skill-knowledge-work

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

Quality

58%

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%

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

The skill body communicates its override mechanism and provides usable commands, but it is verbose and descriptive rather than lean and executable. Repeated banner examples and an off-topic learnings section dilute the core guidance.

Suggestions

Cut the repeated 'CLAUDE OCTOPUS ACTIVATED' banner blocks and the tangential 'Cross-Task Learnings' section to improve conciseness; keep one compact example.

Move the auto-detection heuristics and full example set into a separate reference file, leaving SKILL.md as a lean override quick-start.

Tighten the override instructions into a numbered, checkpointed workflow (set override -> verify with '/octo:km' -> proceed) to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly structured but padded with repeated 'CLAUDE OCTOPUS ACTIVATED' banner blocks, marketing prose, and a tangential 'Cross-Task Learnings' section; it could be tightened considerably without losing clarity.	2 / 3
Actionability	Concrete commands are present ('/octo:km on', '/octo:km off', '/octo:km auto') plus a command reference table, but large portions describe behavior and banners rather than giving executable instruction, leaving it incomplete versus the score-3 anchor.	2 / 3
Workflow Clarity	The override flow is sequenced (auto-detect -> override -> check status) but there are no validation checkpoints or feedback loops, and much of the sequencing is implicit/descriptive rather than an explicit checked workflow.	2 / 3
Progressive Disclosure	This is a single monolithic ~225-line file with no bundle files present in references/scripts/assets; example banners, detection logic, and the learnings section are inlined where separate files would aid navigation, matching the score-2 anchor.	2 / 3
	Total	8 / 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 clearly states both what the skill does and when to use it, but its trigger phrasing is somewhat generic and lacks the natural keyword coverage of the best examples. It is a solid, serviceable description with room to sharpen distinctiveness.

Suggestions

Replace 'non-code focused' with concrete natural triggers users would actually say, e.g. 'Use when working on research, strategy docs, PRDs, reports, or presentations rather than code'.

List specific concrete actions (e.g. 'run knowledge research, draft strategy docs, export DOCX/PPTX') to lift specificity from 2 to 3.

Add a sharper distinguishing clause so it does not compete with generic writing/research skills.

Dimension	Reasoning	Score
Specificity	Quotes 'Switch to Knowledge Work mode for research and writing' — it names the domain and a single action (mode switch) but does not list multiple concrete actions like the score-3 anchor requires.	2 / 3
Completeness	Explicitly answers both what ('Switch to Knowledge Work mode for research and writing') and when ('use when task is non-code focused'), matching the score-3 anchor with an explicit 'Use when...' clause.	3 / 3
Trigger Term Quality	Includes 'research and writing' and 'non-code focused', which are somewhat natural, but 'non-code focused' is awkward and common variations (strategy, PRD, report, docs) are absent, matching the score-2 anchor.	2 / 3
Distinctiveness Conflict Risk	The 'research and writing / non-code focused' framing carves out a niche but still overlaps broadly with general writing and research skills, so it is not a clearly distinct trigger set.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-knowledge-work/SKILL.md
Commit: 9f39f0c

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.