skill-knowledge-work

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

Quality

48%

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

Quality

Content

38%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 skill body is a verbose, monolithic narrative describing an external 'Claude Octopus' system with redundant tables and banner examples rather than tight executable guidance for Claude. It lacks validation checkpoints, externalizes its references outside the bundle, and inlines content that should be split into supporting files.

Suggestions

Trim repeated ASCII banner examples and the redundant command/status tables; keep one concise example per concept.

Remove or relocate the Cross-Task Learnings subsystem to a separate reference file, keeping only a one-line pointer in SKILL.md.

Add validation or verification steps where the skill drives state changes (e.g., confirm the override actually took effect, verify a learning file was written valid JSON).

Either move detailed material into real bundle files under references/ and link to them, or if none are needed, cut the inline bulk so the skill reads as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: repeated ASCII banner examples, redundant status and command-reference tables, an opening section that says "you typically don't need this skill", and a full Cross-Task Learnings subsystem explaining JSON fields and budget controls that pads the skill well past what Claude needs.	2 / 5
Actionability	Override commands like `/octo:km on` are concrete, but with `disable-model-invocation: true` they describe an external system Claude cannot execute directly, and the learnings section gives a JSON template with no command to actually write the file, leaving gaps in executable guidance.	3 / 5
Workflow Clarity	Override and status-check steps are listed in sequence, but there are no validation checkpoints or feedback loops, and the learnings-write flow has no verify step, matching the 'steps listed but checkpoints missing' anchor.	3 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets are absent), the only file references (`skills/blocks/codex-host-adapter.md`, `.claude-octopus/learnings/`) point outside the bundle and are not navigable, and substantial detail that belongs in separate files is inlined into a single monolithic document.	2 / 5
	Total	10 / 20 Passed

Description

58%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, but stays at a high level without concrete capability actions or rich trigger synonyms. It is clear and reasonably distinct, just not comprehensive.

Suggestions

Add concrete verbs for what the skill does (e.g., 'research, draft, synthesize, and refine non-code deliverables').

Broaden trigger terms to include natural synonyms a user might say (e.g., reports, strategy docs, briefs, presentations).

Make the when-clause more specific (e.g., 'use when the task is research, writing, or analysis rather than code').

Dimension	Reasoning	Score
Specificity	"Switch to Knowledge Work mode for research and writing" names the domain and a behavior but lists no concrete actions (no verbs like analyze, draft, synthesize), matching the anchor that names the domain with limited concrete actions.	3 / 5
Completeness	Both what ("Switch to Knowledge Work mode for research and writing") and when ("use when task is non-code focused") are present, but the when clause is terse and could be more explicit with concrete triggers, matching the 'both what and when; when could be more explicit' anchor.	4 / 5
Trigger Term Quality	Terms like "research", "writing", and "non-code focused" are natural but the description misses common synonyms and variations a user might say (e.g., report, drafting, strategy), fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"non-code focused" carves a niche but "research and writing" is broad enough to overlap with general writing or research skills, fitting the 'somewhat specific but could still overlap' anchor.	3 / 5
	Total	13 / 20 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: 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.