CtrlK
BlogDocsLog inGet started
Tessl Logo

research-wiki

Operate the docs/research compiled layer in either full or maintain mode. Use for research-lane creation, research upkeep, authority-sensitive corpus work, source summaries, concepts, systems, decisions, and open-question pages.

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

85%

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

A well-structured, actionable instruction-only workflow with a clear sequenced process, a concrete evidence-ledger template, and explicit validation gates, plus sound one-level-deep references to support docs. Its weakness is conciseness: significant repetition across Core Rules, the ledger section, and Blunt Rules could be consolidated.

Suggestions

Define the eight-value disposition list once (in the Per-Corpus Evidence Ledger) and reference it from Core Rules instead of repeating it.

Merge or remove the Blunt Rules section, which restates Core Rules; keep a single authoritative rule list.

Consolidate the repeated official-source-discovery and 'exhaust strongest local raw hits' guidance, which appears in Core Rules, the Full-Mode steps, and the ledger section.

DimensionReasoningScore

Conciseness

Avoids explaining concepts Claude already knows, but carries notable redundancy: the eight-value disposition list appears in both Core Rules and Per-Corpus Evidence Ledger, the official-source-discovery and 'exhaust strongest local raw hits' rules are stated three times, and Blunt Rules restates Core Rules; it could be tightened, so not a 3.

2 / 3

Actionability

For an instruction-only skill it gives concrete, actionable guidance: a 10-step numbered process, a per-corpus evidence ledger template with nine enumerated fields, an explicit disposition vocabulary, a 'Read First' file list, and 'Before recording X, do Y' gating rules; absence of code is not penalized per the scoring notes.

3 / 3

Workflow Clarity

Provides a clearly sequenced 10-step full-mode process with explicit validation checkpoints ('Before recording raw gap, use official-source discovery to confirm...', 'Before recording evidence gap, read the strongest local raw hits...') and a completion gate requiring a disposition per scoped corpus, matching the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

The body is an overview that delegates detailed pipelines to clearly-signaled, one-level-deep support docs (full-pipeline.md, maintain.md, README/index/log) with well-organized sections; no bundle files exist to verify, but the in-body reference structure is sound and not a monolithic wall of text.

3 / 3

Total

11

/

12

Passed

Description

85%

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 specific, third-person description that cleanly answers both what and when with an explicit 'Use for' trigger clause and a distinct niche. Its main weakness is trigger-term quality: the keywords are internal vocabulary rather than the natural phrasings a user would actually say.

Suggestions

Add plain-language trigger terms a user would naturally say (e.g., 'research this topic', 'compile a research lane for X', 'summarize the sources for') alongside the internal vocabulary.

Soften reliance on jargon like 'authority-sensitive corpus work' as a primary trigger; pair each internal term with a user-facing equivalent.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('research-lane creation, research upkeep, authority-sensitive corpus work, source summaries, concepts, systems, decisions, and open-question pages'), matching the multiple-specific-actions anchor rather than the domain-plus-some-actions level below.

3 / 3

Completeness

Explicitly answers both what ('Operate the docs/research compiled layer in either full or maintain mode') and when ('Use for research-lane creation...'), with an explicit trigger clause; not a 2 because the 'when' is stated, not merely implied.

3 / 3

Trigger Term Quality

The 'Use for' clause is present but its keywords are system-internal jargon ('authority-sensitive corpus work', 'research upkeep') rather than natural user phrasings; missing common plain-user variations like 'research this topic' or 'compile a research lane' that would justify a 3.

2 / 3

Distinctiveness Conflict Risk

Targets a clearly defined niche (the docs/research compiled layer, research lanes, corpus work) with distinct triggers, making conflict with other skills unlikely.

3 / 3

Total

11

/

12

Passed

Validation

75%

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

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 7 missing, 7 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository
udecode/plate
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.