vault-memory-workflow

Commands, architecture conventions, known gotchas, and testing patterns for working in the vault-memory Python daemon repository (FastAPI + Click + Postgres/Weaviate, pytest with mocked heavy deps).

Quality

63%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/vault-memory-workflow/SKILL.md

Quality

Content

68%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.

The body is a lean, highly actionable development-workflow reference with concrete commands and code idioms and clean section structure. Its main weakness is workflow_clarity: it flags destructive vault writes and bulk cleanup but provides no explicit validate→fix→retry feedback loop for those operations.

Suggestions

Add an explicit validation feedback loop for risky operations, e.g. after vault-relative writes run the path-safety check, and after bulk cleanup assert the _cleanup_task handle is None and re-run pytest --basetemp .pytest_tmp.

Promote the loose verify sequence into a short numbered checklist (syntax check → targeted tests → full suite → 'passed + skipped = green') so the workflow is explicit rather than implied.

Replace template placeholders in commands/snippets (tests/test_<file>.py, <domain>_router) with at least one concrete worked example to lift actionability toward fully copy-paste-ready.

Dimension	Reasoning	Score
Conciseness	The body is dense and reference-style, assuming Claude knows FastAPI/pytest with no concept over-explanation; nearly every line is actionable knowledge, with only minor explanatory asides that could be trimmed, fitting anchor 4 rather than the fully lean anchor 5.	4 / 5
Actionability	Provides copy-paste-ready commands (py_compile, pytest invocations) and concrete code idioms for DI, route files, and test patterns covering common cases, but some snippets are idiom fragments with template placeholders (e.g. tests/test_<file>.py, <domain>_router) rather than complete runnable programs.	4 / 5
Workflow Clarity	A loose verify sequence exists (syntax check then pytest, with 'passed + skipped = green' as a pass criterion) but there are no explicit validation checkpoints or fix→retry feedback loops for the destructive/batch operations the skill itself flags (vault writes via _safe_vault_path, bulk _cleanup_task); the missing-feedback-loop caveat caps this at 3.	3 / 5
Progressive Disclosure	No bundle files exist and the skill is self-contained with well-organized sections (What this repo is, Commands, Architecture conventions, Known gotchas, Testing patterns); content is appropriately inline with good structure, though a fair amount of reference material is inlined rather than split out.	4 / 5
	Total	15 / 20 Passed

Description

57%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 highly specific to its target repo and stack, making it very distinct, but it lists content categories rather than concrete actions and entirely omits an explicit 'when to use' trigger clause. Adding a 'Use when…' clause and reframing categories as actions would raise the capped dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when working in the vault-memory repository: running tests, adding routes, fixing CI, or touching the DI/dependency layer.'

Reframe the category list as concrete actions ('run the pytest suite', 'add a daemon route', 'wire DI dependencies', 'write a route test') to lift specificity from content areas to actionable verbs.

Add common natural synonyms users would say ('vault-memory tests', 'daemon route', 'pytest conftest') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and four concrete content categories ('Commands, architecture conventions, known gotchas, and testing patterns') plus the full stack, but these are content areas rather than concrete executable actions, fitting anchor 3 better than 4.	3 / 5
Completeness	Provides a clear 'what' (commands/conventions/gotchas/testing patterns for the vault-memory repo) but no explicit 'when to use it' clause; per the judging guideline a missing 'Use when…' caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant technical keywords ('vault-memory', 'FastAPI', 'Click', 'Postgres/Weaviate', 'pytest') a user in this repo would reference, but lacks the natural 'Use when…' trigger phrases users say to invoke the skill.	3 / 5
Distinctiveness Conflict Risk	Tightly scoped to a named repository with its full technology stack, giving it a clear niche with minimal conflict risk against any other skill.	5 / 5
	Total	14 / 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: pvnkmnk/vault-memory
Path: .agents/skills/vault-memory-workflow/SKILL.md
Commit: 8171052

Reviewed: 2 days 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.