CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

para-vault

Use this skill when the user asks to "file this note into PARA", "process vault inbox", "organize my PARA vault", "reconcile vault documents", "propose note revision", "archive this project", "reactivate archived note", "check vault navigation", "repair broken MOC links", or "import calendar/email records into vault". Covers the full PARA knowledge lifecycle (Projects, Areas, Resources, Archives). Do NOT use this skill for raw filesystem moves outside a PARA vault (use `manage-file-operations`) or drafting user communications (use `write-like-me`).

Quality

81%

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

The canonical home for this skill is para-vault in NyssaAI/agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

60%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 well-designed as a facade — lean, clearly routed, with strong invariants and a real verification checklist — but its progressive disclosure is broken in practice: every primary workflow reference is a dead path and the existing reference files are orphaned. This also drags actionability down, since the concrete runbooks the whole document routes to are absent.

Suggestions

Create the five referenced `workflows/*.md` files (or correct the paths to wherever the runbooks live) so the triage matrix and architecture diagram route to real targets.

Link the existing `references/` files (e.g., classification.md, lifecycle.md, navigation.md, revisions.md, source-records.md) from the body so their content is discoverable instead of orphaned.

Inline a minimal concrete step sequence for the most common operation (e.g., inbox filing classification order with frontmatter checks) so the skill remains actionable even if a workflow file is unavailable.

DimensionReasoningScore

Conciseness

The ~50-line body is lean, assumes PARA knowledge, and avoids padding, but the ASCII architecture tree and the triage matrix encode the same five routing targets twice, so a few tokens could be trimmed — anchor 4 rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Concrete directives exist (strict Projects→Areas→Resources→Archives evaluation order, preserving .eml/.ics payloads, lifecycle fields `status`/`completed`/`archived-from`), but the executable procedures are delegated to five `workflows/*.md` files that do not exist in the bundle, so the specific steps to execute are missing — anchor 3's 'some concrete guidance but incomplete'.

3 / 5

Workflow Clarity

The three-phase lifecycle sequence and triage matrix give a clear routing flow, and the closing verification checklist supplies explicit checkpoints (schema conformance, link integrity, bit-for-bit evidence) appropriate to destructive/batch vault operations. It is not anchor 5 because per-runbook step sequencing and error-recovery feedback loops are absent from the body and their intended home (the workflow files) is missing.

4 / 5

Progressive Disclosure

Scored against the actual bundle: all five primary routing references (`workflows/file.md`, `reconcile.md`, `archive.md`, `navigate.md`, `import-records.md`) point to files that do not exist, and the eight real `references/` files (classification.md, lifecycle.md, navigation.md, etc.) are never linked from the body, leaving navigation broken and the bundle's content undiscoverable — anchor 2 territory rather than 3, since the problem is unresolvable references, not just imperfect organization.

2 / 5

Total

13

/

20

Passed

Description

95%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: explicit what/when with ten natural trigger phrases, explicit exclusion boundaries, and clean delegation to adjacent skills. The only minor weakness is that concrete capabilities are conveyed through quoted user requests rather than a direct action list.

DimensionReasoningScore

Specificity

Concrete actions are enumerated via quoted request phrases ("file this note into PARA", "reconcile vault documents", "repair broken MOC links", "import calendar/email records") covering the lifecycle, but the capability statement itself ("Covers the full PARA knowledge lifecycle") is generic, leaving minor gaps versus anchor 5's direct, comprehensive action list.

4 / 5

Completeness

Both what ("Covers the full PARA knowledge lifecycle (Projects, Areas, Resources, Archives)") and when (explicit "Use this skill when the user asks to..." with concrete trigger phrases) are clearly present, plus explicit negative boundaries; this matches anchor 5 rather than anchor 4, whose 'when' is less explicit.

5 / 5

Trigger Term Quality

Ten natural user-voice trigger phrases are quoted verbatim, including domain synonyms users of a PARA vault would actually say ("process vault inbox", "archive this project", "reactivate archived note", "repair broken MOC links"), matching anchor 5's comprehensive natural-term coverage.

5 / 5

Distinctiveness Conflict Risk

Clear PARA-vault niche with distinct triggers, and the "Do NOT use this skill for..." clause explicitly delegates overlapping cases to `manage-file-operations` and `write-like-me`, minimizing conflict risk as in anchor 5.

5 / 5

Total

19

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 5 missing

Warning

Total

15

/

16

Passed

Repository

NyssaAI/agent-skills

Path

.agents/plugins/agent-skills/skills/para-vault/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.