learnings-researcher

Searches docs/solutions/ for relevant past solutions by frontmatter metadata. Use before implementing features or fixing problems to surface institutional knowledge and prevent repeated mistakes.

Quality

72%

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/learnings-researcher/SKILL.md

Quality

Content

77%

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

The content is highly actionable with a clear, well-checkpointed workflow. Its main weaknesses are moderate verbosity from restated rules and inline reference tables, and a broken/missing external schema reference that undermines progressive disclosure.

Suggestions

Move the category-directory and enum-value tables (problem_type/component/root_cause) into the referenced schema file and keep only a one-line pointer, reducing the inline reference material.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of Claude-already-knows padding, but the DO/DON'T lists and Efficiency Guidelines restate the Step 3 branching rules verbatim, and the long inline enum tables inflate the body; it could be tightened without losing clarity.	2 / 3
Actionability	Concrete content-search patterns with exact syntax, a category-narrowing table, ranking criteria, and a copy-pasteable output template give fully executable, specific guidance.	3 / 3
Workflow Clarity	A clear 7-step sequence with explicit branching checkpoints (>25 re-narrow, <3 broaden), a mandatory critical-patterns read (Step 3b), and a relevance gate before full reads provides explicit validation steps and feedback loops.	3 / 3
Progressive Disclosure	The only external reference '../../skills/ce-compound/references/yaml-schema.md' does not exist as a bundle file, and large reference material (the category directories and enum value tables) is inlined rather than split into a referenced file, so structure is present but not cleanly separated.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 solid and grammatically third-person with a clear 'Use before...' trigger, satisfying completeness. It is held back by single-action specificity, slightly generic trigger coverage, and a broad trigger that invites overlap with general research/planning skills.

Suggestions

List more concrete actions to raise specificity, e.g. 'Extracts, ranks, and distills past solutions from docs/solutions/ by frontmatter metadata.'

Add natural trigger variations users actually say, such as 'lessons learned', 'past learnings', or 'avoid repeating a bug' to improve trigger_term_quality.

Tighten the trigger to the skill's niche (e.g. 'Use before implementing features or fixing problems that touch documented modules') to reduce overlap with general research skills.

Dimension	Reasoning	Score
Specificity	Only a single concrete action verb ('Searches docs/solutions/ for relevant past solutions by frontmatter metadata') is named; the remainder is purpose framing, so it names the domain and one action but is not a comprehensive multi-action list.	2 / 3
Completeness	It explicitly answers what ('Searches docs/solutions/ for relevant past solutions by frontmatter metadata') and when ('Use before implementing features or fixing problems'), matching the 'what AND when' anchor.	3 / 3
Trigger Term Quality	'implementing features or fixing problems' are natural user phrases and 'institutional knowledge'/'past solutions' help, but common variations users would say (e.g., 'avoid repeating bugs', 'lessons learned', 'past learnings') are missing.	2 / 3
Distinctiveness Conflict Risk	The docs/solutions/ + frontmatter-metadata niche is distinctive, but the trigger 'implementing features or fixing problems' is broad and could overlap with general planning/research skills, so it could still conflict with similar skills.	2 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 13 / 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

	Total	13 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/learnings-researcher/SKILL.md
Commit: 45116fd

Reviewed: about 14 hours 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.