CtrlK
BlogDocsLog inGet started
Tessl Logo

metrics

Expertise in analyzing time-series repository health metrics, investigating root causes, and proposing proactive workflow improvements.

55

Quality

61%

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 ./tools/gemini-cli-bot/.gemini/skills/metrics/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

A well-structured, efficient instruction-only skill with a clear six-step investigation workflow and concrete decision gates. Its weaknesses are the lack of any executable examples or commands, and references to files (bundle/gemini.js) and skills ('prs') that are not organized or signaled within the skill's own structure.

Suggestions

Add one or two concrete example commands or script snippets (e.g., a sample gh/GraphQL query or a one-liner for slicing metrics-timeseries.csv) to move guidance from high-level to executable.

Resolve or clearly signal external dependencies — either ship/reference bundle/gemini.js properly or document exactly how the 'prs' skill and Gemini CLI are invoked, since neither is present in the skill's bundle.

Tighten the Preservation Status paragraph and the MUST/MUST NOT phrasing to reduce redundant conditional language.

DimensionReasoningScore

Conciseness

The body is directive and free of explanations of concepts Claude already knows; every section tells the agent what to do (e.g., 'Load and analyze tools/gemini-cli-bot/history/metrics-timeseries.csv'). It sits at anchor 4 ('efficient; minor instances that could be trimmed') rather than 5 because of mild redundancy — the Preservation Status paragraph and the conditional MUST/MUST NOT phrasing could be tightened, and the Repo Policy Priorities prose repeats ideas stated later.

4 / 5

Actionability

It gives concrete file paths and tool names ('tools/gemini-cli-bot/history/metrics-timeseries.csv', '.github/workflows/', 'gh CLI, GraphQL') but contains no executable commands, example queries, or sample scripts — 'Gather Evidence: Use your tools (e.g., gh CLI, GraphQL) to collect data' is high-level direction without the specific steps. This matches anchor 3 ('some concrete guidance but incomplete; missing key details'); it is above anchor 2 because the paths and decision rules are genuinely specific.

3 / 5

Workflow Clarity

The six numbered instructions give a clear sequence with genuine decision gates — competing hypotheses must be supported or refuted by evidence before selection, and maintainer capacity must be quantified before proposing maintainer-dependent fixes. It is anchor 4 ('clear sequence with most checkpoints present; minor validation gaps') rather than 5 because there is no explicit validation step for outputs (e.g., verifying modified scripts still emit the comma-separated format is stated as a constraint, not a checkpoint).

4 / 5

Progressive Disclosure

The body is well-sectioned but monolithic at ~110 lines with no bundle files at all — yet it references 'the Gemini CLI (bundle/gemini.js)' and an external 'prs' skill whose availability is not signaled from this skill's structure. This matches anchor 3 ('some structure but could be better organized; references present but not clearly signaled'); it does not reach anchor 4 because the referenced paths are not clearly organized or discoverable within the skill bundle.

3 / 5

Total

14

/

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.

A concise, third-person description that clearly states what the skill does with three concrete verbs in a specific domain. Its main weakness is the complete absence of a 'when to use' trigger clause and of natural trigger-term variations users would actually say.

Suggestions

Add an explicit trigger clause, e.g., 'Use when analyzing repository health trends, investigating metric anomalies or deteriorating trends, or planning proactive workflow improvements.'

Include natural synonyms users would say — 'trends', 'anomalies', 'DORA metrics', 'CI/Actions spend', 'maintainer workload' — to improve trigger-term coverage.

Mention the concrete sub-capabilities (trend/anomaly detection, hypothesis testing, cost monitoring) to close the coverage gap between the description and the body.

DimensionReasoningScore

Specificity

The description lists three concrete actions — "analyzing time-series repository health metrics", "investigating root causes", and "proposing proactive workflow improvements" — in a clearly named domain. It matches anchor 4 ('several specific actions; minor gaps') rather than 5 because it omits supporting capabilities like trend/anomaly detection, cost monitoring, and maintainer-workload assessment that the body actually covers.

4 / 5

Completeness

The 'what' is clearly stated (analyze metrics, investigate root causes, propose improvements), but there is no 'Use when...' or equivalent trigger clause, so 'when' is entirely absent. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3, which matches the anchor ('clear what, when missing').

3 / 5

Trigger Term Quality

Relevant keywords exist ("repository health metrics", "root causes", "workflow improvements") but common natural variations users would say are missing — e.g., "trends", "anomalies", "DORA metrics", "CI costs", "time-series data". This matches anchor 3 ('some relevant keywords but missing common variations or synonyms'); it is above anchor 2 because the terms present are domain-specific rather than generic filler.

3 / 5

Distinctiveness Conflict Risk

The framing "time-series repository health metrics" plus "root causes" carves a fairly distinct niche with specific triggers, though "proposing proactive workflow improvements" is broad enough to overlap with general code-review or CI-optimization skills. This is anchor 4 ('mostly distinct; minor overlap risk') rather than 5 because the workflow-improvement half is somewhat generic.

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
google-gemini/gemini-cli
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.