CtrlK
BlogDocsLog inGet started
Tessl Logo

learn

Runs a six-phase research workflow that turns unfamiliar domains, source bundles, or collected material into publish-ready output. Use when users ask in any language to research, study, deep-dive, compile sources, synthesize unfamiliar material, or turn a source bundle into a coherent reference. Not for quick lookups or single-file reads.

72

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 content is a well-structured, actionable multi-phase workflow with clear sequencing, explicit feedback loops, and validation checkpoints. Its main weakness is mild redundancy between the Gotchas table and the Hard Rules / Phase sections, and some long inline subsections that could be split into reference files.

Suggestions

Tighten the Gotchas table so each row adds a new failure mode rather than restating the corresponding Hard Rule or Phase guidance (e.g., the native-fetch row overlaps with Phase 1 Fetch).

Consider moving the 'Conversation Or Review Distillation' subsection into a separate reference file and keeping a one-line pointer in Phase 2, improving progressive disclosure now that the body exceeds the simple-skill threshold.

Add one or two concrete command-shaped examples for Phase 1 Discover (e.g., the exact search-plugin invocation pattern) to lift actionability from strong guidance to fully executable.

DimensionReasoningScore

Conciseness

The body is largely lean with short imperatives and no padding of concepts Claude already knows; e.g., 'Generic wisdom is not worth distilling.' earns its place. It is not a 5 because a few Gotchas rows restate Hard Rules / Phase guidance and could be trimmed. Score is above the 3 anchor but not fully lean.

4 / 5

Actionability

Provides concrete, executable guidance: ordered Discover/Fetch/File sub-steps, quantitative targets ('5-10 sources for a blog post, 15-20 for a deep technical survey'), and a decision rule ('Passes two or three: belongs in the outline'). It is instruction-only so absence of code is acceptable, but it stops just short of literal command examples, so not a 5.

4 / 5

Workflow Clarity

Six phases are clearly sequenced (Collect -> Digest -> Outline -> Fill In -> Refine -> Self-review) with explicit validation checkpoints and feedback loops: 'return to Phase 2 for that sub-topic', 'Two passes minimum', Pre-check warnings, and stall signals. This matches the anchor for clear sequence with explicit validation and error-recovery feedback loops.

5 / 5

Progressive Disclosure

Well-organized single-file overview with clear section headers, a mode table, and a Gotchas table; no bundle files exist so there are no nested references to penalize. It is not a 5 because the skill is ~115 lines (above the simple-skill threshold) and inline material like the long 'Conversation Or Review Distillation' subsection could plausibly live in a separate reference file.

4 / 5

Total

17

/

20

Passed

Description

100%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 exemplary: it states a concrete workflow, gives comprehensive bilingual trigger terms, answers both what and when explicitly, and includes a clear negative boundary to avoid overlap with adjacent skills. It uses appropriate third-person voice throughout.

DimensionReasoningScore

Specificity

Names the domain ('six-phase research workflow') and lists multiple concrete actions ('turns unfamiliar domains, source bundles, or collected material into publish-ready output', 'compile sources', 'synthesize unfamiliar material', 'turn a source bundle into a coherent reference'), giving comprehensive coverage rather than just 1-2 actions.

5 / 5

Completeness

Explicitly answers both 'what' (six-phase research workflow producing publish-ready output) and 'when' (Use when users ask... to research, study, deep-dive, compile sources, synthesize) with concrete trigger phrases, and adds a 'Not for quick lookups or single-file reads' boundary.

5 / 5

Trigger Term Quality

Provides comprehensive natural trigger terms in two languages ('research, study, deep-dive, help me understand, compile sources, unfamiliar domain' plus Chinese variants like '学习一下, 深入研究, 整理成文章'), covering synonyms and phrases users would actually say.

5 / 5

Distinctiveness Conflict Risk

Clear niche (multi-source research producing structured output) with distinct triggers and an explicit negative boundary ('Not for quick lookups or single-file reads') that routes single-URL work elsewhere, minimizing conflict risk.

5 / 5

Total

20

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
tw93/Waza
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.