CtrlK
BlogDocsLog inGet started
Tessl Logo

dora-metrics

Generate DORA metrics and engineering performance reports using Harness SEI via MCP. Track deployment frequency, lead time, change failure rate, and MTTR. Use when user says "DORA metrics", "deployment frequency", "lead time", "engineering metrics", or asks about team performance.

68

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

Highly actionable content with concrete, complete MCP call examples, a report template, and troubleshooting guidance. The main cost is token efficiency: the six near-duplicate call blocks and the inlined full resource catalog inflate the body without adding instructional value.

Suggestions

Replace the four near-identical primary-metric call blocks with one example plus a note like "substitute metric: lead_time | change_failure_rate | mttr" — the required inputs are already stated once above.

Move the SEI Resource Types table (most rows are non-DORA resources) into a references/ file and keep only the DORA-relevant rows inline.

Fold the Troubleshooting checks (verify integrations, confirm team_ref_id via harness_list) into the workflow steps as explicit validation checkpoints right after Step 1.

DimensionReasoningScore

Conciseness

The four primary-metric call blocks (deployment_frequency, lead_time, change_failure_rate, mttr) and two drilldown blocks are near-identical, differing only in the 'metric' line — roughly 50 lines that could collapse to one example plus a substitution note. No concept over-explanation, so it sits above the verbose anchors but below 'efficient'.

3 / 5

Actionability

Every call block is fully parameterized with all required inputs (team_ref_id, date_start, date_end, granularity), plus concrete team-lookup commands, a copy-paste report template, benchmark tables, and example prompts mapping to exact calls.

5 / 5

Workflow Clarity

Steps 1–4 are clearly sequenced (metric → drilldown → team lookup → optional AI) and Troubleshooting provides error-recovery paths ("Verify SEI integrations are configured", "Confirm team_ref_id belongs to an active SEI team"), but validation guidance lives in a separate section rather than as explicit checkpoints inside the workflow.

4 / 5

Progressive Disclosure

A single-file skill (no bundle files exist) with well-organized, clearly headed sections and no nested or buried references. The 13-row SEI Resource Types table, mostly covering non-DORA resources, is inlined content that would fit better in a separate reference file.

4 / 5

Total

16

/

20

Passed

Description

88%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 strong description: concrete domain-specific actions, explicit trigger guidance, and third-person voice. The main gaps are missing natural synonyms (change failure rate, MTTR) in the trigger list and a slightly broad "team performance" trigger.

Suggestions

Add "change failure rate" and "MTTR" (or "mean time to recovery") to the 'Use when' trigger list since they are natural phrases users say for this exact skill.

Narrow the "asks about team performance" trigger to "engineering performance" or "dev team performance" to reduce collision with general team-performance skills.

DimensionReasoningScore

Specificity

"Generate DORA metrics and engineering performance reports" and "Track deployment frequency, lead time, change failure rate, and MTTR" list multiple concrete actions covering the full DORA domain comprehensively, matching the top anchor.

5 / 5

Completeness

It explicitly answers both "what" (generate DORA metrics reports via Harness SEI MCP) and "when" ("Use when user says 'DORA metrics', 'deployment frequency'...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Triggers "DORA metrics", "deployment frequency", "lead time", "engineering metrics" are natural user phrases, but common variations the description itself names — "change failure rate", "MTTR"/"mean time to recovery" — are missing from the trigger list.

4 / 5

Distinctiveness Conflict Risk

"DORA metrics" plus "Harness SEI" establishes a clear niche with distinct triggers; minor overlap risk remains from the broad "asks about team performance" clause.

4 / 5

Total

18

/

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
harness/harness-ai
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.