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.

Quality

70%

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/research-wiki/SKILL.md

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 has a clear structure with strong sequencing and genuine validation checkpoints for full-mode passes. Its weaknesses are substantial internal repetition and operational detail (ledger spec, disposition taxonomy) that duplicates the support docs instead of trusting them.

Suggestions

State each full-mode requirement once: merge the overlapping directives from Core Rules, Full-Mode Requirement, the ledger section, and Blunt Rules into a single authoritative checklist.

Move the per-corpus evidence ledger field list and disposition taxonomy into the already-referenced full-pipeline.md, keeping only the mode-selection and read-first guidance in SKILL.md.

Define or link what an 'official-source discovery step' concretely entails, since the full mode hard-depends on it in six places but the body never specifies it.

Dimension	Reasoning	Score
Conciseness	No time is wasted explaining known concepts, but the body repeats itself heavily: the disposition taxonomy appears twice, 'official-source discovery' is mandated in roughly six separate places, and 'Blunt Rules' restates Core Rules nearly verbatim.	3 / 5
Actionability	Concrete artifacts exist (10-step pipeline, ledger field list, disposition taxonomy), but steps are abstract directives ('run an official-source discovery step per corpus' is never defined) and all operational detail is deferred to support docs that are not part of this bundle.	3 / 5
Workflow Clarity	Clear Read-First order, explicit mode-selection criteria, a numbered 10-step full-mode sequence, and real completion validation ('A full pass is not complete until every scoped corpus has one [disposition]'). Minor gaps remain: steps like 'inspect raw coverage' are unparameterized.	4 / 5
Progressive Disclosure	Support docs (full-pipeline.md, maintain.md, README, index, log) are clearly signaled, one level deep, and framed as sub-workflows; however, ~200 lines of ledger and disposition detail are inlined here that belong in those support docs it already points to.	4 / 5
	Total	14 / 20 Passed

Description

80%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 clearly states both capability and trigger conditions with a distinctive niche. Its main weakness is jargon-heavy trigger terms that may not match how users naturally phrase research-documentation requests.

Suggestions

Replace or supplement internal jargon like 'research upkeep' and 'authority-sensitive corpus work' with natural user phrasings such as 'research notes', 'research docs', or 'updating the research wiki'.

Give the trailing list items ('concepts, systems, decisions') real verbs, e.g. 'create concept and system pages' and 'record decisions'.

Dimension	Reasoning	Score
Specificity	Lists several specific actions ('research-lane creation, research upkeep, authority-sensitive corpus work, source summaries... open-question pages') but trailing items like 'concepts, systems, decisions' are bare nouns without verbs, leaving minor gaps in coverage.	4 / 5
Completeness	Explicitly answers both what ('Operate the docs/research compiled layer in either full or maintain mode') and when ('Use for research-lane creation, research upkeep, ... open-question pages') with concrete trigger items, in third person.	5 / 5
Trigger Term Quality	Keywords are relevant to the domain but lean on internal jargon ('research upkeep', 'authority-sensitive corpus work') and miss natural user phrases and synonyms like 'research notes', 'wiki', or 'research docs'.	3 / 5
Distinctiveness Conflict Risk	Targets a clear niche (the docs/research compiled layer with two modes) with distinct trigger vocabulary; minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: .agents/skills/research-wiki/SKILL.md
Commit: babb3c2

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.