skill-context-detection

Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type

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-context-detection/SKILL.md

Quality

Content

62%

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

The skill presents a well-sequenced detection algorithm with clear fallback logic and a feedback loop, but it is monolithic and verbose — the core detection logic stays as prose/pseudocode and large reusable tables/templates are inlined rather than split into reference files.

Suggestions

Collapse the duplicate 'Example Integration (Pseudocode)' section and the redundant full banner blocks; keep one concise banner template and reference it.

Provide executable detection logic (e.g., a runnable bash or script that scores prompt indicators and emits the JSON output) instead of leaving the main algorithm as prose and pseudocode.

Move the phase-behavior tables, banner templates, and proactive-suggestion table into reference files under references/ and link to them one level deep to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The ~270-line body restates the detection algorithm twice (detailed steps then an 'Example Integration (Pseudocode)' section) and includes three near-identical full banner blocks plus repeated phase tables, so it is padded and could be tightened despite being domain-specific rather than explaining basic concepts.	2 / 3
Actionability	It provides concrete bash for the override check, a JSON output schema, and explicit indicator/file-type lists, but the core Step 2/3 detection logic is a prose counting heuristic and the integration example is labeled pseudocode rather than executable code.	2 / 3
Workflow Clarity	The algorithm is a clearly numbered 4-step sequence with explicit scoring rules, tie-breaking to Step 3, a default fallback in Step 4, confidence levels, and a low-confidence feedback prompt to the user — a clear sequenced process with a feedback loop.	3 / 3
Progressive Disclosure	There are no bundle files (references/, scripts/, assets/ absent) and the skill is monolithic at ~270 lines with content that could be split (phase tables, banner templates, suggestion tables) kept inline, though section headers keep it reasonably organized.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 identifies a reasonably specific niche and purpose but lacks explicit trigger guidance and natural user keywords, leaving every dimension at the middle level. It is informative but not yet optimized for discovery or triggering.

Suggestions

Add an explicit 'Use when ...' trigger clause naming natural user phrases (e.g., 'Use when starting a research, planning, or build task to decide between dev-focused and knowledge-focused workflows').

Replace skill-internal jargon ('Dev vs Knowledge context', 'task type') with terms a user would actually say ('research vs implementation', 'strategy vs coding', 'documentation vs code').

Name the concrete detection actions it performs (analyze the prompt, inspect project files, respect an explicit override) to lift specificity toward level 3.

Dimension	Reasoning	Score
Specificity	It names the domain and an action ("Auto-detect work context (Dev vs Knowledge)" and "tailor workflows based on current task type"), but "tailor workflows" is abstract and it does not list multiple specific concrete actions like the level-3 anchor requires.	2 / 3
Completeness	It states what the skill does (auto-detect context) and gives a purpose clause ("use to tailor workflows based on current task type"), but there is no explicit "Use when..." trigger guidance, so completeness caps at 2 per the judging guideline.	2 / 3
Trigger Term Quality	"work context", "Dev vs Knowledge", and "task type" are only borderline natural phrases a user would say; they lean toward skill-internal jargon and miss common natural variations, matching the level-2 anchor rather than the level-1 only because some recognizable terms exist.	2 / 3
Distinctiveness Conflict Risk	The Dev-vs-Knowledge detection niche is somewhat specific, but as a meta/orchestration skill with no distinct user-facing triggers it could still overlap with other workflow skills, matching the level-2 anchor.	2 / 3
	Total	8 / 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-context-detection/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.