reduce

Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract insights", "mine this", "process this".

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skill-sources/reduce/SKILL.md

Quality

Content

40%

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

The skill has strong workflow sequencing and concrete tool calls, but it is severely over-long, repetitive, and monolithic with no progressive disclosure or bundle files despite referencing external structures. Token efficiency and reference organization are the main weaknesses.

Suggestions

Collapse the repeated sections (The Mission, Core Distinction, Extraction Question, Quality Gates, Critical) into a single concise statement of principles to recover large amounts of token budget.

Extract the Handoff Mode queue-management detail, Note Design Reference, and Large Source Handling into separate reference files (e.g., references/handoff.md, references/note-design.md) and link to them from a leaner SKILL.md.

Resolve or explain the {vocabulary.*} placeholders inline (or note they are filled from ops/derivation-manifest.md) so the body reads as executable guidance rather than templated meta-content.

Dimension	Reasoning	Score
Conciseness	The body is extremely long (~1100 lines) with heavy repetition of the same directives across 'The Mission', 'Reduce', 'Quality Gates', and 'Critical' sections, re-explaining concepts like the extraction question and skip-rate rule many times over.	1 / 3
Actionability	It provides concrete tool invocations (mcp__qmd__vector_search, qmd vsearch, jq queue updates) and templates, but much guidance is abstract policy and placeholders like {vocabulary.note_plural} that are never resolved, leaving execution partially incomplete.	2 / 3
Workflow Clarity	The 7-step workflow is clearly sequenced with explicit validation checkpoints (size check, semantic duplicate detection, classification, user approval before writing) and a calibration/yield review gate, with feedback loops for risky batch operations.	3 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) yet the body references ops/ files, derivation-manifests, and queue structures; everything is crammed into one monolithic SKILL.md with no one-level-deep separation.	1 / 3
	Total	7 / 12 Passed

Description

82%

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 specific about the extraction mission and supplies concrete trigger terms, but front-loads behavioral policy (skip-rate thresholds) that is runtime guidance rather than capability description, slightly diluting distinctiveness.

Suggestions

Lead with a concise capability statement and move the skip-rate/BUG policy out of the description into the body so the description reads as third-person capability rather than enforcement rules.

Tighten generic triggers like 'process this' with more domain-specific phrasing to reduce overlap with general extraction skills.

Confirm third-person voice throughout — the current description mixes capability ('Extract structured knowledge') with imperative policy ('skip rate must be below 10%'), which weakens specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and the central action ('Extract structured knowledge from source material') plus a behavioral rule, but the concrete actions are stated abstractly rather than as a list of specific operations.	2 / 3
Completeness	It explicitly answers what it does and when to use it via the 'Triggers on...' clause, satisfying both the 'what' and 'when' requirements.	3 / 3
Trigger Term Quality	Includes explicit natural trigger phrases users would actually say ('/reduce', 'extract insights', 'mine this', 'process this'), giving good coverage of invocation terms.	3 / 3
Distinctiveness Conflict Risk	The extraction niche is specific within a knowledge-vault pipeline, but 'process this'/'extract insights' are generic enough to risk overlap with other extraction or summarization skills.	2 / 3
	Total	10 / 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
skill_md_line_count	SKILL.md is long (1120 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: agenticnotetaking/arscontexta
Path: skill-sources/reduce/SKILL.md
Commit: 2acfd5c

Reviewed: 3 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.