_task and confirm it executes) so configuration errors are caught before tasks are enqueued.

Trim redundancy: the anti-patterns section repeats the idempotent-guard pattern already shown in 'Idempotent Task Pattern' — replace it with a cross-reference, and cut the debug_task boilerplate that is not needed by consumers of the skill.

Dimension	Reasoning	Score
Conciseness	The body is code-dominated with terse, load-bearing comments ("Prevent worker hoarding long tasks", "Re-queue on worker crash") and no explanations of concepts Claude already knows, but minor redundancy remains — the anti-patterns section restates the idempotent pattern and the debug_task boilerplate could be trimmed — matching anchor 4 (efficient, minor instances that could be trimmed) rather than the fully lean anchor 5.	4 / 5
Actionability	Every section contains copy-paste-ready, executable material: install commands, complete celery.py and settings blocks, worker/beat/flower CLI commands, and runnable task code covering the common cases (basic, retry with backoff, idempotent guard, soft-time-limit cleanup, canvas, dead-letter queue, eager tests), matching the anchor-5 fully-executable pattern.	5 / 5
Workflow Clarity	The setup flows install → celery.py → settings → run-worker with clear sequencing, error-recovery feedback (SoftTimeLimitExceeded cleanup before hard kill, retry/backoff, dead-letter persistence after max retries) and a production checklist, but the setup workflow has no explicit verification checkpoint (e.g., confirming worker connectivity via celery inspect) and batch group/chord operations lack a validation step, matching anchor 4 (most checkpoints present, minor validation gaps).	4 / 5
Progressive Disclosure	There are no bundle files and all ~450 lines are inlined in SKILL.md; it is well-sectioned, but content that clearly belongs in separate reference files — canvas workflow detail, the full testing patterns, database-defined schedule management — is inline, matching anchor 3 (some structure, but content that should be separate is inline) rather than anchor 4, which expects most content appropriately split with clear references.	3 / 5
	Total	16 / 20 Passed

Description

92%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 that explicitly states both capabilities and activation triggers in the third person, with a well-defined niche. The only weakness is missing common synonyms (task queue, periodic tasks, cron) that users might naturally say.

Dimension	Reasoning	Score
Specificity	"configuration, task design, beat scheduling, retries, canvas workflows, monitoring, and testing" lists multiple specific concrete capabilities with comprehensive coverage of the Django+Celery domain, matching the anchor-5 example's breadth; no coverage gaps would justify a 4.	5 / 5
Completeness	Both parts are explicit: what ("Django + Celery async task patterns — configuration, task design, beat scheduling, retries, canvas workflows, monitoring, and testing") and when ("Use when adding background jobs, scheduled tasks, or async processing to a Django app") with concrete trigger phrases, exactly matching the anchor-5 example.	5 / 5
Trigger Term Quality	Natural phrases like "background jobs", "scheduled tasks", and "async processing" are present, but common synonyms users would say — "task queue", "periodic tasks", "cron", "workers" — are missing, which is the anchor-4 pattern (good coverage, a few natural terms missing) rather than the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The description is pinned to the narrow "Django + Celery" niche with distinct triggers (beat scheduling, canvas workflows, task retries), so it would not fire for generic Django, Python, or async skills; this is the anchor-5 "clear niche with distinct triggers" case.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/django-celery/SKILL.md
Commit: c70874f

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.