CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/release-runbook-author

Turns one service's release into a written six-phase runbook: pre-flight checks, a smoke gate, a canary observation window, a named human promote gate, progressive rollout, and post-release verification. Fixes each phase's pass criteria as a delta against a recorded baseline rather than a bare absolute number, gives canary and rollout separate windows and separate thresholds, and emits a per-phase evidence table that becomes the release record. Use when a single service is about to ship and its release steps exist only as tribal knowledge or a chat thread, so nobody can say in advance what evidence promotes it, what evidence halts it, or who decides.

75

Quality

94%

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

Overview
Quality
Evals
Security
Files

Quality

Content

85%

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 well-structured, actionable six-phase runbook with concrete templates, clear validation checkpoints, and clean one-level-deep references, scoring at the top anchor on actionability, workflow clarity, and progressive disclosure. Its only weakness is conciseness — the long per-phase prose could be tightened without losing substance.

Suggestions

Tighten the explanatory prose in each phase section: convert multi-sentence rationales into one-line rules where the supporting citation already carries the argument, trimming the ~360-line body toward a leaner core.

Consider moving the extended published-source quotations (e.g., the multi-line Azure/Google SRE citations repeated across phases) into a single consolidated 'Sources' reference, keeping inline only the operative rule each citation justifies.

Pull the dense phase-by-phase conventions (traffic share, window length, metric selection) into the worked-example or output-template reference so the main body reads as the overview it is meant to be.

DimensionReasoningScore

Conciseness

The body is substantive and mostly earns its tokens with specialized release-engineering practice, but the ~360 lines of explanatory prose around each phase could be tightened; it sits at 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than 'every token earns its place'.

2 / 3

Actionability

Concrete, copy-paste-ready artifacts abound: a fully fleshed canary observation table with example values, a three-option promote-gate decision table, a pre-flight evidence table, an 11-row defect checklist, and a separate output template — actionable guidance without relying on code.

3 / 3

Workflow Clarity

A clearly sequenced six-phase workflow with explicit validation at each gate and a feedback loop ('A threshold trip during rollout halts the expansion and returns to phase 4's decision table'), plus the 'Before the runbook is usable' checklist, matches 'clear sequence with explicit validation steps; feedback loops for error recovery'.

3 / 3

Progressive Disclosure

The body is an overview that signals three real one-level-deep references — references/worked-example.md, references/output-template.md, references/anti-patterns.md (all present on disk) — each with a descriptive lead-in, so content is appropriately split and navigation is easy.

3 / 3

Total

11

/

12

Passed

Description

100%

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 is specific, uses third-person voice, and explicitly pairs concrete capabilities with a 'Use when' trigger, scoring at the top anchor on every dimension. Its distinctiveness is strong because the single-service release-runbook niche is clearly bounded.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'pre-flight checks, a smoke gate, a canary observation window, a named human promote gate, progressive rollout, and post-release verification' plus 'fixes each phase's pass criteria as a delta against a recorded baseline' and 'emits a per-phase evidence table' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly answers both what ('Turns one service's release into a written six-phase runbook...') and when via an explicit 'Use when...' clause, matching the 'clearly answers both what AND when with explicit triggers' anchor.

3 / 3

Trigger Term Quality

Natural trigger phrasing a user would actually say appears explicitly: 'Use when a single service is about to ship and its release steps exist only as tribal knowledge or a chat thread', giving good coverage of terms like 'service is about to ship', 'release steps', and 'tribal knowledge'.

3 / 3

Distinctiveness Conflict Risk

A clear, narrow niche (single-service release runbook) with distinct triggers; it even self-distinguishes by scope ('a single service is about to ship'), so it is unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents