CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

wiki-mode

Read or configure the vault filing methodology and suggest destinations for planned knowledge creation under Generic, LYT, PARA, or Zettelkasten. Use for wiki mode, methodology mode, what is my vault mode, set vault mode, switch to PARA, use LYT, Zettelkasten setup, change mode, configure mode, or methodology routing. This skill does not save content or migrate notes.

68

Quality

85%

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

75%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.

A well-built instruction-only skill body: concrete commands, a validated dry-run-then-apply transaction workflow with hash-pinned approval, fail-closed handling of corrupt configuration, and clearly signaled references. The main improvements are deduplicating the repeated no-migration guarantees, specifying the actual repair command for invalid mode.json, and showing how the approval hash is derived.

Suggestions

State the no-migration guarantee once (e.g., in the intro) and reference it thereafter; it is currently repeated across the intro, the routing section, and the Change mode section.

Replace "repair it through a reviewed configuration operation" with the concrete command or procedure to run when .vault-meta/mode.json is invalid, since the fail-closed path is currently unactionable.

Show how approved_plan_sha256 is obtained from the dry-run preview output (e.g., which field to copy), completing the copy-paste chain for the apply command.

DimensionReasoningScore

Conciseness

The body is dense and command-first with useful tables, but the no-migration guarantee is repeated three times ("It does not write knowledge pages or move existing notes", "Never bulk-create folders, move notes...", "switching mode never rewrites existing notes" plus the migration-needs-a-plan statement appearing twice), and the advisory Checkpoint section is mildly padded. This is efficient-with-minor-trim, matching anchor 4 rather than the every-token-earns-its-place lean of anchor 5.

4 / 5

Actionability

Concrete, mostly copy-paste-ready bash commands cover get/config/route and the dry-run-then-apply mode change with full flags and hash pinning. Two gaps hold it below anchor 5: the invalid-mode.json path says only "repair it through a reviewed configuration operation" with no command, and how "approved_plan_sha256" is obtained from the preview is not shown.

4 / 5

Workflow Clarity

The mode change is a numbered six-step sequence with explicit checkpoints: dry-run preview first, pinned UTC timestamp and operation ID, "Copy its approved_plan_sha256 only after review", and apply by regenerating the exact plan — validation is present, so the destructive/batch cap does not apply. It falls short of anchor 5 because there is no explicit error-recovery loop (e.g., what to do on hash mismatch or a failed apply) and the fail-closed repair procedure is left vague.

4 / 5

Progressive Disclosure

A well-sectioned ~116-line overview with clearly signaled, one-level-deep references (seven template links and the operation-transactions contract), each annotated with when to use it. No bundle files exist in references/scripts/assets to back the referenced paths, and the transaction-workflow detail is inlined, which leaves minor organization gaps consistent with anchor 4 rather than the fully well-split structure of anchor 5.

4 / 5

Total

16

/

20

Passed

Description

91%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: it states concrete capabilities in third person, includes an explicit and richly varied "Use for" trigger list, and closes with a clear boundary statement. The only weaknesses are the slightly abstract "suggest destinations for planned knowledge creation" phrasing and a couple of generic trigger terms ("change mode", "configure mode").

DimensionReasoningScore

Specificity

Names the domain ("vault filing methodology") and three concrete actions ("Read or configure", "suggest destinations") across the four named methodologies, which goes beyond the 1-2 actions of anchor 3; however "suggest destinations for planned knowledge creation" is less concrete than the fully enumerative actions in anchor 5.

4 / 5

Completeness

It explicitly answers both "what" ("Read or configure the vault filing methodology and suggest destinations...") and "when" (an explicit "Use for..." clause with concrete trigger phrases), and adds a boundary statement ("This skill does not save content or migrate notes").

5 / 5

Trigger Term Quality

The "Use for" clause lists many natural user phrasings with synonym variations ("wiki mode", "what is my vault mode", "set vault mode", "switch to PARA", "use LYT", "Zettelkasten setup", "change mode", "configure mode", "methodology routing"), matching the comprehensive synonym coverage of anchor 5; file extensions are inapplicable to this domain.

5 / 5

Distinctiveness Conflict Risk

Distinct niche triggers like "use LYT", "Zettelkasten setup", and "switch to PARA" give it a clear niche, but the generic phrases "change mode" and "configure mode" carry minor overlap risk with other mode-configuring skills, keeping it just below anchor 5.

4 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 6 missing, 6 deeper-than-1-level, 1 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository

AgriciDaniel/claude-obsidian

Path

skills/wiki-mode/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.