CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

to-tickets

Decompose a PRD issue into tracer-bullet tickets — demoable vertical slices sized to one fresh context window, with blocking edges and HITL/AFK labels, published as GitHub sub-issues. Use after /to-prd when a build spans more than one session; skip it (use /implement directly) when the whole change fits one context window.

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 disciplined, dense instruction-only skill: every rule is a decision rule, the workflow has a genuine human validation gate before publishing, and detail is deliberately deferred to its one home instead of restated. The only meaningful gap is the absence of a worked example (a full gh command or sample ticket body) for the publish step.

DimensionReasoningScore

Conciseness

Every rule is a distinct decision rule and each line earns its place; rationale appears only where it counteracts instinct ("an agent asked to size itself has every incentive to answer 'the strongest one'"). It assumes competence — no space is spent explaining what a PRD, ticket, or DAG is. Not 4: there is no padding to trim.

5 / 5

Actionability

Concrete, executable guidance throughout — "gh issue create", "Part of #<prd>", "Blocked by: #N", "Tier: <tier>", "ready-for-agent", "sh scripts/agents.lib.sh <tier>" — with specific quiz-step content. Not 5: the publish step lacks a full gh invocation with flags, and no example ticket body is shown, leaving minor gaps for the most fragile step.

4 / 5

Workflow Clarity

A five-step procedure with an explicit, mandatory validation checkpoint before the batch publish operation ("Do not publish until they confirm") that specifies exactly what to present (DAG, labels, tier mix) and what to ask the user to challenge. The trust-boundary stop-and-surface rule adds an error-recovery path, so the batch-operation cap does not apply.

5 / 5

Progressive Disclosure

The body is under 50 lines with clean, well-labeled sections, and it defers the tier rubric to its single home with a clearly signaled path and section title ("constitution/local-workflow.md, 'Capability tiers — the cost/benefit call'") rather than duplicating it — exactly the one-level-deep disclosure the rubric rewards. No bundle files exist to verify, but the structure and signaling stand on their own.

5 / 5

Total

19

/

20

Passed

Description

92%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, third-person, with an explicit use/skip condition pair that pins both when it applies and when it does not. The only gap is a handful of missing natural synonyms ("break down", "split") for the trigger terms.

DimensionReasoningScore

Specificity

Names multiple concrete actions and their artifacts — "Decompose a PRD issue into tracer-bullet tickets — demoable vertical slices sized to one fresh context window, with blocking edges and HITL/AFK labels, published as GitHub sub-issues" — covering the transformation, the artifact's specific properties, and the publication mechanism. Not 4: coverage is comprehensive rather than 'several actions with minor gaps'.

5 / 5

Completeness

Explicitly answers both: what ("Decompose a PRD issue into tracer-bullet tickets… published as GitHub sub-issues") and when ("Use after /to-prd when a build spans more than one session; skip it (use /implement directly) when the whole change fits one context window"), including a concrete negative trigger.

5 / 5

Trigger Term Quality

Good natural triggers — "PRD", "tickets", "GitHub sub-issues", "build spans more than one session", "/to-prd" — that a user in this pipeline would actually say. Not 5: common phrasings like "break down the PRD", "split into tickets", or "plan the work" are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche in the /to-prd → /to-tickets → /implement pipeline and explicitly disambiguates against /implement, so it is unlikely to trigger for the wrong skill.

5 / 5

Total

19

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 possibly missing (scripts/agents.config.sh, scripts/agents.lib.sh)

Warning

Total

15

/

16

Passed

Repository

agranado2k/ai-report-platform

Path

.agents/skills/to-tickets/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.