CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

project-observability-analyzer

Analyze projects and recommend observability integration. Use when adding observability to projects Claude Code works on.

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/project-observability-analyzer/SKILL.md

The canonical home for this skill is project-observability-analyzer in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

61%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 admirably lean and well-sectioned, with a sensible seven-step sequence and a helpful example output. But it stops at the outline level: no executable guidance for any step, no validation of generated files, and framework 'templates' that are named but not provided anywhere.

Suggestions

Add concrete, executable guidance for the key steps — e.g. an actual OTEL instrumentation snippet for Express, a docker-compose observability block, and the detection patterns/commands used to identify frameworks and existing logging libraries.

Add a validation checkpoint after file generation (e.g. 'Verify: docker compose -f docker-compose-with-app.yml config' and 'Run the app and confirm Prometheus metrics endpoint responds') with a fix-and-retry loop.

Either inline the per-framework integration snippets or move them into real reference files (e.g. references/express.md, references/fastapi.md) and link them from the Framework Templates section instead of listing bare names.

DimensionReasoningScore

Conciseness

The ~49-line body has no explanations of concepts Claude already knows and no padding; the Workflow, Example Output, and Framework Templates sections each carry information. Lean and efficient — fits anchor 5.

5 / 5

Actionability

Steps like 'Scan Project Structure (files, dependencies, framework)' and 'Generate Integration Files' are high-level directives with no commands, code, or detection patterns showing how to execute them; the Example Output shows output format, not method; and the four named framework templates exist nowhere (no references/ directory). Specific tool names (Winston, Pino, express-prom-bundle, LGTM) are the only concrete anchors — fits anchor 2, not 3 since there is no executable or even pseudocode-level instruction.

2 / 5

Workflow Clarity

Seven steps are clearly sequenced (scan → detect → analyze → generate), but there are no validation checkpoints — generated docker-compose and instrumentation files are never verified, and file generation is a batch write with no feedback loop. Fits anchor 3, not 4 due to the absent checkpoints.

3 / 5

Progressive Disclosure

Sections are well-organized and the skill is under 50 lines, but the 'Framework Templates' section (Express.js, Next.js, FastAPI, Spring Boot) promises per-framework material that exists neither inline nor in reference files — a dangling pointer. Fits anchor 4, not 5.

4 / 5

Total

14

/

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 answers both what the skill does and when to use it, with a clear observability niche. Its main weaknesses are thin action specificity and sparse trigger vocabulary — no synonyms like monitoring, logging, metrics, tracing, or telemetry that users would naturally say.

Suggestions

Enumerate the concrete capabilities, e.g. 'Scan project structure, detect frameworks and existing logging/observability tooling, and generate OTEL instrumentation, Prometheus metrics, and docker-compose observability integration.'

Broaden trigger terms to include natural synonyms: 'Use when the user mentions observability, monitoring, logging, metrics, tracing, telemetry, Prometheus, Grafana, or OTEL.'

Avoid the generic opener 'Analyze projects' — lead with the observability-specific action to reduce overlap with general code-analysis skills.

DimensionReasoningScore

Specificity

Names the observability domain with two actions ('Analyze projects and recommend observability integration'), but the actions are generic and coverage is not comprehensive — no mention of tracing, metrics, logging, or the concrete integration files the skill produces. Fits anchor 3, not 4 which requires several specific actions.

3 / 5

Completeness

Both 'what' ('Analyze projects and recommend observability integration') and 'when' ('Use when adding observability to projects Claude Code works on') are explicitly present, but the when-clause is narrow and lacks concrete trigger variations. Fits anchor 4, not 5.

4 / 5

Trigger Term Quality

'observability' is a genuinely natural domain keyword, but common variations users would say — 'monitoring', 'logging', 'metrics', 'tracing', 'telemetry', 'Prometheus', 'Grafana', 'OTEL' — are all absent. Fits anchor 3: some relevant keywords, missing common variations and synonyms.

3 / 5

Distinctiveness Conflict Risk

The observability-integration niche has distinct triggers, but the broad opening 'Analyze projects' could overlap with general code-analysis or logging-setup skills. Mostly distinct with minor overlap risk — fits anchor 4, not 5.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

fernandezbaptiste/Skrillz

Path

.claude/skills/project-observability-analyzer/SKILL.md

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.