CtrlK
BlogDocsLog inGet started
Tessl Logo

source-command-track-mentions

Search for new online mentions of the Claude Code Ultimate Guide or Florian Bruniaux's public project portfolio and update the relevant tracker

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/source-command-track-mentions/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 is a tightly written, highly actionable 9-step workflow with explicit validation and approval gates, scoring at the top of actionability and workflow clarity. The only soft spot is progressive disclosure: with no bundle files, a larger skill keeps all detail inline where a couple of reference files could offload the prompt template and classification taxonomy.

Suggestions

Move the full Perplexity prompt template and the mention-classification taxonomy into a reference file (e.g. references/prompt-and-classification.md) and link to it from Step 2, keeping the body as an overview.

Trim the classification list in Step 2 slightly or move it to the same reference file to nudge conciseness from 4 toward 5.

Optionally externalize the domain-to-platform inference rules (Step 5) into a small table reference so the body stays a concise overview.

DimensionReasoningScore

Conciseness

Mostly lean imperative instructions with no padding about what a mention or search engine is; the embedded Perplexity prompt and classification taxonomy add some length that could be trimmed, fitting anchor 4 (efficient with minor over-explanation).

4 / 5

Actionability

Fully executable guidance: concrete file paths, a named MCP tool with a parameter, ready-to-run WebSearch queries, an explicit validation command, copy-paste git commands, and a domain-to-platform mapping table covering the common cases, matching anchor 5.

5 / 5

Workflow Clarity

A clear 9-step sequence with an explicit validation checkpoint (Step 8, fail validation => no commit), approval gates, the '--scheduled always wins' precedence rule, and a Notes checklist, satisfying anchor 5 for explicit validation steps and feedback loops.

5 / 5

Progressive Disclosure

No bundle files exist, so all content is inline but well-organized into clear sections (Command Template, Usage, Steps 1-9, Notes); for a ~200-line skill some inline material (prompt template, taxonomy) could be split into reference files, landing at anchor 4 rather than 5.

4 / 5

Total

18

/

20

Passed

Description

53%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 states a clear what and a specific niche but omits any 'Use when...' trigger clause and lacks natural keyword variations, so it sits at the midpoint across most dimensions. Adding an explicit when/trigger phrase and synonyms like 'track' or 'monitor' would lift completeness and trigger_term_quality.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when the user asks to track or monitor new press, media, or online mentions of the guide or portfolio.'

Broaden trigger keywords to include natural synonyms users would say: 'track', 'monitor', 'media mentions', 'press coverage', not just 'search' and 'mentions'.

List a couple more concrete actions (e.g. deduplicate against the existing tracker, classify by type) to push specificity from 1-2 actions toward comprehensive coverage.

DimensionReasoningScore

Specificity

Names the domain ('online mentions', 'tracker') and two concrete actions ('Search for new online mentions', 'update the relevant tracker'), matching anchor 3 for 1-2 concrete actions without comprehensive coverage.

3 / 5

Completeness

Has a clear 'what' (search mentions, update tracker) but no explicit 'Use when...' clause, so per the judging guideline a missing trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Includes some relevant keywords ('mentions', 'search', 'Claude Code Ultimate Guide') but misses common natural variations users would say like 'track', 'monitor', 'media', or 'press', fitting anchor 3.

3 / 5

Distinctiveness Conflict Risk

Proper nouns ('Claude Code Ultimate Guide', 'Florian Bruniaux's public project portfolio') give it a distinct niche with minimal conflict risk, but it is narrower than a general skill niche with broad distinct triggers, landing just below 5.

4 / 5

Total

13

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
FlorianBruniaux/claude-code-ultimate-guide
Reviewed

Table of Contents

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.