skill-knowledge-work

Switch to Knowledge Work mode for research and writing — use when task is non-code focused

Quality

56%

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 ./.claude/skills/skill-knowledge-work/SKILL.md

Quality

Content

50%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 delivers concrete commands and clear context tables but is padded with redundant examples and conceptual explanation. The destructive learnings-pruning step lacks validation, and all content is inlined with no reference-file separation.

Suggestions

Collapse the four near-duplicate auto-detection examples into one concise example; remove repeated banner blocks to tighten conciseness.

Add a validation/checkpoint step before pruning learning files (e.g. confirm count exceeds 50, verify JSON validity) so the destructive batch operation has a feedback loop.

Move the detailed worked examples and Cross-Task Learnings subsystem into separate reference files and link to them one level deep from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The 218-line body is noticeably verbose: four near-duplicate auto-detection examples, repeated banner blocks, and conceptual explanations of Dev vs Knowledge context that Claude could infer, alongside genuinely useful command tables.	2 / 5
Actionability	Provides exact, executable override commands (/octo:km on\|off\|auto) and specific per-context workflow/agent tables with only minor gaps in showing what concretely differs in Knowledge behavior.	4 / 5
Workflow Clarity	The toggle action itself is unambiguous, but the Cross-Task Learnings subsystem performs destructive batch file pruning ('oldest pruned automatically') with no validation checkpoint, which caps workflow clarity at 3 per the batch/destructive guidance.	3 / 5
Progressive Disclosure	Good section headers and a Related Skills list, but no one-level-deep reference files (none exist in the bundle) and content that could be split out (worked examples, learnings subsystem) is inlined rather than pointed to.	3 / 5
	Total	12 / 20 Passed

Description

62%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 cleanly states both what the skill does and when to use it in third-person voice, with a recognizable niche. Its main weakness is generic trigger phrasing and a lack of enumerated concrete actions or synonyms.

Suggestions

Add concrete trigger phrases to the 'when' clause, e.g. 'use when the user mentions research, reports, strategy, PRDs, or market analysis'.

List a few more specific actions (e.g. 'switch context for research, writing, and strategy work') to lift specificity from 3 toward 4-5.

Include synonyms/file-type cues users actually say (e.g. 'research', 'report', 'PRD', 'presentation') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Knowledge Work mode') and a couple of concrete actions ('research and writing') but does not enumerate several specific actions, so it stops at the 'domain + 1-2 actions' anchor rather than reaching 'several specific actions'.	3 / 5
Completeness	Explicitly answers both 'what' ('Switch to Knowledge Work mode for research and writing') and 'when' ('use when task is non-code focused'); the 'when' is explicit but generic rather than concrete trigger phrases, so it sits at 4 rather than 5.	4 / 5
Trigger Term Quality	Includes natural terms ('research', 'writing', 'non-code focused') but lacks common synonyms and variations users might say, fitting 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	Tied to a specific Knowledge-vs-Dev context niche, making it mostly distinct with only minor overlap risk; not a 5 because 'non-code focused' is broad enough to overlap with other research/writing skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-knowledge-work/SKILL.md
Commit: 242e51d

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.